天游平台

  • <meter id="382q6"><strong id="382q6"><del id="382q6"></del></strong></meter>
    <meter id="382q6"><delect id="382q6"><p id="382q6"></p></delect></meter>
    <mark id="382q6"><button id="382q6"></button></mark>
  • <mark id="382q6"><u id="382q6"></u></mark>

  • <small id="382q6"></small>
    <label id="382q6"></label>
    <output id="382q6"><button id="382q6"><span id="382q6"></span></button></output>
      <code id="382q6"></code>
        1. <output id="382q6"></output>
          <tt id="382q6"></tt><mark id="382q6"><u id="382q6"></u></mark>
            CONFERENCE
            Area 1 - Intelligent Control Systems and Optimization
            Area 2 - Robotics and Automation
            Area 3 - Signal Processing, Systems Modeling and Control
             
            SPECIAL SESSIONS
            Special Session on Service Oriented Architectures for SMErobots and Plug-and-Produce
            Special Session on Multi-Agent Robotic Systems
             
            WORKSHOPS
            Workshop on Artificial Neural Networks and Intelligent Information Processing (ANNIIP)
            Workshop on Intelligent Vehicle Control Systems (IVCS)
             
            Area 1 - Intelligent Control Systems and Optimization
            Title:
            MOTOR PARAMETERS INFLUENCE ON STABILITY OF DRIVE FOR INDUSTRIAL ROBOT
            Author(s):
            Sorin Enache, Monica Adela Enache, Mircea Dobriceanu, Mircea Adrian Drighiciu and Anca Petrisor
            Abstract:
            This paper analyzes a driving system for an industrial robot from the stability point of view. For doing this, an original analysis method has been conceived. The method has as starting point the two axes mathematical model with equations written in per unit values. A Matlab program has been conceived with their help; this program has led to results and conclusions detailed in this paper. Finally a series of experimental results confirming the conclusions deduced with the new method are presented.

            Title:
            EVOLUTION OF A MOBILE ROBOT’S NEUROCONTROLLER ON THE GRASPING TASK - Is Genetic also Generic?
            Author(s):
            Philippe Lucidarme
            Abstract:
            This paper presents a survey on the generic evolution of mobile robot’s neurocontrollers with a particular focus on the capacity to adapt these controllers in several environments. Several experiments on the example of the grasping task (autonomous vacuum cleaner for example) are performed and the results show that the produced neurocontroller is dedicated to the trained conditions and cannot be considered as generic. The last part of the paper discusses of the necessary changes in the fitness function in order to produce generic neurocontrollers.

            Title:
            OPTIMAL CONTROL WITH ADAPTIVE INTERNAL DYNAMICS MODELS
            Author(s):
            Djordje Mitrovic, Stefan Klanke and Sethu Vijayakumar
            Abstract:
            Optimal feedback control has been proposed as an attractive movement generation strategy in goal reaching tasks for anthropomorphic manipulator systems. The optimal feedback control law for systems with non-linear dynamics and non-quadratic costs can be found by iterative methods, such as the iterative Linear Quadratic Gaussian (iLQG) algorithm. So far this framework relied on an analytic form of the system dynamics, which may often be unknown, difficult to estimate for more realistic control systems or may be subject to frequent systematic changes. In this paper, we present a novel combination of learning a forward dynamics model within the iLQG framework. Utilising such adaptive internal models can compensate for complex dynamic perturbations of the controlled system in an online fashion. The specific adaptive framework introduced lends itself to a computationally more efficient implementation of the iLQG optimisation without sacrificing control accuracy - allowing the method to scale to large DoF systems.

            Title:
            LHTNDT: LEARN HTN METHOD PRECONDITIONS USING DECISION TREE
            Author(s):
            Fatemeh Nargesian and Gholamreza Ghassem-Sani
            Abstract:
            In this paper, we describe LHTNDT, an algorithm that learns the preconditions of HTN methods by examining plan traces produced by another planner. LHTNDT extracts conditions for applying methods by using decision tree algorithm. It considers the state of relevant domain objects in both current and goal state. Structurally repetitive training samples are removed using graph isomorphism. In our experiments, LHTNDT converged. It can learn most of preconditions correctly and almost quickly. Approximately 80% of test problems can be solved by preconditions extracted by ?of plan traces needed for full convergence.

            Title:
            FEEDING A GENETIC ALGORITHM WITH AN ANT COLONY FOR CONSTRAINED OPTIMIZATION - An Application to the Unit Commitment Problem
            Author(s):
            Guillaume Sandou, Stéphane Font, Sihem Tebbani, Arnaud Hiret and Christian Mondon
            Abstract:
            In this paper, a new optimisation strategy for the solution of the classical Unit Commitment problem is proposed. This problem is known to be an often large scale, mixed integer programming problem. Due to high combinatorial complexity, the exact solution is often intractable. Thus, a metaheuristic based method has to be used to compute a very often suitable solution. The main idea of the approach is to use ant colony algorithm, to explicitly deal with the feasibility of the solution, and to feed a genetic algorithm whose goal is to intensively explore the search space. Finally, results show that the proposed method leads to the tractable computation of satisfying solutions for the Unit Commitment problem.

            Title:
            SELF-ORGANISATION OF GAIT PATTERN TRANSITION - An Efficient Approach to Implementing Animal Gaits and Gait Transitions
            Author(s):
            Zhijun Yang, Juan Huo and Alan Murray
            Abstract:
            As an engine of almost all life phenomena, the motor information generated by the central nervous system (CNS) plays a critical role in the activities of all animals. Despite the difficulty of being physically identified, the central pattern generator (CPG), which is a concrete branch of studies on the CNS, is widely recognised to be responsible for generating rhythmic patterns. This paper presents a novel, macroscopic and model-independent approach to the retrieval of different patterns of coupled neural oscillations observed in biological CPGs during the control of legged locomotion. Based on the simple graph dynamics, various types of oscillatory building blocks (OBB) can be reconfigured for the production of complicated rhythmic patterns. Our quadrupedal locomotion experiments show that an OBB-based artificial CPG model alone can integrate all gait patterns and undergo self-organised gait transition between different patterns.

            Title:
            REDUCED ORDER H∞ SYNTHESIS USING A PARTICLE SWARM OPTIMIZATION METHOD
            Author(s):
            Guillaume Sandou, Gilles Duc and Patrick Boucher
            Abstract:
            Hinfinity controller synthesis is a well known design method for which efficient dedicated methods have been developed. However, such methods compute a full order controller which has often to be reduced to be implemented. Indeed, the reduced order Hinfinity synthesis is a non convex optimization problem due to rank constraints. In this paper, a particle swarm optimization method is used to solve such a problem. Numerical results show that the computed controller has a lower Hinfinity norm than the controller computed from a classical Hankel reduction of the full order Hinfinity controller.

            Title:
            OBTAINING MINIMUM VARIABILITY OWA OPERATORS UNDER A FUZZY LEVEL OF ORNESS
            Author(s):
            Kaj-Mikael Björk
            Abstract:
            Finding the optimal OWA (ordered weighted averaging) operators is important in many decision support problems. The OWA-operators enables the decision maker to model very different kinds of aggregator operators. The weights need to be, however, determined under some criteria, and can be found through the solution of some optimization problems. The important parameter called the level of orness may, in many cases, be uncertain to some degree. Decision makers are often able to estimate the level using fuzzy numbers. Therefore, this paper contributes to the current state of the art in OWA operators with a model that can determine the optimal (minimum variability) OWA operators under a (unsymmetrical triangular) fuzzy level of orness.

            Title:
            SYNCHRONIZATION OF ARM AND HAND ASSISTIVE ROBOTIC DEVICES TO IMPART ACTIVITIES OF DAILY LIVING TASKS
            Author(s):
            Duygun Erol and Nilanjan Sarkar
            Abstract:
            Recent research in rehabilitation indicates that tasks that focus on activities of daily living (ADL) is likely to show significant increase in motor recovery after stroke. Most ADL tasks require patients to coordinate their arm and hand movements to complete ADL tasks. This paper presents a new control approach for robot assisted rehabilitation of stroke patients that enables them to perform ADL tasks by providing controlled and coordinated assistance to both arm and hand movements. The control architecture uses hybrid system modelling technique which consists of a high-level controller for decision-making and two low-level assistive controllers (arm and hand controllers) for arm and hand motion assistance. The presented controller is implemented on a test-bed and the results of this implementation are presented to demonstrate the feasibility of the proposed control architecture.

            Title:
            DATA MINING AND KNOWLEDGE DISCOVERY FOR MONITORING AND INTELLIGENT CONTROL OF A WASTEWATER TREATMENT PLANT
            Author(s):
            S. Manesis, V. Deligiannis and M. Koutri
            Abstract:
            Intelligent control of medium-scale industrial processes has been applied with success but, as a method of advanced control, can be further improved. Since intelligent control makes use of knowledge-based techniques (such as expert systems, fuzzy logic, neural networks, etc.), a data mining and knowledge discovery subsystem embedded in a control system can support an intelligent controller to achieve a more reliable and robust operation of the controlled process. This paper proposes a combined intelligent control and data mining scheme for monitoring and mainly for controlling a wastewater treatment plant. The intelligent control system is implemented in a programmable logic controller, while the data mining and knowledge discovery system in a personal computer. The entire control system is basically a knowledge-based system which improves drastically the behavior of the wastewater treatment plant.

            Title:
            CONTROLLING INVESTMENT PROPORTION IN CYCLIC CHANGING ENVIRONMENTS
            Author(s):
            J.-Emeterio Navarro-Barrientos
            Abstract:
            In this paper, we present an investment strategy to control investment proportions for environments with cyclic changing returns on investment. In our approach, we consider an investment model where the agent decides at every time step the proportion of wealth to invest in a risky asset, keeping the rest of the budget in a risk-free asset. Every investment is evaluated in the market modeled by stylized returns on investment (RoI). For comparison reasons, we present two reference strategies which represent the case of agents with zero-knowledge and complete-knowledge of the dynamics of the RoI, and we consider also an investment strategy based on technical analysis. To account for the performance of the different strategies, we perform some computer experiments to calculate the average budget that can be obtained over a certain number of time steps. To assure for fair comparisons, we first tune the parameters of each strategy. Afterwards, we compare their performance for RoIs with fixed periodicity (stationary scenario) and for RoIs with changing periodicities (non-stationary scenario).

            Title:
            ENERGY MODEL BASED CONTROL FOR FORMING PROCESSES
            Author(s):
            Patrick Girard and Vincent Thomson
            Abstract:
            Thermoforming consists of shaping a plastic material by deforming it at an adequate deformation rate and temperature. It often exhibits abrupt switches between stable and unstable material behaviour that have neither been identified nor controlled up to now. PID control, although adequate for simple parts, has not been able to control very well the forming of complex parts and parts made of newer materials. In this paper, the state parameters that allow the development of predictive models for the forming process and the construction of control systems are identified. A robust, model based control system capable of in-cycle control is presented. It is based on a simulator continuously tuned and supported in real time by intelligent agents that incorporate diagnostic capabilities.

            Title:
            AUTOMATED SIZING OF ANALOG CIRCUITS BASED ON GENETIC ALGORITHM WITH PARAMETER ORTHOGONALIZATION PROCEDURE
            Author(s):
            Masanori Natsui and Yoshiaki Tadokorot
            Abstract:
            This paper presents a method for the automated sizing of analog circuits using genetic algorithm (GA). GA is a kind of optimization techniques based on natural selection and genetics. For the rapid and efficient exploration of GA, we introduce the idea of search space sphering and dimension reduction with principal component analysis (PCA). The potential capability of the system is demonstrated through the automated sizing of wide-swing current mirror circuit. Experimental results show that the search space optimization using PCA improves the search efficiency of the system, and the system can estimate sub-optimal parameter set successfully.

            Title:
            DESIGN OF NEURONAL NETWORK TO CONTROL SPIRULINA AQUACULTURE
            Author(s):
            Ernesto Ponce, Claudio Ponce and Bernardo Barraza
            Abstract:
            A neural network that was designed to control a Spirulina aquaculture process in a pilot plant in the north of Chile, is presented in this work. Spirulina is a super food, but is a delicate alga and its culture may be suddenly lost by rapid changes in the weather that can affect its temperature, salinity or pH. The neural network control system presented is complex and non linear, and has several variables. The previous automatic control system for the plant proved unable to cope with large climatic variations. The advantage of this new method is the improvement in efficiency of the process, and a reliable control system that is able to adapt to climatic changes. The future application of this work is related to the industrial production of food and fuel from micro algae culture, for the growing world population.

            Title:
            NONLINEAR SYSTEM IDENTIFICATION USING DISCRETE-TIME NEURAL NETWORKS WITH STABLE LEARNING ALGORITHM
            Author(s):
            Talel Korkobi, Mohamed Djemel and Mohamed Chtourou
            Abstract:
            This paper presents a stable neural sytem identification for nonlinear systems. An input output discrete time representation is considered. No a priori knowledge about the nonlinearities of the system is assumed. The proposed learning rule is a the backpropagation algorithm under the condition tha the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomenon during the learning process is avoided. A Lyapunov analysis is made in order to extract the new updating formulations which contain a set of inequality constraints. In the constrained learning rate algorithm, the learning rate is updated at each iterative instant by an equation derived using the stability conditions. As a case study, identification of two discrete time systems are considered to demonstrate the effectiveness of the proposed algorithm. Simulation results concerning the considered systems are presented.

            Title:
            IMPROVEMENTS IN THE FIELD OF DEVICE INTEGRATION INTO AUTOMATION SYSTEMS WITH EMBEDDED WEB INTERFACES
            Author(s):
            Anton Scheibelmasser, Jürgen Menhart and Bernd Eichberger
            Abstract:
            Web-Technologies which came up in many fields of automation seem to be a solution which improves device integration in many ways. On the one hand the used Ethernet improves the installation techniques with reliable and approved network cables and routing devices. On the other hand the used internet protocols provide several services for the application software development. With the introduction of those services, the local controller of the measurement devices has to execute complex communication protocols in addition to the device specific tasks. This fact has serious influences on the measurement device instrumentation and the execution of the device firmware. Concerning new developments and compatible adaptations of existing instruments several ways for the integration of web technologies are available. The following article is intended to explain the architectural aspects of device integrations using Industrial Ethernet by means of an embedded web server. As a practical example to this architecture, concepts and results of a new developed communication module called EWI (embedded web interface) are given to demonstrate the improvements in measurement device integration in the field of automotive test bed automation.

            Title:
            MERGING OF ADVICES FROM MULTIPLE ADVISORY SYSTEMS - With Evaluation on Rolling Mill Data
            Author(s):
            Pavel Ettler, Josef Andrýsek, Václav Šmídl and Miroslav Kárn?/DIV>
            Abstract:
            The problem of evaluation of advisory system quality is studied. Specifically, 18 advisory strategies for operators of a cold rolling mill were designed using different modelling assumptions. Since some assumptions may be more appropriate in different working regimes, we also design a new advising strategy based on on-line merging of advices. In order to measure actual suitability of the advisory systems, we define two measures: operator’s performance index and coincidence of the observed operator’s actions with the advices. A time-variant model of advisory system suitability is proposed. Merging of the advices is achieved using Bayesian theory of decision-making. Final assessment of the original advisory systems and the new system is performed on data recorded during 6 months of operation of a real rolling mill. This task is complicated by the fact that the operator did not follow any of the advisory systems. Validation was thus performed with respect to the proposed measures. It was found that merging of the advising strategies can significantly improve quality of advising. The approach is general enough to be used in many similar problems.

            Title:
            MATHEMATICAL MODELLING OF THERMAL AREA IN CUTTING TOOL
            Author(s):
            Daschievici Luiza, Ghelase Daniela and Goanta Adrian
            Abstract:
            Since experimental researches regarding cutting process have stated a proportionality dependence of wear medium intensity on cutting area temperature and because this fact was avoid or ignored by thorough studies and researches, we considered to be helpful developing a physical-mathematical model able to correlate the two phenomena: wear and temperature in the cutting area. The complete and correct research on thermal phenomena in the cutting area is possible only by taking into consideration the feed-back relation between the physical and phenomenological elements of the studied tribosystem and also, by taking into account the splinter movement, resulting in a continuous supplying with cold layers of the splinter area and in heat evacuating by warm splinter movement.

            Title:
            A DISTRIBUTED FAULT TOLERANT POSITION CONTROL SYSTEM FOR A BOAT-LIKE INSPECTION ROBOT
            Author(s):
            Christoph Walter, Tino Krueger and Norbert Elkmann
            Abstract:
            Here we present the position control system of a swimming inspection robot for large under-ground con-crete pipes that are partially filled with waste water. The system consists of a laser-based measurement sub-system for position determination and a mechanical rudder to move the robot laterally within the pipe. The required software components are implemented as services following a CORBA-based architecture. To automatically adapt to different environment conditions a self tuning controller with hybrid requirements regarding latency and interarrival times of computed position values is used. We describe the architectural support for this type of application as well as how the system deals with ex-cessive latencies due to transient overload.

            Title:
            SMART SEMANTIC MIDDLEWARE FOR THE INTERNET OF THINGS
            Author(s):
            Artem Katasonov, Olena Kaykova, Oleksiy Khriyenko, Sergiy Nikitin and Vagan Terziyan
            Abstract:
            As ubiquitous systems become increasingly complex, traditional solutions to manage and control them reach their limits and pose a need for self-manageability. Also, heterogeneity of the ubiquitous components, standards, data formats, etc, creates significant obstacles for interoperability in such complex systems. The promising technologies to tackle these problems are the Semantic technologies, for interoperability, and the Agent technologies for management of complex systems. This paper describes our vision of a middleware for the Internet of Things, which will allow creation of self-managed complex systems, in particular industrial ones, consisting of distributed and heterogeneous components of different nature. We also present an analysis of issues to be resolved to realize such a middleware.

            Title:
            A GENETIC ALGORITHM APPLIED TO THE POWER SYSTEM RESTORATION PLANNING PROBLEM - A Metaheuristic Approach for a Large Combinatorial Problem
            Author(s):
            Adelmo Cechin, Jos?Vicente Canto dos Santos, Arthur Tórgo Gómez and Carlos Mendel
            Abstract:
            This work reports the development of a Genetic Algorithm (GA) to solve the Power Systems Restoration Planning Problem (PSRP). The solution of the PSRP is a plan that informs to the Power System operator strategies or operation plans to be used after the occurrence of interruptions in the electrical energy transmission. The GA generates sequences of operations which are analyzed by a Power Flow program to verify and access their fitness. For this GA, a new genoma representation was developed, as well as two genetic operators, for crossover and mutation. This is one of the main contributions of this work. Tests performed with different electric networks shown the validity of the proposal.

            Title:
            FAIR AND EFFICIENT RESOURCE ALLOCATION - Bicriteria Models for Equitable Optimization
            Author(s):
            Włodzimierz Ogryczak
            Abstract:
            Resource allocation problems are concerned with the allocation of limited resources among competing activities so as to achieve the best performances. In systems which serve many users there is a need to respect some fairness rules while looking for the overall efficiency. The so-called Max-Min Fairness is widely used to meet these goals. However, allocating the resource to optimize the worst performance may cause a dramatic worsening of the overall system efficiency. Therefore, several other fair allocation schemes are searched and analyzed. In this paper we focus on mean-equity approaches which quantify the problem in a lucid form of two criteria: the mean outcome representing the overall efficiency and a scalar measure of inequality of outcomes to represent the equity (fairness) aspects. The mean-equity model is appealing to decision makers and allows a simple trade-off analysis. On the other hand, for typical dispersion indices used as inequality measures, the mean-equity approach may lead to inferior conclusions with respect to the outcomes maximization (system efficiency). Some inequality measures, however, can be combined with the mean itself into optimization criteria that remain in harmony with both inequality minimization and maximization of outcomes. In this paper we introduce general conditions for inequality measures sufficient to provide such an equitable consistency. We verify the conditions for the basic inequality measures thus showing how they can be used not leading to inferior distributions of system outcomes.

            Title:
            LOSS MINIMIZATION OF INDUCTION GENERATORS WITH ADAPTIVE FUZZY CONTROLLER
            Author(s):
            Durval de Almeida Souza*, Jos?Antonio Dominguez Navarro** and Jesús Sallán Arasanz
            Abstract:
            In this paper a new technique for efficiency optimization of induction generator working a variable speed and load is introduced. The technique combines two distinct control methods, namely, on-line search of the optimal operating point, with a model based efficiency control. For a given operating condition, characterized by a given speed (m) and load torque (TL), the search control is implemented via the “Rosenbrock?method, which determines the flux level that results in the maximum output power. Once the optimal flux level has been found, this information is utilized to update the rule base of a fuzzy controller, which plays the role of an implicit mathematical model of the system. Initially, for any load condition the rule base yields the rated flux value. As the optimum points associated with the several operating conditions are identified, the rule base is progressively updated, such that the fuzzy controller learns to model the optimal operating conditions for the entire torque-speed plane. After every rule base update, the Rosenbrock controller output is reset, but it is kept active to track possible minor deviations of the optimum point.

            Title:
            LEARNING DISCRETE PROBABILISTIC MODELS FOR APPLICATION IN MULTIPLE FAULTS DETECTION
            Author(s):
            Luis E. Garza Castañón, Francisco J. Cant?Ortíz and Rubén Morales-Menéndez
            Abstract:
            We present a framework to detect faults in processes or systems based on probabilistic discrete models learned from data. Our work is based on a residual generation scheme, where the prediction of a model for process normal behavior is compared against measured process values. The residuals may indicate the presence of a fault. The model consists of a general statistical inference engine operating on discrete spaces, and represents the maximum entropy joint probability mass function (pmf) consistent with arbitrary lower order probabilities. The joint pmf is a rich model that, once learned, allows us to address inference tasks, which can be used for prediction applications. In our case the model allows the one step-ahead prediction of process variable, given its past values. The relevant dependencies between the forecast variable and past values are learnt by applying an algorithm to discover discrete bayesian network structures from data. The parameters of the statistical engine are also learn by an approximate method proposed by Yan and Miller. We show the performance of the prediction models and their application in power systems fault detection.

            Title:
            GPC AND NEURAL GENERALIZED PREDICTIVE CONTROL
            Author(s):
            S. Chidrawar, Nikhil Bidwai, L. Waghmare and B. M. Patre
            Abstract:
            As Model Predictive Control (MPC) relies on the predictive Control using a multilayer feed forward network as the plants linear model is presented. In using Newton-Raphson as the optimization algorithm, the number of iterations needed for convergence is significantly reduced from other techniques. This paper presents a detailed derivation of the Generalized Predictive Control and Neural Generalized Predictive Control with Newton-Raphson as minimization algorithm. Taking two separate systems tested the performances of the system. Simulation result show the effect of Neural network on Generalized Predictive Control. The performance comparison of these two-system configurations has been given in terms of ISE and IAE.

            Title:
            COGNITIVE TECHNICAL SYSTEMS IN A PRODUCTION ENVIRONMENT - Outline of a Possible Approach
            Author(s):
            Eckart Hauck, Arno Gramatke and Klaus Henning
            Abstract:
            High-Wage countries face the dilemmas of value- vs. planning orientation and the dilemma of economies of scale vs. economies of scope summed up in the term polylemma. To reduce the dilemma of planning vs. value orientation cognitive technical systems seem to be a promising approach. In this paper the requirements of such a cognitive system in a production environment is presented. Furthermore a first concept of a software architecture is given. To implement a knowledge base for a cognitive technical system certain formalism were scrutinized for their suitability in this approach and a possible use case for such a cognitive technical system is presented.

            Title:
            SELF CONSTRUCTING NEURAL NETWORK ROBOT CONTROLLER BASED ON ON-LINE TASK PERFORMANCE FEEDBACK
            Author(s):
            Andreas Huemer, Mario Gongora and David Elizondo
            Abstract:
            In this paper we present a novel methodology to create a powerful controller for robots that minimises the design effort. We show that using the feedback from the robot itself, the system can learn from experience. A method is presented where the interpretation of the sensory feedback is integrated in the creation of the controller, which is achieved by growing a spiking neural network system. The feedback is extracted from a performance measuring function provided at the task definition stage, which takes into consideration the robot actions without the need for external or manual analysis. With this research we aim to create a novel unsupervised design methodology for robot controllers where, starting with the interface between the sensors and actuators and the input and output neurons of a network, new connections are created using a novel structure tied to the performance interpretation of the robot. With this method we have enabled the neural network to optimise the total number of neurons and connections in the final system, creating an efficient learning controller. Results and conclusions are presented showing our contribution to further advance in the use of automated design as a tool for creating robotics control systems efficiently.

            Title:
            ONTOLOGY ADAPTER - Network Management System Interface Model
            Author(s):
            Lingli Meng, Lusheng Yan and Wenjing Li
            Abstract:
            This paper proposes a new way to define the interface model of network management system, that is ontology adapter. This model includes three parts, which are ontology agent, ontology knowledge base and ontology resource description. We can realize the uniform presentation of different network resource interface information using it. Therefore, we can take this model as a common data platform to offer the information to the network management system

            Title:
            STOCHASTIC CONTROL STRATEGIES AND ADAPTIVE CRITIC METHODS
            Author(s):
            Randa Herzallah and David Lowe
            Abstract:
            Adaptive critic methods have common roots as generalizations of dynamic programming for neural reinforcement learning approaches. Since they approximate the dynamic programming solutions, they are potentially suitable for learning in noisy, nonlinear and nonstationary environments. In this study, a novel probabilistic dual heuristic programming (DHP) based adaptive critic controller is proposed. Distinct to current approaches, the proposed probabilistic (DHP) adaptive critic method takes uncertainties of forward model and inverse controller into consideration. Therefore, it is suitable for deterministic and stochastic control problems characterized by functional uncertainty. Theoretical development of the proposed method is validated by analytically evaluating the correct value of the cost function which satisfies the Bellman equation in a linear quadratic control problem. The target value of the critic network is then calculated and shown to be equal to the analytically derived correct value.

            Title:
            LIGHT-WEIGHT REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION FOR REAL-LIFE CONTROL TASKS
            Author(s):
            Kary Främling
            Abstract:
            Despite the impressive achievements of reinforcement learning (RL) in playing Backgammon already in the beginning of the 90's, hardly any successful real-world applications of RL have been reported since then. This could be due to the tendency of RL research to focus on discrete Markov Decision Processes that make it difficult to handle tasks with continuous-valued features. Another reason could be a tendency to develop continuously more complex mathematical RL models that are difficult to implement and operate. Both of these issues are addressed in this paper by using the gradient-descent Sarsa($\lambda$) method together with a Normalised Radial Basis Function neural net. The experimental results on three typical benchmark control tasks show that these methods outperform most previously reported results on these tasks, while remaining computationally feasible to implement even as embedded software. Therefore the presented results can serve as a reference both regarding learning performance and computational applicability of RL for real-life applications.

            Title:
            AN APPROACH FOR A KNOWLEDGE-BASED NC PROGRAMMING SYSTEM
            Author(s):
            Ulrich Berger, Ralf Kretzschmann and Jan Noack
            Abstract:
            There are existing significant deficiencies in the information flow and access along the NC (Numerical Control) process chain. The deficiencies are solved insufficient by introducing CAD/CAM systems and feature-oriented specification languages. In contrast to that the application of new production and new machining systems requires an intensive information exchange. The introduced approach enables the preparation for feature-based work plans with methods known from the graph theory as a knowledge-based NC programming system. Therefore the work plan will be mapped into a directed graph in a mathematically defined way. Now it is possible to use algorithms to find the shortest path and a Hamiltonian path inside this directed graph regarding to given requirements. Thus, the work plan will be re-ordered and scheduled. Finally the corresponding NC paths will be generated and distributed to the machinery. Thence in this in-process paper the requirements, the investigation and selection of suitable knowledge structuring concepts, mathematically basics and the work flow in such a system will be pointed out. Finally a preliminary prototype will be introduced.

            Title:
            ADAPTIVE RESOURCES CONSUMPTION IN A DYNAMIC AND UNCERTAIN ENVIRONMENT - An Autonomous Rover Control Technique using Progressive Processing
            Author(s):
            Simon Le Gloannec, Abdel Illah Mouaddib and François Charpillet
            Abstract:
            This paper address the problem of an autonomous rover that have limited consumable resources to accomplish a mission. The robot has to cope with limited resources : it must decide the resource among to spent at each mission step. The resource consumption is also uncertain. Progressive processing is a meta level reasoning model particulary adapted for this kind of mission. Previous works have shown how to obtain an optimal resource consumption policy using a Markov decision process (MDP). Here, we make the assumption that the mission can dynamically change during execution time. Therefore, the agent must adapt to the current situation, in order to save resources for the most interesting future tasks. Because of the dynamic environment, the agent cannot calculate a new optimal policy online. However, it is possible to compute an approximate value function with which the robot will behave as good as if it knew the optimal policy.

            Title:
            FLEXIBLE ROBOT-BASED INLINE QUALITY MONITORING USING PICTURE-GIVING SENSORS
            Author(s):
            Chen-Ko Sung, Andreas Jacubasch and Thomas Müller
            Abstract:
            As part of the ROBOSENS project, the IITB developed and tested a new four-step concept for multiple sensor quality monitoring. The robot-based system uses an array of test-specific short-range and wide-range sensors which make the inspection process more flexible and problem-specific. To test this innovative inline quality monitoring concept and to adapt it to customized tasks, a development and demonstration platform was created. It consists of an industrial robot with various sensor ports - a so-called “sensor magazine?- with various task-specific, interchangeable sensors and a flexible transport system.

            Title:
            AN EFFICIENT INFORMATION EXCHANGE STRATEGY IN A DISTRIBUTED COMPUTING SYSTEM - Application to the CARP
            Author(s):
            Kamel Belkhelladi, Pierre Chauvet and Arnaud Schaal
            Abstract:
            Distributed computation models have been widely used to enhance the performance of traditional evolutionary algorithms, and they have been implemented on parallel computers to speed up the computation. In this paper, we introduce a multi-agent model conceived as a conceptual and practical framework for distributed genetic algorithms used both to reduce execution time and get closer to optimal solutions. Instead of using expensive parallel computing facilities, our distributed model is implemented on easily available networked PCs. Furthermore, distributed genetic algorithms with multiple subpopulations are difficult to configure because they are controlled by many parameters that affect their efficiency and accuracy. Among other things, one must decide the number and the size of the subpopulations (demes), the rate of migration, the frequency of migrations, and the destination of the migrants. Moreover, we develop an efficient information exchange strategy based on the different dynamic migration window methods defined in (Kim, 2002) and the selective migration model defined in (Eldos, 2006). To evaluate the proposed approach, different kinds of experiments have been conducted on an extended set of Capacitated Arc Routing Problem(CARP). Obtained results are useful for optimization practitioners and show the efficiency of our approach.

            Title:
            A MARINE FAULTS TOLERANT CONTROL SYSTEM BASED ON INTELLIGENT MULTI-AGENTS
            Author(s):
            Tianhao Tang and Gang Yao
            Abstract:
            This paper presents a hybrid intelligent multi-agent method for marine faults tolerant control (FTC). A new FTC schema, implemented by different kinds of agent, is discussed as well as the structure and functions of those agents, which have been encapsulated with intelligent algorithms to carry out different aspects in FTC. These agents could, having a purpose of trying to earn payoff as much as possible in a mission, communicate and form a coalition via negotiation when they find cooperation would bring them more benefits. Simulation experiments and its results are shown at last to demonstrate the efficiency of the proposed system.

            Title:
            EXPONENTIAL OBSERVER FOR A CLASS OF NONLINEAR DISTRIBUTED PARAMETER SYSTEMS WITH APPLICATION TO A NONISOTHERMAL TUBULAR REACTOR
            Author(s):
            Nadia Barje, Mohammed Achhab and Vincent Wertz
            Abstract:
            This paper present sufficient conditions to guarantee the existence of an exponential state estimator for a class of infinite dimensional non-linear systems driven in a real Hilbert state description. The theory is applied to a nonisothermal plug flow tubular reactor, governed by hyperbolic first order partial differential equations. For this application performance issues of the exponential state estimator design are illustrated in a simulation study.

            Title:
            NEURAL NETWORK AND GENETIC ALGORITHMS FOR COMPOSITION ESTIMATION AND CONTROL OF A HIGH PURITY DISTILLATION COLUMN
            Author(s):
            J. Fernandez de Cañete, P. del Saz-Orozco and S. Gonzalez-Perez
            Abstract:
            Many industrial processes are difficult to control because the product quality cannot be measured rapidly and reliably. One solution to this problem is neural network based control, which uses an inferential estimator (software sensor) to infer primary process outputs from secondary measurements, and control these outputs. This paper proposes the use of adaptive neural networks applied both to the prediction of product composition from temperature measurements, and to the dual control of distillate and bottom composition for a continuous high purity distillation column. Genetic algorithms are used to automatically choice of the optimum control law based on the neural network model of the plant. The results obtained have shown the proposed method gives better or equal performances over other methods such fuzzy, or adaptive control

            Title:
            RECONFIGURATION OF EMBEDDED SYSTEMS
            Author(s):
            Mohamed Khalgui, Martin Hirsch, Dirk Missal and Hans-Michael Hanisch
            Abstract:
            This paper deals with automatic reconfiguration of control systems following the component-based standard IEC61499. First of all, we propose a new reconfiguration semantic allowing to improve the system performance even if there is no hardware fault. In addition, we propose to characterize the possible reconfiguration forms in order to cover all the possible execution scenarios. To apply an automatic reconfiguration, we define thereafter an agent-based architecture that we propose to model with nested state machines to control the design complexity.

            Title:
            OBDD COMPRESSION OF NUMERICAL CONTROLLERS
            Author(s):
            Giuseppe Della Penna, Nadia Lauri, Daniele Magazzeni and Benedetto Intrigila
            Abstract:
            In the last years, the use of control systems has become very common, especially in the embedded systems contained in a growing number of everyday products. Therefore, the problem of the automatic synthesis of control systems is extremely important. However, most of the current techniques for the automatic generation of controllers, such as cell-to-cell mapping, dynamic programming, set oriented approach or model checking, typically generate numerical controllers that cannot be embedded in limited hardware devices due to their size. A possible solution to this problem is to compress the controller. However, most of the common lossless compression algorithms, such as LZ77, would decrease the controller performances due to their decompression overhead. In this paper we propose a new, completely automatic OBDD-based compression technique that is capable of reducing the size of any numerical controller up to a space savings of 90% without any noticeable decrease in the controller performances.

            Title:
            THE PARALLELIZATION OF MONTE-CARLO PLANNING - Parallelization of MC-Planning
            Author(s):
            S. Gelly, J. B. Hoock, A. Rimmel, O. Teytaud and Y. Kalemkarian
            Abstract:
            Since their impressive successes in various areas of large-scale parallelization, recent techniques like UCT and other Monte-Carlo planning variants have been extensively studied. We here propose and compare various forms of parallelization of bandit-based tree-search, in particular for our computer-go algorithm XYZ.

            Title:
            PATH PLANNING FOR MULTIPLE FEATURES BASED LOCALIZATION
            Author(s):
            Francis Celeste, Frederic Dambreville and Jean-Pierre Le Cadre
            Abstract:
            In surveillance or exploration mission in a known environment, the localization of the dedicated sensor is of main importance. In this paper, we discuss the path planning problem for the localization algorithm which correlates range and bearing measurements and a map composed of several features. The sensor motion is designed from an in information measure deduced from the Fisher Information Matrix. It is shown that a closed form expression of the cost can be obtained. The optimal features location can be neatly geometrically interpreted. An integral cost which includes the sensor perception is then formulated based on this information metric. It is used in a dynamic programming framework to tackle the path optimization problem.

            Title:
            AN ONLINE BANDWIDTH SCHEDULING ALGORITHM FOR DISTRIBUTED CONTROL SYSTEMS WITH MULTIRATE CONTROL LOOPS
            Author(s):
            Saroja Kanchi and Juan Pimentel
            Abstract:
            In this paper, we present an online scheduling algorithm for communication in a distributed control system. The packet size of the communication varies for each execution of the loop within certain bounds. We consider systems with closed loops that restart immediately after the completion of an execution. Our algorithm is based on priority of the loop and size of the communication packet. We demonstrate through simulation that our algorithm generates a feasible schedule that minimizes average control delay over all the loops. Our simulations demonstrate that this online schedule reduces average delay significantly compared to a-priori schedules for distributed control systems. We demonstrate that bandwidth utilization is more efficient in case of online scheduling.

            Title:
            COMBINATION OF BREEDING SWARM OPTIMIZATION AND BACKPROPAGATION ALGORITHM FOR TRAINING RECURRENT FUZZY NEURAL NETWORK
            Author(s):
            Soheil Bahrampour, Sahand Ghorbanpour and Amin Ramezani
            Abstract:
            The usage of recurrent fuzzy neural network has been increased recently. These networks can approximate the behaviour of the dynamical systems because of their feedback structure. The Backpropagation of error has usually been used for training this network. In this paper, a novel approach for learning the parameters of RFNN is proposed using combination of the backpropagation and breeding particle swarm optimization. A comparison of this approach with previous methods is also made to demonstrate the effectiveness of this algorithm. Particle swarm is a derivative free, globally optimizing approach that makes the training of the network easier. These can solve the problems of gradient based method, which are instability, local minima and complexity of taking derivation.

            Title:
            TWO-SIDED ASSEMBLY LINE - Estimation of Final Results
            Author(s):
            Waldemar Grzechca
            Abstract:
            The paper considers simple assembly line balancing problem and two-sided assembly line structure. In the last four decades a large variety of heuristic and exact solutions procedures have been proposed to balance one-sided assembly line in the literature. Some heuristic were given to balance two-sided lines, too. Some measures of solution quality have appeared in line balancing literature: balance delay (BD), line efficiency (LE), line time (LT) and smoothness index (SI). These measures are very important for estimation the balance solution quality. Author of this paper modified and discussed the line time and smoothness for two-sided assembly line. Some problems, which appeared during evaluations, are mentioned.

            Title:
            A REAL TIME EXPERT SYSTEM FOR FAULTS IDENTIFICATION IN ROTARY RAILCAR DUMPERS
            Author(s):
            Osevaldo S. Farias, Jorge H. M. Santos, João V. F. Neto, Sofiane Labidi, Thiago Drumond, Jos?Pinheiro de Moura and Simone C. F. Neves
            Abstract:
            This paper describes the development of a real-time Expert System applied to the ore extraction Industrial branch, specifically used to assist the decision making and fault identification on rotary railcar dumpers of the operational productive system located at Ponta da Madeira Dock Terminal, built and operated by Companhia Vale do Rio Doce (CVRD) in São Luis-MA. The Expert System is built on JESS (Java Expert System Shell) platform and provides support to engineers and operators during the ore unloading as soon as supplying on-line information about faults triggered by device sensors of the rotary railcar. The system’s conception involves the application of CommonKADS methodology, knowledge engineering and artificial intelligence techniques at the symbolic level for representing and organizing the knowledge domain in which the system is applied.

            Title:
            AUTOMATIC PARAMETERIZATION FOR EXPEDITIOUS MODELLING OF VIRTUAL URBAN ENVIRONMENTS - A New Hybrid Metaheuristic
            Author(s):
            Filipe Cruz, António Coelho and Luis Paulo Reis
            Abstract:
            Expeditious modelling of virtual urban environments consists of generating realistic 3d models from limited information. It has several practical applications but typically suffers from a lack of accuracy in the parameter values that feed the modeller. By gathering small amounts of information about certain key urban areas, it becomes possible to feed a system that automatically compares and adjusts the input parameter values to find optimal solutions of parameter combinations that resemble the real life model. These correctly parameterized rules can then be reapplied to generate virtual models of real areas with similar characteristics to the referenced area. Based on several nature inspired metaheuristic algorithms such as genetic algorithms, simulated annealing and harmony search, this paper presents a new hybrid metaheuristic algorithm aiming to find the optimal solution of a multi-parameter real-based optimization problem. Results achieved in a simple test-case are also presented showing the potential of the new hybrid metaheuristic algorithm when compared with standard optimization algorithms.

            Title:
            WISA - A Modular and Hybrid Expert System for Machine and Plant Diagnosis
            Author(s):
            Mario Thron, Thomas Bangemann and Nico Suchold
            Abstract:
            Expert systems are well known tools for diagnosis purposes in medicine and industry. One problem is the hard efford, to create the knowledge base. This article describes an expert system for industrial diagnosis and shows an efficient approach for the creation of the rule base, which is based on the reusage of knowledge modules. These knowledge modules are representants for assets like devices, machines and plants. The article encourages manufacturers of such assets to provide diagnosis knowledge bases by using a proposed multi-paradigm rule definition language called HLD (Hybrid Logic Description). Rule based knowledge may be expressed by using various methodologies, which differ in expressiveness but also in runtime performance. The HLD allowes rules to be defined as propositional logic with or without the use of certainty factors, as Fuzzy Logic or as probabilistic rules as in Bayesian Networks. The most effective rule type may be choosen to describe causal dependencies between symptoms and faillures. An evaluation prototype implementation provides separate terminals for experts and operators to communicate with the HLD interpreter via Internet-based communication systems.

            Title:
            AN EVOLUTIONARY ALGORITHM FOR UNICAST/ MULTICAST TRAFFIC ENGINEERING
            Author(s):
            Miguel Rocha, Pedro Sousa, Paulo Cortez and Miguel Rio
            Abstract:
            A number of Traffic Engineering (TE) approaches have been recently proposed to improve the performance of network routing protocols, both developed over MPLS and intra-domain protocols such as OSPF. In this work, a TE approach is proposed for routing optimization in scenarios where unicast and multicast demands are simultaneously present. Evolutionary Algorithms are used as the optimization engine with overall network congestion as the objective function. The optimization aim is to reach a set of (near-)optimal weights to configure the OSPF protocol. The results show that the method is able to obtain networks with low congestion, even under scenarios with heavy unicast/multicast demands.

            Title:
            COLLISION AVOIDANCE SYSTEM PRORETA - Strategies Trajectory Control and Test Drives
            Author(s):
            R. Isermann, U. Stählin and M. Schorn
            Abstract:
            Methods and experimental results of a collision avoidance driver assistance system are described with automatic object detection, trajectory prediction, and path following with controlled braking and steering. The objects are detected by a fusion of LIDAR scanning and video camera pictures resulting in the location, size and speed of objects in front of the car. A desired trajectory is calculated depending on the distance, the width of a swerving action and difference speed. For the trajectory control different control methods were designed and tested experimentally like velocity depend linear feedback and feedforward control, nonlinear asymptotic output tracking and nonlinear flatness based control using extended one-track models with vehicle state estimation for the sideslip angle and cornering stiffness. Automatic braking is realized with an electrohydraulic brake (EHB) and automatic steering with an active front steering (AFS). The various control systems are compared by simulations and real test drives showing the behaviour of a VW Golf with automatic braking or/and automatic swerving to a free track, such avoiding hitting a suddenly appearing obstacle. The research project PRORETA was a four-years-cooperation between Continental Automotive Systems and Darmstadt University of Technology.

            Title:
            EVALUATION OF NEURAL PDF CONTROL STRATEGY APPLIED TO A NONLINEAR MODEL OF A PUMPED ?STORAGE HYDROELECTRIC POWER STATION
            Author(s):
            G. A. Munoz-Hernandez, C. A. Gracios-Marin, A. Diaz-Sanchez, S. P. Mansoor and D. I. Jones
            Abstract:
            In this paper, a neural Pseudoderivative control (PDF) is applied to a nonlinear mathematical model of the Dinorwig pumped - storage hydroelectric power station. The response of the system with this auto-tuning controller is compared with the classic controller, currently implemented on the system. The results show how the application of PDF control to a hydroelectric pumped-storage station improves the dynamic response of the power plant, even when multivariable effects are taken into account.

            Title:
            THE BEES ALGORITHM AND MECHANICAL DESIGN OPTIMISATION
            Author(s):
            D. T. Pham, M. Castellani, M. Sholedol and A. Ghanbarzadeh
            Abstract:
            The Bees Algorithm is a search procedure inspired by the way honey-bees forage for food. A standard mechanical design problem, the design of a welded beam structure, was used to benchmark the Bees Algorithm against other optimisation techniques. The paper presents the results obtained showing the robust performance of the Bees Algorithm.

            Title:
            A NOVEL PARTICLE SWARM OPTIMIZATION APPROACH FOR MULTIOBJECTIVE FLEXIBLE JOB SHOP SCHEDULING PROBLEM
            Author(s):
            Souad Mekni, Besma Fayech Char and Mekki Ksouri
            Abstract:
            Because of the intractable nature of the problem of flexible job shop scheduling and its importance in both fields of production management and combinatorial optimization, it is desirable to employ efficient metaheuristics in order to obtain a better solution quality for the problem. In this paper, a novel approach based on the vector evaluated particle swarm optimization and the weighted average ranking is presented to solve flexible job shop scheduling problem (FJSP) with three objectives (i) minimize the makespan, (ii) minimize the total workload of machines and (iii) minimize the workload of critical machine. To convert the continuous position values to the discrete job sequences, we used the heuristic rule the Smallest Position Value (SPV). Experimental results in this work are very enouraging since that relevent solutions were provided in a reasonable computational time.

            Title:
            RFID BASED LOCATION IN CLOSED ROOMS - Implementation of a Location Algorithm using a Passive UHF-RFID System
            Author(s):
            Christoph Schönegger, Burkhard Stadlmann and Michael E. Wernle
            Abstract:
            This paper presents a new concept for determining the location of an RFID-tag without any additional hardware. For this positioning system standard RFID components within the UHF range are used. The measurement is based on a location algorithm which makes use of the RSSI value of the UHF reader. The RSSI value is the return signal strength indicator and, as it is shown in the paper in hand, this signal correlates to the distance between the RFID tag and the antenna of the reader. This positioning system is especially useful indoors, where other positioning systems may not work. For this reason it could prove very useful in various logistics applications. The maximum distance from antenna to the tag is approximately between 0.5 m and 3 m. To this end a special algorithm is used to obtain stable calculation results. A minimum of two antennas is needed to get a two-dimensional location.

            Title:
            PARALLEL MACHINE EARLINESS-TARDINESS SCHEDULING - Comparison of Two Metaheuristic Approaches
            Author(s):
            Marcin Bazyluk, Leszek Koszalka and Keith J. Burnham
            Abstract:
            This paper considers the problem of parallel machine scheduling with the earliness and tardiness penalties (PMSP\_E/T) in which a set of sequence-independent jobs is to be scheduled on a set of given machines to minimize a sum of the weighted earliness and tardiness values. The weights and due dates of the jobs are distinct positive numbers. The machines are diverse - each has a different execution speed of the respective jobs, thus the problem becomes more complex. To handle this, it two heuristics are employed, namely: the genetic algorithm with the MCUOX crossover operator and the tabu search. The performances of the both approaches are evaluated and their dependency on the shape of the investigated instances examined. The results indicate the significant predominance of the genetic approach for the larger-sized instances.

            Title:
            SENSOR AND ACTUATOR FAULT ANALYSIS IN ACTIVE SUSPENSION IN VIEW OF FAULT-TOLERANT CONTROL
            Author(s):
            Claudio Urrea and Marcela Jamett
            Abstract:
            This paper shows the first step of a fault tolerant control system (FTCS) to control active suspension on a full-car suspension model. In this paper, the elimination of the inevitable pitch and roll actions of a spring suspension between each axle and the body of a vehicle is studied. An actuator (linear motor) producing an electromagnetic force and a pneumatic force acting simultaneously on the same output element is used. This linear motor acts as a force generator that compensates instantly for the disturbing effects of the road surface. Simulation results to illustrate the system’s performance in front of the occurrence of sensor and actuator faults are shown.

            Title:
            HUNTER ?HYBRID UNIFIED TRACKING ENVIRONMENT - Real-time Identification and Tracking System using RFID Technology
            Author(s):
            A. G. Foina and F. J. Ramirez Fernandez
            Abstract:
            This article presents the results of the use of RFID technology for trucks?cargo real-time tracking. RFID tags were settled at trucks?dump-carts and readers were spread throughout warehouses entrances, at the truck weighting scale and through unload platforms. The unload inspectors used robust PDA with camera, along with Wi-Fi access points installed in warehouses, to confirm the truck information and take a snapshot for future audits. A wireless broadband link was used to connect two weighting scale that are distant from the unloading area. All technologies communicate with a web-based middleware that manages all different devices. The system design is flexible enough to be used in very different applications like product process control, automated manufactory lines control, supply chain applications and others.

            Area 2 - Robotics and Automation
            Title:
            GENETIC-ALGORITHM SEEDING OF IDIOTYPIC NETWORKS FOR MOBILE-ROBOT NAVIGATION
            Author(s):
            Amanda M. Whitbrook, Uwe Aickelin and Jonathan M. Garibaldi
            Abstract:
            Robot-control designers have begun to exploit the properties of the human immune system in order to produce dynamic systems that can adapt to complex, varying, real-world tasks. Jerne’s idiotypic-network theory has proved the most popular artificial-immune-system (AIS) method for incorporation into behaviour-based robotics, since idiotypic selection produces highly adaptive responses. However, previous efforts have mostly focused on evolving the network connections and have often worked with a single, pre-engineered set of behaviours, limiting variability. This paper describes a method for encoding behaviours as a variable set of attributes and shows that when the encoding is used with a genetic algorithm (GA), multiple sets of diverse behaviours can develop naturally and rapidly, providing much greater scope for flexible behaviour-selection. The algorithm is tested extensively with a simulated e-puck robot that navigates around a maze by tracking colour. Results show that highly successful behaviour sets can be generated within about 25 minutes, and that much greater diversity can be obtained when multiple autonomous populations are used, rather than a single one.

            Title:
            ROBOT GOES BACK HOME DESPITE ALL THE PEOPLE
            Author(s):
            Paloma de la Puente, Diego Rodriguez-Losada, Luis Pedraza and Fernando Matia
            Abstract:
            We have developed a navigation system for a mobile robot that enables it to autonomously return to a start point after completing a route. It works efficiently even in complex, low structured and populated indoor environments. A point-based map of the environment is built as the robot explores new areas; it is employed for localization and obstacle avoidance. Points corresponding to dynamical objects are removed from the map so that they do not affect navigation in a wrong way. The algorithms and results we deem more relevant are explained in the paper.

            Title:
            IDENTIFICATION OF THE DYNAMIC PRAMETERS OF THE C5 PARALLEL ROBOT
            Author(s):
            B. Achili, B. Daachi, Y. Amirat and A. Ali-Cherif
            Abstract:
            This paper deals with the experimental identification of the dynamic parameters of the C5 parallel robot. The inverse dynamic model of the robot is formulated under the form of linear equation with respect to the dynamic parameters. Moreover, a heuristic procedure for finding the exciting trajectory has been conducted. This trajectory is based on Fourier series whose coefficients are determined by using a heuristic method. The least squares method has been applied to solve an over-determined linear system which is obtained by sampling the dynamic model along the exciting trajectory. The experimental results show the effectiveness of the identification procedure.

            Title:
            ROBUST CONTROL OF THE C5 PARALLEL ROBOT
            Author(s):
            B. Achili, B. Daachi, A. Aliu-Cherif and Y. Amirat
            Abstract:
            This paper deals with the dynamic control of a parallel robot with C5 joints. Computed torque control and robust control have been studied and implemented. For this purpose, we have used the inverse dynamic model whose parameters have been experimentally identified. The closed loop stability has been studied using the Lyapunov principle. The addition of a robustness term based on sliding mode technique ensures good tracking performances. The experimental results show the effectiveness of the robust control.

            Title:
            ROBOT NAVIGATION MODALITIES
            Author(s):
            Ray Jarvis
            Abstract:
            Whilst navigation (robotic or otherwise) consists simply of traversing from a starting point to a goal, there are a plethora of conditions, states of knowledge and functional intentions which dictate how best to execute this process in a manageable, reliable, safe and efficient way. This position paper addresses the broad issues of how a continuum of choices from pure manual or teleoperation control through to fully autonomous operation can be laid out and then selected from, taking into account the variety of factors listed above and the richness of live sensory data available to describe the operational environment and the location of the robot vehicle within it.

            Title:
            SHOE GRINDING CELL USING VIRTUAL MECHANISM APPROACH
            Author(s):
            Bojan Nemec and Leon Zlajpah
            Abstract:
            The paper describes the automation of the shoe grinding process using an industrial robot. One of the major problems of flexible automation using industrial robots is how to avoid joint limitations, singular configuration and obstacles. This problem can be solved using kinematically redundant robots. Due to the circular shape of the grinding disc, the robot becomes kinematically redundant. This task redundancy was efficiently handled using virtual mechanism approach, where the tool is described as a serial mechanism.

            Title:
            ROBOTIC WHEELCHAIR CONTROL CONSIDERING USER COMFORT - Modeling and Experimental Evaluation
            Author(s):
            Razvan Solea and Urbano Nunes
            Abstract:
            This paper analyzes the comfort of wheelchair users when a sliding mode trajectory-tracking controller is used. The transmission of the horizontal (fore-and-aft) vibration to the head-neck complex (HNC) in the seated human body may cause unacceptable discomfort and motion sickness. A double-inverted pendulum model with two degrees of freedom is considered as a model for the HNC. The user comfort is examined not only in the time domain (using the fourth power vibration dose value), but also in the frequency domain (using the cross-spectral density method). For measuring the acceleration of the wheelchair, along the trajectory, an inertial measurement unit was used.

            Title:
            DYNAMICAL MODELS FOR OMNI-DIRECTIONAL ROBOTS WITH 3 AND 4 WHEELS
            Author(s):
            Hélder P. Oliveira, Armando J. Sousa, A. Paulo Moreira and Paulo J. Costa
            Abstract:
            Omni-directional robots are becoming more and more common in recent robotic applications. They offer improved ease of maneuverability and effectiveness at the expense of increased complexity. Frequent applications include but are not limited to robotic competitions and service robotics. The goal of this work is find a precise dynamical model to predict the robot behavior. During this work, models were found for two real world omni-directional robot configurations and its parameters estimated using a prototype that can have 3 or 4 wheels. Results of experimental runs are presented in order to validate the presented work.

            Title:
            REAL TIME GRASPING OF FREELY PLACED CYLINDRICAL OBJECTS
            Author(s):
            Mario Richtsfeld, Wolfgang Ponweiser and Markus Vincze
            Abstract:
            In the near future, service robots will support people with different handicaps to improve the quality of their life. One of the required key technologies is to setup the grasping ability of the robot. This includes an autonomous object detection and grasp motion planning to fulfil the task of providing objects from any position on a table to the user. This paper presents a complete system, which consists of a fixed working station equipped with a laser-range scanner, a seven degrees of freedom arm manipulator and an arm prothesis as gripper. The contribution of this work is to use only one sensor system based on a laser-range scanning head to solve this challenge. The presented work is tested at a live demo presentation in front of more than 1000 college students in about 50 trials. The goal is that the user can select any defined object on the table and the robot arm delivers it to a target position or to the disabled person.

            Title:
            DIAGNOSIS OF DISCRETE EVENT SYSTEMS WITH PETRI NETS AND CODING THEORY
            Author(s):
            Dimitri Lefebvre
            Abstract:
            Event sequences estimation is an important issue for fault diagnosis of DES, so far as fault events cannot be directly measured. This work is about event sequences estimation with Petri net models. Events are assumed to be represented with transitions and firing sequences are estimated from measurements of the marking variation. Estimation with and without measurement errors are discussed in n ? dimensional vector space over alphabet Z3 = {-1, 0, 1}. Sufficient conditions and estimation algorithms are provided. Performance is evaluated and the efficiency of the approach is illustrated on two examples from manufacturing engineering.

            Title:
            MODELING AND SIMULATION OF A NEW PARALLEL ROBOT USED IN MINIMALLY INVASIVE SURGERY
            Author(s):
            Doina Pisla, Calin Vaida, Nicolae Plitea, Jürgen Hesselbach, Annika Raatz, Marc Simnofske, Arne Burisch and Liviu Vlad
            Abstract:
            Surgery is one of the fields where robots have been introduced due to their positioning accuracy which exceed the human capabilities. Parallel robots offer higher stiffness and smaller mobile mass than serial ones, thus allowing faster and more precise manipulations that fit medical applications. In the paper is presented the modeling and simulation of a new parallel robot used in minimally invasive surgery. The parallel architecture has been chosen for its superiority in precision, repeatability, stiffness, higher speeds and occupied volume. The robot kinematics, singular position identification and workspace generation are illustrated. Using the developed virtual model of the parallel robot, some simulation tests are presented. The latest obtained results demonstrate that the computing time necessary for generating the virtual model is relatively small.

            Title:
            DYNAMIC MODELING OF A 6-DOF PARALLEL STRUCTURE DESTINATED TO HELICOPTER FLIGHT SIMULATION
            Author(s):
            Nicolae Plitea, Adrian Pisla, Doina Pisla and Bogdan Prodan
            Abstract:
            The dynamic analysis is the basic element of the mechanical design and control of parallel mechanisms. The parallel robots dynamics requires a great deal of computing as regards the formulation of the generally nonlinear equations of motion and their solution. In this paper a solution for solving the dynamical model of a 6-DOF parallel structure destined to helicopter flight simulation is presented. The obtained dynamical algorithms, based on the kinematical ones, offer the possibility of a complex study for this type of parallel structure in order to evaluate the dynamic capabilities and to generate the control algorithms.

            Title:
            RACBOT-RT: ROBUST DIGITAL CONTROL FOR DIFFERENTIAL SOCCER-PLAYER ROBOTS
            Author(s):
            João Monteiro and Rui Rocha
            Abstract:
            Robot soccer is a popular testbed to study challenging problems of mobile robotics. It is recognized in the robot soccer domain that robust trajectory control and high responsiveness to motion commands are key aspects to successfully deal with the game dynamic. With this aim, the paper presents a digital controller developed to small-sized robot soccer players. A special emphasis has been given to design a controller as much generic as possible, which can be applied to any mobile robot with differential kinematics. The theoretical framework is based on Lyapunov equations for pose stability convergence. The controller was implemented as a software module running on the robot, which responds to motion commands through the decomposition of the trajectory into a set of virtual reference positions with respect to the world reference coordinates system, which are further followed robustly by the robot, even in the presence of unwanted motion disturbances. Experimental results obtained with a mobile robot moving on the game field demonstrate the quality of the proposed solution and validate the implemented controller.

            Title:
            CONTRIBUTION CONCERNING ROBOT ACCURACY USING NUMERICAL MODELING
            Author(s):
            Daniela Ghelase, Luiza Daschievici and Irina Ghelase
            Abstract:
            The kinematical accuracy of robot is very important. It is induced by the rigidity of each mechanism of the robot. The paper presents a numerical method to evaluate the rigidity of worm-gearing teeth. The software, including setting-up and graphic display, could be adopted of any kind of cylindrical worm-gear drive or for spur gear drives and bevel gear drives, mechanisms which are in the robot structure. Besides, we can determine geometrical parameters of the gear drives which influence the increase of accuracy of robot linkages.

            Title:
            HYDROGEN POWERED CAR CONTROL SYSTEM
            Author(s):
            Srovnal Vilem, Koziorek Jiri, Horak Bohumil, Adam George and Garani Georgia
            Abstract:
            Mobile embedded systems belong among the typical applications of the distributed systems control in real time. An example of a mobile control system is the hydrogen powered prototype car control system. The proposal and realization of such distributed control system represents a demanding and complex task of real time control for track optimizing with minimal fuel consumption. Design and realization of distributed control system, mention above, is prepared to realize as a complex laboratory task. Control system software using of multi-agent technology with dynamic mutual negotiation of mobile system parts. This task allows in a form of control system for prototype race car modelling of distributed control system. The real hardware and software model is also important motivation for extended study.

            Title:
            PROGRESSIVE MESH BASED ITERATIVE CLOSEST POINTS FOR ROBOTIC BIN PICKING
            Author(s):
            Kay Boehnke and Marius Otesteanu
            Abstract:
            This paper describes a hierarchical registration process using the iterative closest point algorithm combined with a Progressive mesh. We integrated this in a system for automated robotic bin picking. Laser range sensors provide range data of a box filled with scrambled production parts. An industrial robot is use to pick these parts out of the box and feed them into an automated process. To find the exact pose of the objects we use knowledge about the form of the objects to find them in range data. We simulate the appearance of object poses and compare them with the real range data provided by laser range sensors. The coarse pose is estimated in a first step und then refined with the well known iterative Closest Point (ICP) algorithm combined with Progressive meshs for hierarchical object localization. We evaluate our approach with different test scenarios and show the comprehensive potential of this idea for other registration problems.

            Title:
            VIDEO TRANSMISSION WITH ADAPTIVE QUALITY BASED ON NETWORK FEEDBACK FOR MOBILE ROBOT TELEOPERATION IN WIRELESS MULTI-HOP NETWORKS
            Author(s):
            Florian Zeiger, Markus Sauer and Klaus Schilling
            Abstract:
            A video stream is still one of the most important data sources for the user while remote-operating a mobile robot. Human operators have comprehensive capabilities to interpret the displayed image information, but therefore, some constraints must be fulfilled. Constant frame rates and delays below a certain threshold are a minimum requirement to use video for teleoperation. Modern multi-hop networks often use WLAN to set up ad-hoc networks of mobile nodes with each node acting as traffic source, sink, or router. Considering these networks, routes between sources and destinations might be established via several relay nodes. Thus, the utilization of intermediate nodes which are part of a route influences the overall route performance, whereas sender and receiver have no direct feedback of the overall route status. In case video is transmitted via wireless ad-hoc networks in a teleoperation scenario, the displayed video-stream for the operator might have variable frame rates, very high packet loss, and packet inter-arrival times which are not appropriate for mobile robot teleoperation. This work presents an approach using a feedback generated by the network to adapt the image quality to present communication constraints. Thus, according to the current network status, the best possible video image is provided to the operator while keeping constant frame rates and low packet loss.

            Title:
            PARAMETER TUNING OF ROUTING PROTOCOLS TO IMPROVE THE PERFORMANCE OF MOBILE ROBOT TELEOPERATION VIA WIRELESS AD-HOC NETWORKS
            Author(s):
            Florian Zeiger, Nikolaus Kraemer and Klaus Schilling
            Abstract:
            Currently, the use of wireless networks is very common in the field of networked robotics and can be considered as a key issue for capable multi robot systems with a high grade of mobility. Nevertheless, this mobility requests for special features of the communication infrastructure, which leads to the integration of mobile robots into wireless ad-hoc networks. Since the late nineties, more than 80 ad-hoc routing protocols were developed and nowadays some of them are implemented and ready to use in real world applications. A comparison of four ad-hoc routing protocols (AODV, DSR, OLSR, and BATMAN) showed some shortfalls of the default parameter settings not allowing a reliable teleoperation of mobile robots while using AODV, OLSR, or BATMAN. This work is focused on the parameter tuning of the routing protocols to use them in wireless ad-hoc networks of mobile robots. The time required for route reestablishing, as well as the packet loss during rerouting is investigated in hardware tests of a network with dynamic network topology consisting of mobile robots. It could be demonstrated, that an appropriate parameter setting of OLSR and AODV allow the teleoperation of mobile robots in outdoor environments via a wireless ad-hoc network.

            Title:
            LegOSC - Mindstorms NXT Robotics Programming for Artists
            Author(s):
            Jorge Cardoso, Manuel Ferreira and Cristina Santos
            Abstract:
            Robotics is an interesting but difficult area for digital artists who generally don’t have much academic background on electronics or computer programming. Digital art students normally use high-level application to program their visual and sonorous installations. This paper presents LegOSC - a tool that allows the control of the Mindstorms NXT robots from any application that uses the Open Sound Control protocol which is implemented by most of those high-level applications. This allows artists to create works which incorporate robotic parts using the familiar programming environment.

            Title:
            ACTIVE SECURITY SYSTEM FOR AN INDUSTRIAL ROBOT BASED ON ARTIFICIAL VISION AND FUZZY LOGIC PRINCIPLES
            Author(s):
            B. Fevery, B. Wyns, L. Boullart, J. R. Llata García and C. Torre Ferrero
            Abstract:
            An active security system assures that interacting robots don’t collide or that a robot operating independently doesn’t hit any obstacle that is encountered in the robots workspace. In this paper, an active security system for a FANUC industrial robot is introduced. The active security problem where one robot needs to avoid a moving obstacle in its workspace is considered. An obstacle detection and localization mechanism based on stereoscopic vision methods was successfully developed. To connect the vision system, an operator’s pc and the robot environment a real-time communication is set up over Ethernet using socket messaging. We used fuzzy logic for intelligent trajectory planning. A multitask oriented robot application in the KAREL programming language of FANUC Robotics was implemented and tested.

            Title:
            A QUADRATIC PROGRAMMING APPROACH TO THE MINIMUM ENERGY PROBLEM OF A MOBILE ROBOT
            Author(s):
            Alain Segundo Potts, Jos?Jaime da Cruz and Reinaldo Bernardi
            Abstract:
            As a consequence of physical constraints and of dynamical nonlinearities, optimal control problems involving mobile robots are generally difficult ones. Many algorithms have been developed to solve such problems, the more common being related to trajectory planning, minimum-time control or any specific performance index. Nevertheless optimal control problems associated to mobile robots have not been reported. Minimum energy problems subject to both equality and inequality constraints are generally intricate ones to be solved using classical methods. In this paper we present an algorithm to solve it using a Quadratic Programming approach. In order to illustrate the application of the algorithm, one practical problem was solved

            Title:
            WHAT’S THE BEST ROLE FOR A ROBOT? - Cybernetic Models of Existing and Proposed Human-Robot Interaction Structures
            Author(s):
            Victoria Groom
            Abstract:
            Robots intended for human-robot interaction are currently designed to fill simple roles, such as task completer or tool. The design emphasis remains on the robot and not the interaction, as designers have failed to recognize the influence of robots on human behavior. Cybernetic models are used to critique existing models and provide revised models of interaction that delineate the paths of social feedback generated by the robot. Proposed robot roles are modeled and evaluated. Features that need to be developed for robots to succeed in these roles are identified and the challenges of developing these features are discussed.

            Title:
            THE APPLICATION OF REFERENCE-PATH CONTROL TO VEHICLE PLATOONS
            Author(s):
            Drago Matko, Gregor Klančar, Sašo Blažič, Olivier Simonin, Franck Gechter, Jean-Michel Contet and Pablo Gruer
            Abstract:
            A new algorithm for the control of vehicle platooning is proposed and tested on a robot-soccer test bed. We considered decentralized platooning, i.e., a virtual train of vehicles, where each vehicle is autonomous and decides on its motion based on its own perceptions. The platooning vehicles have non-holonomic constraints. The following vehicle only has information about its own orientation and about its distance and azimuth to the leading vehicle. Its position is determined using odometry and a compass. The reference position and the orientation of the following vehicle are determined by the estimated path of the leading vehicle in a parametric polynominal form. The parameters of the polynominals are determined using the least-squares method. This parametric reference path is also used to determine the feed-forward part of the applied control algorithm. The feed-back control consists of a state controller with three inputs: the longitudinal and lateral position errors and the orientation error. The results of the experiments demonstrate the applicability of the proposed algorithm for vehicle platoons.

            Title:
            AN EMBEDDED SYSTEM FOR SMALL-SCALED AUTONOMOUS VEHICLES
            Author(s):
            David Vissière and Nicolas Petit
            Abstract:
            We consider the problem of designing a modular real-time embedded system for control applications with unmanned vehicles. We propose a simple and low-cost solution. Its computational power can be easily improved, depending on application requirements. To illustrate its performance, we report the implementation of a 75~Hz Extended Kalman Filter used for state estimation on a small-scaled helicopter.

            Title:
            WALKING PLANNING AND CONTROL FOR A BIPED ROBOT UPSTAIRS
            Author(s):
            Chenbo Yin, Donghua Zheng and Le Xiao
            Abstract:
            The focus of this paper is the problem of walking stability control in humanoid robot going upstairs. Walking stability is a very important problem in the field of robotics. Lots of researches have been done to get stable walking on plane. But it is very limited on going upstairs. We first plan the gate of ankle and hip when going upstairs as well as the calculation of stable region and stability margin. Then the emergency-coping strategy of enlarging the support polygon is provided. At last, a control system which is proved to be effective by simulation is presented. If the ZMP is in the support polygon, this control system makes fine setting to gait to get higher stability. If the ZMP is out of the support polygon, the control system adjusts the location of ZMP through the emergency coping strategy.

            Title:
            DRIVER’S DROWSINESS DETECTION BASED ON VISUAL INFORMATION
            Author(s):
            Marco Javier Flores, Jos?María Armingol and Arturo de la Escalera
            Abstract:
            In this paper, a new Driver Assistance System (DAS) for automatic driver’s drowsiness detection based on visual information and image processing is presented. This algorithm works on several stages using Viola and Jones (VJ) object detector, expectation maximization algorithm, the Condensation algorithm and support vector machine to compute a drowsiness index. The goal of the system is to help in the reduction of traffic accidents caused by human errors. Examples of different driver’s images taken over a real vehicle are shown to validate the algorithm.

            Title:
            HYBRID MATCHING OF UNCALIBRATED OMNIDIRECTIONAL AND PERSPECTIVE IMAGES
            Author(s):
            Luis Puig, J. J. Guerrero and Peter Sturm
            Abstract:
            This work presents an automatic hybrid matching of central catadioptric and perspective images. It is based on the hybrid epipolar geometry. The goal is to obtain correspondences between an omnidirectional image and a conventional perspective image taken from different points of view. Mixing both kind of images has multiple applications in visual localization, recognition, surveillance and robot navigation, since an omnidirectional image captures many information and perspective images are the simplest way of acquisition. Scale invariant features with a simple unwrapping are considered to help the initial putative matching. Then a robust technique gives an estimation of the hybrid fundamental matrix, to avoid outliers. Experimental results with real image pairs show the feasibility of that hybrid and difficult matching problem.

            Title:
            TEMPORAL MATCH OF MULTIPLE SOURCE DATA IN AN ETHERNET BASED INDUSTRIAL ENVIRONMENT
            Author(s):
            Daniela Hossu and Andrei Hossu
            Abstract:
            The actual trend in automation control systems is to distribute control logic to modular and easy to connect production cells. As part of this trend is the increase of Ethernet technology for machine-machine data communication inside this modular based architecture. The paper presents a robotic handling application of moving parts located on a transport conveyor. Data representing a set of parameters of the parts to be handle form the conveyor is provided by a Routing Control System (RCS). The Control Management System (CMS), which controls a number of robotic cells is receiving this data from RCS and merge it with the information provided by an Artificial Vision System. The communication between these two Control Systems (RCS and CMS) is Ethernet-based. Ethernet technology is good, reliable and fast for large amount of data, but because of its non-deterministic character, it has a lack of tools for data synchronization. The paper includes an analysis of the experimental results of the measurements of the non-deterministic factor of the existing network. The "worst case scenario" of the maximum communication delay caused by Ethernet traffic and the minimum time between two consecutive data commands, shows that without recovering data transfer time-consistency, the application requirements can not be achieved. The paper is presenting a mechanism developed at protocol level, in order to guarantee the consistency in time, at CMS level, of the data provided from RCS with the data provided by Vision System.

            Title:
            A NEW APPROACH OF GRAY IMAGES BINARIZATION FOR ARTIFICIAL VISION SYSTEMS WITH THRESHOLD METHODS
            Author(s):
            Daniela Hossu and Andrei Hossu
            Abstract:
            The paper presents some aspects of the (gray level) image binarization methods used in artificial vision systems. It is introduced a new approach of gray level image binarization for artificial vision systems dedicated to industrial automation ?temporal thresholding. In the first part of the paper are extracted some limitations of using the global optimum thresholding in gray level image binarization. In the second part of this paper are presented some aspects of the dynamic optimum thresholding method for gray level image binarization. Starting from classic methods of global and dynamic optimal thresholding of the gray level images in the next section are introduced the concepts of temporal histogram and temporal thresholding. In the final section are presented some practical aspects of the temporal thresholding method in artificial vision applications form the moving scene in robotic automation class; pointing out the influence of the acquisition frequency on the methods results.

            Title:
            CALIBRATION ASPECTS OF MULTIPLE LINE-SCAN VISION SYSTEM APPLICATION FOR PLANAR OBJECTS INSPECTION
            Author(s):
            Andrei Hossu and Daniela Hossu
            Abstract:
            Besides the accuracy performances and response time, one of the characteristics of an Industrial Vision System is its set-up time. Minimizing the set-up time while keeping the performances in accuracy is one of the goals of any advanced Vision System. The calibration method presented in the paper is developed for a dual line-scan camera system. The paper presents the architecture and the purpose and the performances required for the proposed Industrial Vision System. The calibration method presented is based on analyzing the image of a calibration tool exposed to the Vision System. There are presented the type of dimensional distortions identified from the experimental results. The second part of the paper presents the calibration method. The Industrial Vision System described in the paper is designed for silhouette inspection of planar objects located on a moving scene (transport conveyor), in a robotic handling application. This means the Vision System is not analyzing the volumetric characteristics of the objects. However the height of the object is varying in time (from one set of objects to another). Due to the fact the distance between the cameras and the objects is changing, the measuring results are affected. The proposed calibration method allow the Vision System to self adjust the calibration parameters for a known new height of the objects, without disturbing the application. In the final section of the paper are presented some practical aspects of how the results of the proposed calibration method require minimum computational efforts from the online tasks of the Vision System.

            Title:
            OPTIMISING A FLYING ROBOT - Controller Optimisation using a Genetic Algorithm on a Real-World Robot
            Author(s):
            Benjamin N. Passow and Mario Gongora
            Abstract:
            This work presents the optimisation of the heading controller of a small flying robot. A genetic algorithm (GA) has been used to tune the proportional, integral, and derivative (PID) parameters of the helicopter’s controller. Instead of evaluating each individual’s fitness in an artificial simulation, the actual flying robot has been used. The performance of a hand-tuned PID controller is compared to the GA-tuned controller. Tests on the helicopter confirm that the GA’s solutions result in a better controller performance. Further more, results suggest that evaluating the GA’s individuals on the real flying robot increases the controller’s robustness.

            Title:
            A PERCEPTUAL MOTOR CONTROL MODEL BASED ON OUTPUT FEEDBACK ADAPTIVE CONTROL THEORY
            Author(s):
            Hirofumi Ohtsuka, Koki Shibasato and Shigeyasu Kawaji
            Abstract:
            In this paper, a perceptual motor control model based on output feedback adaptive control theory is considered from the viewpoint of voluntary movement such as hand-tracking control. At first, we give an account of the basic theory of the output feedback control based on almost strict positive real characteristics for the linear plant and the Smith prediction method for plant with pure time delay. Then, a perceptual motor control model is constructed using together with above methods. In the proposed method, there exists the attractive structural similarity between the cerebrum-cerebellum neuro-motor signal feedback loop and the adaptive controller - compensators local minor feedback loop. The proposed perceptual motor control model is examined through the comparison of between the experiment and the simulation of for handling 1-link mechanism in order to track an indicator.

            Title:
            TWO LAYERS ACTION INTEGRATION FOR HRI - Action Integration with Attention Focusing for Interactive Robots
            Author(s):
            Yasser Mohammad and Toyoaki Nishida
            Abstract:
            \fontsize{9}{11}\selectfont Behavior architectures are widely used to program interactive robots. In these architectures multiple \emph{behaviors} are usually running concurrently so a mechanism for integrating the resulting actuation commands from these \emph{behaviors} into actual actuation commands sent to the robot's motor system must be faced. Different architectures proposed different action integration mechanisms that range from distributed to central integration. In this paper an analysis of the special requirements that HRI imposes on the action integration system is given. Based on this analysis a novelle hybrid action integration mechanism that combines distributed attention focusing with a fast central integration algorithm is presented in the framework of the EICA architecture. The proposed system was tested in a simulation of a listener robot that aimed to achieve human-like nonverbal listening behavior in real world interactions. The analysis of the system showed that the proposed mechanism can generate coherent human-like behavior while being robust against signal correlated noise.

            Title:
            TELECONTROL PLATFORM - Telecontrol Platform for Industrial Installations
            Author(s):
            Eduardo J. Moya, Oscar Calvo, Jos?María Pérez, Jos? Ramón Janeiro and David García
            Abstract:
            This article explains the telecontrol platform for industrial installations developed by CARTIF Foundation. Using this system it will be able to send control orders and receive notification of alarms from the PLC thanks to SMS messages (Short Messages System) which use GSM technology. In case of requiring a greater flow of data it will use telephone line combined with MODBUS protocol. All this will enable us to monitor and control any industrial installation with a very low cost

            Title:
            TRAFFIC SIGN RECOGNITION WITH CONSTELLATIONS OF VISUAL WORDS
            Author(s):
            Toon Goedem?/DIV>
            Abstract:
            In this paper, we present a method for fast and robust object recognition. As an example, the method is applied to traffic sign recognition from a forward-looking camera in a car. To facilitate and optimise the implementation of this algorithm on an embedded platform containing parallel hardware, we developed a voting scheme for constellations of visual words, i.e. clustered local features (SURF in this case). On top of easy implementation and robust and fast performance, even with large databases, an extra advantage is that this method can handle multiple identical visual features in one model.

            Title:
            DCT DOMAIN VIDEO WATERMARKING - Attack Estimation and Capacity Evaluation
            Author(s):
            O. Dumitru, M. Mitrea and F. Prêteux
            Abstract:
            The first difficulty which should be overcome when trying to evaluate with accuracy the video watermarking capacity is the lack of a reliable statistical model for the malicious attacks. The present paper brings into evidence that the attack effects in the DCT (Discrete Cosine Transform) domain are stationary and computes the corresponding pdfs. In this respect, an in-depth statistical approach is deployed by combining Gaussian mixture estimation with the probability confidence limits. Further on, these pdfs are involved in capacity computation. The experimental results are obtained on a corpus of 10 video sequences (about 30 minutes each), with heterogeneous content (film, news, home, etc).

            Title:
            LEARNING BY EXAMPLE - Reinforcement Learning Techniques for Real Autonomous Underwater Cable Tracking
            Author(s):
            Andres El-Fakdi, Marc Carreras, Javier Antich and Alberto Ortiz
            Abstract:
            This paper proposes a field application of a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a Direct Policy Search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot $ICTINEU^{AUV}$.

            Title:
            MODIFIED LOCAL NAVIGATION STRATEGY FOR UNKNOWN ENVIRONMENT EXPLORATION
            Author(s):
            Safaa Amin, Andry Tanoto, Ulf Witkowski, Ulrich Rückert and Saied Abdel-Wahab
            Abstract:
            This paper presents an algorithm for unknown environment exploration. Our algorithm based on the local navigation algorithm (LNA) that we have described in a previous paper. The LNA doesn’t take into account the case in which the robots are trapped and stop exploring the environment. In this paper, we propose some modifications to overcome this problem and demonstrate it by using real robots. For validation purpose, we ran several experiments using mini-robot Khepera II running on the Teleworkbench. The complete environment is divided into small quadratic patches with some objects placed in it representing obstacles. With on-board infrared sensors and wheel encoder, the robot can successfully explore the unknown environment. Moreover, by calculating the distance to surrounding patches, the implemented algorithm will minimize the distance traveled, and in turn of consumed energy and time. This paper also shows the advantage of using the Teleworkbench for performing experiments using real robots.

            Title:
            REAL TIME TRACKING OF AN OMNIDIRECTIONAL ROBOT - An Extended Kalman Filter Approach
            Author(s):
            Jos?Gonçalves, Jos?Lima and Paulo Costa
            Abstract:
            This paper describes a robust localization system, similar to the used by the teams participating in the Robocup Small size league (SLL). The system, developed in Object Pascal, allows real time localization and control of an autonomous omnidirectional mobile robot. The localization algorithm is done resorting to odometry and global vision data fusion, applying an extended Kalman filter, being this method a standard approach for reducing the error in a least squares sense, using measurements from different sources

            Title:
            IMPLEMENTATION OF A HOMOGRAPHY-BASED VISUAL SERVO CONTROL USING A QUATERNION FORMULATION
            Author(s):
            T. Koenig and G. N. De Souza
            Abstract:
            In this paper, we present the implementation of a homography-based visual servo controller as introduced in [4]. In contrast to other visual servo controllers, this formulation uses a quaternion representation of the rotation. By doing so, potential singularities introduced by the rotational matrix representation can be avoided, which is usually a very desirable property in, for example, aerospace applications such as for visual control of satellites, helicopters, etc. The movement of the camera and the image processing were performed using a simulation of the real environment. This testing environment was developed in Matlab-Simulink and it allowed us to test the controller regardeless of the mechanism in which the camera was moved and the underlying controller that was needed for this movement. The final controller was tested using yet another simulation program provided by Kawasaki Japan for the UX150 industrial robot. The setup for testing and results of the simulations are presented in this paper.

            Title:
            ROBOT LOCALIZATION BASED ON VISUAL LANDMARKS
            Author(s):
            Hala Mousher Ebied, Ulf Witkowski, Ulrich Rückert and Mohamed Saied Abdel-Wahab
            Abstract:
            In this paper, we will consider the localization problem of the autonomous minirobot Khepera II in a known environment. Mobile robots must be able to determine their own position to operate successfully in any environments. Our system combines odometry and a 2-D vision sensor to determine the position of the robot based on a new triangulation algorithm. The new system uses different colored cylinder landmarks which are positioned at the corners of the environment. The main aim is to analyze the accuracy and the robustness in case of noisy data and to obtain an accurate method to estimate the robot’s position.

            Title:
            ALTITUDE CONTROL OF SMALL HELICOPTERS USING A PROTOTYPE TEST BED
            Author(s):
            Nikos I. Vitzilaios and Nikos C. Tsourveloudis
            Abstract:
            In this paper we present an experimental test bed for the development and evaluation of control systems for unmanned helicopters. The test bed consists of a small unmanned helicopter, mounted on a flying stand that permits all possible movements but prevents the helicopter from damaging or crashing. A fuzzy controller is developed in MATLAB and tested in the helicopter using the test bed. The controller is able to perform hovering and altitude control. Experimental results are presented for various test cases.

            Title:
            AN APPROACH TO OBTAIN A PLC PROGRAM FROM A DEVS MODEL
            Author(s):
            Hyeong T. Park, Kil Y. Seong, Suraj Dangol, Gi N. Wang and Sang C. Park
            Abstract:
            Proposed in the paper is an approach to generate the PLC code from the Discrete Event System Specification (DEVS) model. DEVS have been widely accepted to model the real system for the discrete event system simulation. The objective of this paper is to generate PLC control code from the DEVS model. To achieve it, this paper proposes two steps. First step is to convert the real system into the virtual model using the ‘three-phase modeling procedure? In the second step, the obtained model is formalized with DEVS formalism. The final model consists of different components, among them the state manager and the flow controller model plays vital role to generate PLC code. In this paper, proposed steps are described with a work cell example.

            Title:
            COMPARATIVE STUDY OF ROBOT-DESIGNS FOR A HANDHELD MEDICAL ROBOT
            Author(s):
            Peter P. Pott, Markus L. R. Schwarz, Achim Wagner and Essameddin Badreddin
            Abstract:
            Robotic systems are used within a great variety of medical disciplines. A handheld robot promises a number of advantages compared to conventional (medical) robots but this approach leads to strict specifications regarding size, weight and dynamic properties. A new hybrid kinematics ?the Epizactor ?seems to be advantageous and is compared to two well-known parallel kinematics regarding the ratio of workspace and volume the number of kinematic elements, the cost of computation, the stiffness the effects of clearance, actuation (weight), and accuracy using a well-described industrial method for comparison. It becomes clear that the Epizactor has advantages concerning the ratio of workspace and volume, needs a smaller number of kinematic elements and fewer computations, and has less than half the mass than the parallel kinematics. Its accuracy, stiffness and the effects of clearance are comparable. The advantages of this new kinematic set-up lead to a first deployment within the field of medical robotics.

            Title:
            RE-USING 3D MODELING DATA FOR CONSTRUCTING 3D SIMIULATION DATA
            Author(s):
            Jonggeun Kwak, Min. S. Ko, Sang C. Park and Gi-Nam Wang
            Abstract:
            With the aid of the powerful computational ability and software tools, we undergo rapid change in a whole product manufacturing process. In a traditional way, it took long time and cost to build real manufacturing line. The behind time change for the manufacturing process ends up with supplementing large amount of budget. Therefore early detecting the errors on manufacturing process saves quite a big amount of time and money. As a result, the need for plant simulations rises. When we simulate manufacturing line on a virtual environment, it is not easy to acquire 3D data. If we have 3D CAD data, we can reuse them for each tools, products and equipments for the manufacturing line. Even in this case, the size matters. The large size of CAD data makes it difficult for us to directly use CAD data for simulation. As the CAD data and simulation data differs in their own purpose, we can reduce the size of the CAD data without losing simulation purpose. In this paper we propose effective methods for reducing the size of the CAD data and re-using them for simulation, assuming the 3D CAD data are already available.

            Title:
            AN OPTIMIZATION PROCEDURE TO RECONSTRUCT THE AUTOMOBILE INGRESS MOVEMENT
            Author(s):
            Ait El Menceur M. O., P. Pudlo, F.-X. Lepoutre and P. Gorce
            Abstract:
            To simulate the automobile ingress movement, joint angles are needed. The joint angles are computed from the experimental data issued from an optoelectronic motion capture system. As these systems are often corrupted by problems linked either to the system or to the experimentation, the computed angles are biased. Lempereur et al., (2003b) proposed an optimization procedure to remedy to this problem. However, their method gives good results only on the end effectors trajectories, while the other bodies?trajectories are not considered by their method. That degrades their positions and causes eventual collisions of these parts with the vehicle’s parts. On the other hand the corrected angles present some vibrations causing unrealistic simulation. In this paper we present a multi objective optimization based procedure to correct the joint articulation angles in automobile ingress movement for an elderly person. Our method minimises the distance between all reconstructed trajectories with the real ones at each step of time. Our method follows a kind of compromise between all trajectories of the model. Our method gives better global results. Correction of the joint angles allows a realistic simulation.

            Title:
            USING STEREO VISION AND TACTILE SENSOR FEATURES - For Grasp Planning Control
            Author(s):
            Madjid Boudaba, Nikolas Gorges, Heinz Woern and Alicia Casals
            Abstract:
            Planning the grasp positions either from vision or tactile sensor one can expected various uncertainties. This paper describes a matching schemes based on stereo vision and tactile sensor. To control the grasp planning execution, initially, the grasping positions are generated from stereo features, then the feedback of tactile features is used to match those positions. The result of matching algorithm is used to control the grasping positions. The grasping process proposed is experimented with an anthropomorphic robotic system.

            Title:
            FOOT STEP PLANNING FOR BIPED ROBOT BASED ON FUZZY Q-LEARNING APPROACH
            Author(s):
            Christophe Sabourin, Kurosh Madani, Weiwei Yu and Jie Yan
            Abstract:
            Biped robots have more flexible mechanical system and can move in more complex environment than wheeled robots. Its abilities to step over static or dynamic obstacles allow to the biped robot to cross uneven terrain where ordinary wheeled robots can fail. Consequently, the choice of the landing point for the foot of the swing leg is crucial when biped robots moves in uneven terrain. In this paper we present a footstep planning allowing to biped robots to step over dynamic obstacles. This can be done by adjusting step-length of the biped robot in advance. Our footstep planning strategy is based on a fuzzy Q-learning concept. In comparison with other previous works, one of the most interest of our approach is its good robustness because the proposed footstep planning is also efficient in the case of unpredictable motion of the obstacle.

            Title:
            ENVIRONMENT FOR DESIGNING AND SIMULATING CONTROL NETWORKS AT DIGITAL HOME
            Author(s):
            Jorge Azorín-López, Rafael J. Valdivieso-Sarabia, Andrés Fuster-Guill and Juan M. García-Chamizo
            Abstract:
            A design and simulation environment for control network is presented. Design of control networks could be complex task because there are many heterogeneous technologies. Each network technology uses its own design and configuration software. Also it is necessary realize network installation to validate the correct operation. This fact introduces high temporal and economical costs in the network installation. Simulation as a task inside design methodology allows detect errors prematurely since checks are made to a high level of abstraction. Our approach proposes a design and simulation environment of control network inside digital home. It is based on a design independent from any technology and leaves for latest tasks the technology election. It incorporates a simulation task that allows simulate the network behaviour designed at environment

            Title:
            PEOPLE TRACKING USING LASER RANGE SCANNERS AND VISION
            Author(s):
            Andreas Kräußling, Bernd Brüggemann, Dirk Schulz and Armin B. Cremers
            Abstract:
            Tracking multiple crossing people is a great challenge, since common algorithms tend to loose some of the persons or to interchange their identities when they get close to each other and split up again. In several consecutive papers it was possible to develop an algorithm using data from laser range scanners which is able to track an arbitrary number of crossing people without any loss of track. In this paper we address the problem of rediscovering the identities of the persons after a crossing. Therefore, a camera system is applied. An infrared camera detects the people in the observation area and then a charge--coupled device camera is used to extract the colour information about those people. For the representation of the colour information the HSV colour space is applied using a histogram. Before the crossing the system learns the mean and the standard deviation of the colour distribution of each person. After the crossing the system relocates the identities by comparing the actually measured colour distributions with