CONFERENCE
Area 1 - Intelligent Control Systems and Optimization
Area 2 - Robotics and Automation
Area 3 - Signal Processing, Systems Modeling and Control

WORKSHOPS
Workshop on Artificial Neural Networks: data preparation techniques and application development (ANNs)
Workshop on e-learning and Virtual and Remote Laboratories (VIRTUAL-LAB)

Area 1 - Intelligent Control Systems and Optimization

Area 2 - Robotics and Automation
 Title: AIRCRAFT ELECTRICAL MONITORING & FAULT DETECTION Author(s): George Kusic Abstract: Fault detection and electrical system monitoring (management) for aircraft/spacecraft dc or 400 Hz electrical systems is presented. Real-time ‘snapshot’ data is collected from current and voltage measurement transducers on radial or loop aircraft electrical system and introduced into a State Estimator. The State Estimator ‘smoothes’ the data, detects bad transducers, and calculates the best estimate of the voltage and phase angle at busses of the network, i.e., the ‘state’ of the network. Experimental results of estimation and fault detection are presented. Title: CONTROL THROUGH STATE CONVERGENCE OF TELEOPERATION SYSTEMS WITH VARYING TIME DELAY Author(s): José M. Azorín, Oscar Reinoso, José M. Sabater and Rafael Aracil Abstract: Teleoperation systems that use Internet as communication channel must deal with varying time delays. In these situations, the system can become unstable due to the irregular variations of the time delay. In this paper, a control method of teleoperation systems that we presented considering constant time delays is applied to control a teleoperation system with varying time delays. The control gains obtained with a constant time delay can be used to control the teleoperation system with varying time delays because of the control method robustness. Simulation and experimental results are presented to illustrate the validity of the method. Title: A SHALLOW DRAFT VEHICLE FOR INTERDISCIPLINARY RESEARCH AND EDUCATION Author(s): Carl Steidley, Ray Bachnak, Wien Lohatchit, Alex Sadovsky, and Cody Ross Abstract: Water quality data collection in shallow water areas can be a challenging task. Obstacles encountered in such environments include difficulty in covering large territories and the presence of inaccessible areas due to a variety of reasons such as a soft bottom or contamination. There is also a high probability of disturbing the test area while placing the sensors. This paper describes a NASA-funded project, which has had a great deal of student involvement and is currently in the test phase, to develop a remote-controlled, shallow-draft vehicle designed as a supplemental tool for our studies of the South Texas Coastal waters. The system transmits environmental data wirelessly via a radio to a docking and control station in real-time. Title: ANALYSIS OF THE ARCHITECTURE AND RELIABILITY OF DATA TRANSMISSION NETWORK USED FOR RADIO BASED CAB SIGNALING SYSTEM Author(s): Wang Junfeng, Zhang Yong, Wang Huashen and Wang Xishi Abstract: The application background and basic structure of train control system based on the combination of Radio Based Cab Signaling (RBCS) and Automatic Train Protection (ATP) is introduced. The architecture of the data transmission network used for RBCS is analyzed in detail, together with the reliability of radio data transmission. Title: MOTION PLANNING APPROACH OF A MULTI-FINGERED ROBOT FOR CARTON FOLDING OPERATIONS Author(s): Hidetsugu Terada and Takayuki Kobayashi Abstract: The motion planning approach of a multi-fingered robot for carton folding operations has been newly developed. This approach considers the loci of the tool center point for carton flap folding operations. Also that considers the push or fixing points of the carton flap. This approach is calculated from the rotating angle of a carton flap folding and the contact position with robot finger head and carton surface, using inverse kinematics. And this approach can be applied to changes of a carton size or a folding position. In cases in which the carton flap is folded using this approach, the robot finger head touches the carton surface without slipping and moves along circular continuous path. Therefore in case of the rectangular carton box folding, each robot finger moves in each 2.5-dimensional Cartesian frame. In this report, the proposed approach is verified using a prototype robot system. This prototype system consists of two pairs of the robot fingers and rotating mechanism for carton paper. Each finger has a 3-DOF SCARA type robot and a 1-DOF linear motion system. The testing carton boxes can fold to the desired shape. Title: TWO APPROACHES FOR A SERVOMECHANISM CONTROL SYSTEM USING COMPUTER VISION Author(s): João Manual R. S. Tavares, Ricardo Ferreira and Francisco Freitas Abstract: In this paper a servomechanism control system based on computational vision is presented. The control Images, based in hand language, are acquired by a generic webcam and processed, in the working phase, in quasi real time. For this processing, two approaches were considered: in the first one, we used the object control moments to identify the desired order; in the second approach, we used Images control orientation histograms. In both approaches, the preset orders Images to be considered for the servomechanism vision control are acquired in the learning phase. The used servomechanism and the two approaches used for the vision control system are described and some vantages and weakness of each are indicated. An example of an image control order set, which works satisfactory, is also presented and some conclusions and future works are also addressed. Title: ON THE DECENTRALIZED CONTROL OF LARGE DYNAMICAL COMPLEX SYSTEM Author(s): M. Kidouche, M. Zelmat and A. Charef Abstract: This paper describes a systematic procedure to build reduced order analytical models for a design of decentralized controllers for large scale interconnected dynamical systems. The design method employs Davison techniques to affect decoupling of the interconnections into its subsystems components which is done by using the most dominant eigenvalues and the most influent inputs in each subsystem. In this way, advantage can be taken of the special structural feature of a given system to devise feasible and efficient decentralized strategies for solving large control problem which are impractical to solve by one shot centralized methods. Title: PREVISUALIZATION IN ROBOTICS: AN ATOMIC APPROACH Author(s): Mauno Rönkkö Abstract: In this paper, we discuss use of previsualization in robotics. In previsualization, a computer animates a highly underspecified model; thus, helping the designers to detect missing components. When applied to robotics, previsualization should reveal detailed dynamics that is not explicitly specified in the model. In particular, it should reveal interaction dynamics of the physical components. Such a requirement is non-trivial. In this paper, we investigate an atomic approach that uses emergent dynamics to reveal the interaction dynamics. The approach is based on use of atoms that obey simple, compositional interaction laws. The laws produce emergent interaction dynamics for physical components composed of atoms. As the main contribution, we shall illustrate how the atomic approach, despite its simplicity, captures compactly non-trivial settings, and reveals effortlessly intricate dynamics that are otherwise considered too laborious for modelling. Title: PREDICTED POLAR MAPPING FOR MOVING OBSTACLE DETECTION Author(s): Young-Joong Kim, Beom-Soo Kim and Myo-Taeg Lim Abstract: This paper presents the predicted polar mapping that is to improve the efficiency of an unexpected moving obstacle detecting system in a single vision-based robot. The polar mapping is used to simplify the segmentation of moving objects from the background and is performed with the focus of expansion (FOE) as the center. When the movement of the robot per a step becomes a bit large, then static objects or background are detected as moving objects. Thus, the velocity of the robot becomes so slow. Therefore, to enlarge the movement of the robot and to improve this system, we propose the predicted polar mapping that predicts the polar mapped image after robot moves to be admissible. In order to verify experimentally our proposed procedure, we make several comparative tests in the corridor. Title: FORCE RIPPLE COMPENSATOR FOR A VECTOR CONTROLLED PM LINEAR SYNCHRONOUS MOTOR Author(s): Markus Hirvonen, Heikki Handroos and Olli Pyrhönen Abstract: A dynamic model including non-idealities for a permanent magnet linear synchronous motor (PMLSM) is postulated and verified. The non-idealities acting on the physical linear motor are measured and analyzed. These experimental results are utilized in the model. The verified simulation model is used in developing a force disturbance compensator for the velocity controller of the motor. The force non-idealities, such as the cogging force, friction and load force variation, are estimated using a disturbance observer. The acceleration signal in the observer is derived through the use of a low-acceleration estimator. The significant effects of the disturbance compensator on the simulated and measured dynamics of the motor are shown. Title: MOTION PLANNING FOR MOBILE ROBOTS IN DYNAMIC ENVIRONMENTS Author(s): Jing Ren, Kenneth. A. McIsaac and Xishi Huang Abstract: In this paper, we present an agent-based motion planning technique for a multi-robot team in a complex dynamic environment. We define a cell-based navigation control law that can guide the robot team through the environment while avoiding collisions with both static and dynamic obstacles and other team members. To further speed up the robots' move and overcome the zigzagging phenomenon, we extend our modified Newton's method to the dynamic environment and greatly improved the system performance. To illustrate our techniques, we consider a robot team motion planning problem in a complex maze'' with obstacles of arbitrary shape. First, we assign potential values to a set of landmarks based on their shortest distance to the goal, and then we use a spline function to generate a potential field for the entire workspace, which is inherently free of undesired local minima. Simulation results show that robots can successfully transport materials along an optimal and collision-free path and reach the goal in a complex and dynamic maze environment. Finally we proved the team stability under all defined control laws. Title: LASER-BASED ADAPTIVE CRUISE CONTROL FOR INTELLIGENT VEHICLES Author(s): Miguel Ángel Sotelo, David Fernández, Eugenio Naranjo, Carlos González, Ricardo García, Teresa de Pedro and Jesús Reviejo Abstract: Vehicle and highway automation is believed to reduce the risk of accident, improve safety, increase capacity, reduce fuel consumption and enchance overall comfort and performance for drivers. One of the most important research topics in the field of Intelligent Transportation Systems (ITS) is Adaptive Cruise Control (ACC), aiming at adapting the vehicle speed to a predefined value while keeping a safe gap with regard to potential obstacles. For this purpose, a laserscanner system provides the distance between the ego vehicle and the preceding vehicle on the road. Laserscanners are able to observe the vehicle environment in order to detect, track, and classify the surrounding objects and thus providing data for active safety systems. The complete system can be understood as a Laser-based ACC controller, based on Fuzzy Logic, which assists the vehicle velocity control offering driving strategies and actuation over the throttle of a car. This controller is embedded in an automatic driving system installed in two testbed mass-produced cars operating in a real environment. The results obtained in these experiments show a good performance of the Laser-based gap controller, which is adaptable to all speeds and safe gap selections. Title: HYBRID CONTROL DESIGN FOR A ROBOT MANIPULATOR IN A SHIELD TUNNELING MACHINE Author(s): Jelmer Braaksma, Ben Klaassens, Robert Babuska and Cees de Keizer Abstract: In a novel shield tunneling method, the tunnel lining is produced by an extrusion process with continuous shield advance. A robotic manipulator is used to build the tunnel supporting formwork, consisting of rings of steel segments. As the shield of the tunnel-boring machine advances, concrete is continuously injected in the space between the formwork and the surrounding soil. This technology requires a fully automated manipulator, since potential human errors may jeopardize the continuity of the tunneling process. Moreover, the environment is hazardous for human operators. The manipulator has a linked structure with seven degrees of freedom and it is equipped with a head that can clamp the formwork segment. To design and test the controller, a dynamic model of the manipulator and its environment was first developed. Then, a feedback-linearizing hybrid position-force controller was designed. The design was validated through simulation in Matlab/Simulink. Virtual reality visualization was used to demonstrate the compliance properties of the controlled system. Title: INTEGRATING A POTENTIAL FIELD BASED PILOT INTO A MULTIAGENT NAVIGATION ARCHITECTURE FOR AUTONOMOUS ROBOTS Author(s): Manikanth Mohan, Dídac Busquets, Ramon López de Màntaras and Carles Sierra Abstract: In this paper we present a new Pilot for a Multi-Agent based control architecture for Autonomous Robots. This Pilot is based on the use of virtual potential fields and is easy to implement yet effective. The Pilot functions as an autonomous agent in a complex Multi-Agent Architecture for the control and navigation of an autonomous robot. In this architecture, various agents are responsible for different tasks, and they might have to compete and cooperate for the successful completion of a particular navigation mission. The interaction between different agents is achieved through the use of a bidding mechanism. In this respect, we also present a way to define the bid for the new pilot, so that the pilot can be integrated easily into the Multi-Agent Architecture. The pilot has been tested both on simulations and navigation experiments involving a real robot and it has given successful and encouraging results. We also deal with some problems of this pilot and ways to get around them. Title: VERTICAL INTEGRATION OF TTP/A FIELDBUS SYSTEMS USING WEB SERVICES Author(s): Volker Turau, Marcus Venzke, Christoph Weyer and Yesenia Vigil Abstract: This paper presents a generic technique to expose data and control of fieldbus systems to applications located at the level of operational management. To provide a high degree of interoperability between the operational level and different fieldbus systems we utilize standardized techniques such as XML, HTTP, and Web services which can be deployed independently of the platform. The proposed service is based on the interface file system for TTP/A smart transducers. The defined interface provides high level abstractions appropriate for the integration into business applications and considers the latency introduced by the internet protocols. Title: TRACKING OF EXTENDED CROSSING OBJECTS USING THE VITERBI ALGORITHM Author(s): Andreas Kräussling, Frank E. Schneider and Dennis Wildermuth Abstract: Tracking, which means determining the positions of the humans in the surrounding, is one of the goals in the field of mobile robots that operate in populated environments. This paper is concerned with the special problem of tracking expanded objects under such constraints. A solution in form of a Viterbi based algorithm, which can be useful for real--time systems, is presented. Thus a Maximum--a--posteriori (MAP) filtering technique is applied to perform the tracking process. The mathematical background of the algorithm is proposed. The algorithm is tested and evaluated on real and simulated data. The method uses the robots' sensors in form of a laser range finders and a motion and observation model of the objects being tracked. The special problem of the crossing of two expanded objects is considered. The mathematical background for this problem is lighted and a solution for it in form of a heuristic algorithm is proposed. This algorithm is tested on simulated and real data. Title: AN INTEGRATED ENVIRONMENT FOR MACHINE SYSTEM SIMULATION, REMOTE MONITORING AND FAULT DETECTION Author(s): Amos Ng, Leo De Vin, Martin Sundberg, Fredrik Oldefors, Philip Moore and Sanho Yeo Abstract: Machine service and maintenance is an intricate specialist task and machine builders often have to provide worldwide service at short notice. Machine builders would benefit enormously from the possibility to monitor and diagnose equipment operating at distant locations – both for condition-based preventive maintenance and for diagnostic purposes before flying in qualified maintenance personnel and spare parts. This paper introduces an innovative virtual engineering framework that extends the kinematics modelling and dynamics modelling capability of advanced machine simulation systems to incorporate remote monitoring and fault detection features. Specifically, it addresses the software environment that is designed to facilitate the tight integration between virtual engineering tools (machine system simulation), machine controllers (real/simulated) and model-based fault detection schemes. The underlying real-time communication framework based on the publish-subscribe model and applications interfacing techniques are also presented. Title: FUZZY CONTROLLER DESIGN FOR A THREE JOINT ROBOT LEG IN PROTRACTION PHASE - AN OPTIMAL BEHAVIOR INSPIRED FUZZY CONTROLLER DESIGN Author(s): Mustafa Suphi Erden and Kemal Leblebicioğlu Abstract: A fuzzy controller design is performed for a three joint robot leg in protraction phase. The aim is to develop a controller to carry the tip point to any given destination. The design is based on the inspirations derived from optimal behaviors of the leg. The optimal trajectories are obtained by using optimization methods utilizing “numerical gradient” and based on “optimal control” successively. Separate fuzzy controllers are designed for each actuator. In writing the rules each actuator is considered to be an independent agent of the leg system. The protraction motion is divided into two epochs. For each epoch different controller systems are designed to switch from one to the other in between. The crucial idea in this work is the “multi agent perspective” in designing separate fuzzy controllers for the separate joints. The results of the overall controller system are successful in carrying the tip point to any given destination, following a path resembling the optimal one. Title: MOCONT LOCATION MODULE: A CONTAINER LOCATION SYSTEM BASED ON DR/DGNSS INTEGRATION Author(s): Joseba Landaluze, Victoria del Río, Carlos F. Nicolás, José M. Ezkerra and Ana Martínez Abstract: The problem of identifying and adequately positioning containers in the terminal yard during handling with Reach Stackers still remains to be solved in an appropriate manner, while this is extremely important in making the identification and positioning operations automatic. A precise knowledge in the Terminal Operating System (TOS) of such data in Real Time would have considerable economic impact on the logistic treatment of operations. The MOCONT system sets out to provide a solution to this lack. In particular, the MOCONT Location Module establishes the position of the container in the yard while it is being handled by a Reach Stacker. This system is based on the integration of the Differential Global Navigation Satellite System (DGNSS) with a Dead Reckoning (DR) inertial system. This article presents the general characteristics of the MOCONT Location Module, its structure, and the structure of data fusion, besides some results obtained experimentally. Title: VISION-BASED TRAFFIC SIGN DETECTION FOR ASSISTED DRIVING OF ROAD VEHICLES Author(s): Miguel Ángel García, Miguel Ángel Sotelo and Ernesto Martín Gorostiza Abstract: A system for real-time traffic sign detection is described in this paper. The vision-based traffic sign detection module developed in this work is intended for assisted driving of road vehicles by handling color Images in RGB (Red, Green, Blue) format. In a first step a preattentive area of interest is determined based on the vertical projection of edge pixels. In a second step, a shape analysis is performed. In a third step, a color analysis is performed, and finally, a template is adjusted. Some results obtained on a series of real road Images are presented in order to illustrate the robustness of the detection system Title: CYCLOP SYSTEM: MOTION CONTROL OF MULTI-ROBOTS THROUGH A SINGLE EYE Author(s): George Tho, Douglas Tavares, Pablo Alsina and Luiz Gonçalves Abstract: We propose a way to control several robots at a glance by using visual data provided by a single vision camera. Position and orientation of the group is given by a main robot (a master) which has a very simple camera on its top. This robot also has two encoders for determining its positioning related to the origin. The other (slave) robots have no position/orientation sensors as camera/angle-sensors. Their only local sensing capabilities are light (infra-red) and bump sensors. They have a top mark that allows the master discovering their orientation and positioning through the vision software. All robots can be controled by using a control software running in a host computer, through a communication protocol also developed in this work. The robots have some software tools running inside a local processor and memory so they can perform some tasks autonomously, as obstacle avoidance. The main goal is to control all slave robots to stay inside the field of view of the master. With this behavior, the master can have control over the slaves position and can eventually send some of them to perform usefull tasks in certain places, inside its field of view. Title: PLAYING WITH ROBOTS AND AVATARS IN MIXED REALITY SPACES Author(s): V. Antunes, R. Wanderley, T. Tavares, P. Alsina, G. Lemos and Luiz Gonçalves Abstract: We propose a hyperpresence system designed for broad manipulation of robots and avatars in mixed reality spaces. The idea is to let human users play with robots and avatars through the internet via a mixed reality system interface. We make a mixing between hardware and software platforms for control of multi-user agents in a mixed reality environment. We introduce several new issues (or behaviors) as Remote Control'', Augmented Reality'' for robots, making robots Incarnating'' avatars and user humans connected through the Internet. A human user can choose which role he/she wants to play. The proposed system involves a complex implementation of heterogeneous software and hardware platforms including their integration in a real-time system working through the Internet. We performed several tests including experiments using different computer architectures and different operating systems, in order to validate the syustem. Title: PLATFORM-BASED TELEOPERATION CONTROL OF SYMBIOTIC HUMAN-ROBOT SYSTEM Author(s): Tao Zhang, Vuthichai Ampornaramveth, Md. Hasanuzzaman, Pattara Kiatisevi and Haruki Ueno Abstract: This paper presents a platform-based teleoperation control approach of symbiotic human-robot system. With frame-based knowledge representation, features of robots, human-robot interface and cooperative operation of symbiotic human-robot system are defined in the Software Platform of Agents and Knowledge Management (SPAK). By means of this software platform, human can communicate with robots using human-robot interface. Cooperative operation of multiple robots can be implemented by teleoperation control through wireless network. In this paper, platform-based teleoperation control of an actual symbiotic human-robot system comprised of human, humanoid robot (Robovie) and entertainment robot (AIBO) is implemented and the experimental results demonstrate its effectiveness. Title: A LATERAL DIRECTOR AUTOPILOT DESIGN FOR CONFLICT RESOLUTION ALGORITHMS Author(s): Mustafa Suphi Erden and Kemal Leblebicioğlu Abstract: Conflict resolution, namely avoidance of aircraft crushes, is one of the main problems to be solved in a free flight based air traffic system. In our previous work we had studied on three conflict resolution techniques, which were based on potential fields, negotiation, and the amount of the danger and concession, respectively. In the work presented here, linearized lateral aircraft dynamics is incorporated with these conflict resolution techniques. A lateral director autopilot is designed for this purpose. These three conflict resolution techniques are tested and compared on the autopilot-aircraft system. The simulation results are presented. The effects of aircraft dynamics on the generated paths are discussed. Title: AVOIDING VISUAL SERVOING SINGULARITIES USING A COOPERATIVE CONTROL ARCHITECTURE Author(s): Nicolas García Aracil, C. Pérez, Luis Payá, Ramon Ñeco, Jose Maria Sabater and Jose Maria Azorín Abstract: To avoid the singularities of an image-based visual control of an industrial robot (Mitsubishi PA-10), a simple and efficient control law which combines the information of two cameras in a cooperative way has been developed and tested. One of this cameras is rigidly mounted on the robot end-effector (eye-in-hand configuration) and the other one observes the robot within its workspace (eye-to-hand configuration). The system architecture proposed allows us to control the 6 dof of an industrial robot when typical problems of image-based visual control techniques are produced. Title: POSITION CONTROL OF AN ELECTRO-HYDRAULIC SERVOSYSTEM - A non-linear backstepping approach Author(s): Claude Kaddissi, Jean-Pierre Kenné and Maarouf Saad Abstract: This paper studies the control of an electro-hydraulic servo system using non-linear backstepping approach. Such systems are known to be highly non-linear due to many factors as leakage, friction and especially to the fluid flow expression through the servo-valve. Another fact, often neglected or avoided, is that such systems have a non-differentiable mathematical model for bi-directional applications. All these facets are pointed out in the proposed model. Therefore, such systems control should be based on non-linear strategies. Many experiments showed the failure of classic control with electro-hydraulic systems, unless operating in the neighborhood of a desired value or reference signal. The backstepping is used here to overcome all non-linear effects, but not the non-differentiable aspect. This problem is solved in this paper, by approximating the non-differentiable function by a sigmoid, so that the backstepping could always be used. In fact, simulation results show the effectiveness of the proposed approach in terms of guaranteed stability and zero tracking error. Title: VISUAL SERVOING TECHNIQUES FOR CONTINUOUS NAVIGATION OF A MOBILE ROBOT Author(s): Nicolas García Aracil, Oscar Reinoso, J. M. Azorín, Ezio Malis and Rafael Aracil Abstract: A new method to control the navigation of a mobile robot which is based on visual servoing techniques is presented. The new contribution of this paper could be divided in two aspects: the first one is the solution of the problem which takes place in the control law when features appear or disappear from the image plane during the navigation; and the second one is the way of providing to the control system the reference path that must be followed by the mobile robot. The visual servoing techniques used to carry out the navigation are the image-based and the intrinsic-free approaches. Both are independent of calibration errors which is very useful since it is so difficult to get a good calibration in this kind of systems. Also, the second technique allows us to control the camera in spite of the variation of its intrinsic parameters. So, it is possible to modify the zoom of the camera, for instance to get more details, and drive the camera to its reference position at the same time. An exhaustive number of experiments using virtual reality worlds to simulate a typical indoor environment have been carried out. Title: MAN AND WOMAN DISTINCTION USING THERMOGRAPHY Author(s): Satoshi Nishino, Igarashi Sachiyo and Atsushi Matsuda Abstract: Man and woman distinction is necessary to make security stronger and when various statistics on the visitor are taken in commercial facilities and so on. The conventional method of man and woman distinction is currently determined by using the person's appearance, the person's dress and in such cases, the way of walking, the foot pressure, the hair type.　But, these characteristics can be intentionally changed by human intervention or design. The proposed method gets a difference in the man's and woman's characteristics by taking Images of the heat distribution of the person's face by thermography. This is a man and woman distinction based on the new concept idea which this is used for. Consequently, this can be used to distinguish a man from a woman even if a man turns himself into the woman intentionally (and vice versa), because this method involves biometrics authentication. Title: MOBILE ROBOT LOCALIZATION BY CONSTRAINT PROPAGATION ON INTERVALS Author(s): Mélanie Delafosse, Arnaud Clérentin, Laurent Delahoche and Eric Brassart Abstract: This paper proposes to use constraint propagation on intervals to solve the mobile robot localization problem. The mobile robot is equipped with an exteroceptive sensor and dead-reckoning. These two sensors give imprecise data that are modelled by intervals. Our localization strategy is based on multi target tracking. To this aim, the data given by our two sensors are fused by constraint propagation. So, at the end of the localization process, we get a 3-D subpaving which is supposed to contain the robot’s position in a guaranteed way. The localization imprecision is naturally managed by our method. Title: A DSP-BASED ACTIVE CONTOUR MODEL Author(s): Juan Zapata and Ramón Ruiz Abstract: In this paper a DSP-based active contour model for tracking of the endocardium in a sequence of echocardiographic Images is presented. If a contour is available in the first frame of a sequence, the contours in the subsequent frames are segmented. Deformable active contours is a technique that combine geometry, physics and approximation theory in order to solve problems of fundamental importance to medical image analysis; such as segmentation, representation and matching of shapes, and the tracking of objects in movement. The procedure has been developed on a DSP processor using its hardware features. The results are illustrated using a sequence of four-chambers apical echocardiographic Images. Title: LOCATING AND CROSSING DOORS AND NARROW PASSAGES FOR A MOBILE ROBOT Author(s): Zhiyu Xiang, Vitor Santos and Jilin Liu Abstract: Behaviour based navigation for mobile robot is popular because of its clarity in hierarchy and simplicity in implementation. During the decision of the next behaviour, the environmental information provided from sensors has the priority to be taken into account. In structured indoor environment, the information was divided into three different classes with levels increasing progressively: walls, corners and passages. Besides detecting walls and corners, the paper focuses on narrow passage detecting and crossing. By detecting the Complete Points in the laser map, the two types of narrow passages are easy to find. Two immediate applications of the proposed approach emerge: localization for robots and automatic crossing of passages. The experimental results showed our success Title: MOBILE ROBOT LOCALIZATION USING LINEAR SYSTEM MODEL Author(s): Xu Zezhong and Liu Jilin Abstract: Localization is a fundamental problem for mobile robot autonomous navigation. EKF is an efficient tool for position estimation, but it suffers from linearization errors due to linear approximation of nonlinear system equations. In this paper we describe a position estimation method for mobile robot. Process and measurement equations are linear by appropriately constructing the state vector and system models. The position of mobile robot is estimated recursively based on optimal KF. It avoids linear approximation of nonlinear system equations and is free of linearization error. All these techniques have been implemented on our mobile robot ATRVII equipped with 2D laser rangefinder SICK. Title: HEXAPOD STRUCTURE EVALUATION AS WEB SERVICE Author(s): Leonardo Jelenkovic, Domagoj Jakobovic and Leo Budin Abstract: This paper describes several methods for evaluation of kinematic parameters of a Stewart platform. One of those methods is the calculation of workspace area both in numerical and graphical form. The second method allows us to analyze and estimate inherent mechanism errors that occur due to actuator errors, elastic and thermal deformations and other error sources. Furthermore, another procedure is presented which calculates certain kinematic parameters throughout the workspace area of the model and outputs them as numerical and graphical data. Finally, a forward kinematics algorithm designed for use in real-time conditions and its adaptation is presented. The described algorithms are implemented and made available as web services on the project web site. Title: SIMULTANEOUS LOCALIZATION AND MAPPING BASED ON MULTI-RATE FUSION OF LASER AND ENCODERS MEASUREMENTS Author(s): Leopoldo Armesto and Josep Tornero Abstract: In this paper the SLAM problem in static environments with EKF is adapted for more realistic approaches where sensors have different sampling rates. In particular, the multi-rate fusion is performed with encoders and laser rangers. Moreover, the formulation is general and can be adapted for any multi-sensor fusion application. The proposed algorithm, based on well-known techniques for feature extraction, data association and map building, is validated with some experimental results. This algorithm should been seen as a part of a complete autonomous robot navigation algorithm, also described in the paper. Title: SKILL ACQUISITION PROCESS OF A ROBOT-BASED AND A TRADITIONAL SPINE SURGERY Author(s): Meike Jipp, Peter Pott, Achim Wagner, Essameddin Badreddin and Werner W. Wittmann Abstract: Technological progress greatly revolutionizes medicine. Robots give the opportunity to reach greater accuracy and thus improve the medical outcome. The results of a surgical invention profoundly depend on the robot system and on the training state of the operator. Since the learning of a surgical invention can be influenced by the complexity of the system, these interconnection are investigated with psychological methods. Therefore, the skill acquisition process of a robot-based surgery is compared to a traditional spine surgery. The usage of an appropriate robot shortens the learning curve of a spine surgery due to a decreased complexity and reduces the impact of the surgeons’ psychomotor abilities on the surgery’s outcome. For the design of a surgical system, different realizations must be tested in advance regarding their cognitive workload to avoid training costs learning the operation of the system, afterwards. The methods used are not restricted to surgical robotics. Title: PARTIAL VIEWS MATCHING USING A METHOD BASED ON PRINCIPAL COMPONENTS Author(s): Santiago Salamanca Miño, Carlos Cerrada Somolinos, Antonio Adán Oliver and Miguel Adán Oliver Abstract: This paper presents a method to estimate the pose (position and orientation) associated to the range data of an object partial view with respect to the complete object reference system. A database storing the principal components of the different partial views of an object, which are generated virtually, is created in advance in order to make a comparison between the values computed in a real view and the stored values. It allows obtaining a first approximation to the searched pose transformation, which will be afterwards refined by applying the Iterative Closest Point (ICP) algorithm. The proposed method obtains very good pose estimations achieving very low failure rate, even in the case of the existence of occlusions. The paper describes the method and demonstrates these conclusions by presenting a set of experimental results obtained with real range data. Title: TOWARDS A CONCEPTUAL FRAMEWORK- BASED ARCHITECTURE FOR UNMANNED SYSTEMS Author(s): Norbert Oswald Abstract: Future unmanned aerial systems demand capabilities to perform missions automatically to the greatest possible extent. Missions like reconnaissance, surveillance, combat, or SEAD usually consist of recurring phases and contain resembling or identical portions such as autonomous flight control, sensor processing, data transmission, communication or emergency procedures. To avoid implementing many similar singular solutions, a systematic approach for the design of an unmanned avionic software architecture is needed. Current approaches focus on a coarse system design, do not integrate off-the-shelf middleware, and do not consider the needs for having on-board intelligence. This paper presents a reference software architecture to design and implement typical missions of unmanned aerial vehicles based on a Corba middleware. The architecture is composed of identical components and rests upon the peer-to-peer architectural style. It describes the internal structure of a single component with respect to autonomous requirements and provides a framework for the rapid development and implementation of new components. The framework separates functionality and middleware by hiding ORB specific statements from components. Experimental tests simulating a reconnaissance mission using various ORB implementations indicate the benefits of having an architectural design supporting multi-lingual multi-process distributed applications. Title: STEREO VISION SENSOR FOR 3D MEASUREMENTS - A complete solution to produce, calibrate and to verify the accuracy of the measurements results Author(s): Liviu Toma, Fangwu Shu, Werner Neddermeyer and Alimpie Ignea Abstract: Our goal was to build a stereo sensor to be used as a 3D measurement tool with direct application in car industry. The distance between the object to be measured and the stereo sensor is situated between 200 mm and 300 mm. In this paper we will present our solutions developed in order to produce, to calibrate and to verify a stereo sensor used to measure 3D coordinates with an accuracy of 0.1 mm. The measurement area is defined by a square having a side of 100 mm. We have brought two important contributions to the existing solutions. The first one is represented by the solution, we developed, to compute the coefficient of the radial distortion. The second one is represented by the image processing algorithm, developed by us, in order to minimize the errors that occur from the non-correspondence problem. The most important issues that must be solved are to define a camera model, in order to simulate as good as possible a real camera, and to be able to identify the same point with both cameras of the stereo sensor (correspondence problem), in order to reduce the measurement errors. Title: INTERACTIVE SOFTWARE FOR SYMBOLIC MODELING OF PHYSICAL SYSTEMS USING GRAPHS Author(s): André Laurindo Maitelli and Gilbert Azevedo da Silva Abstract: This paper presents the ModSym, a computational environment for teaching of control systems. The software implements a graphical interface for physical systems modeling using graphs. Based on the energy concept, the ModSym generalizes physical elements and dynamics variables of several physical domains as electrical, mechanical and fluid. This approach allows to represent and to connect elements of different systems in a linear graph model. Algorithms implemented in the software obtain a signal flow graph for the system linear graph and, based on it, calculate the symbolic transfer function of system using Mason’s rule. Title: POSITION AND ORIENTATION CONTROL OF A TWO-WHEELED DIFFERENTIALLY DRIVEN NONHOLONOMIC MOBILE ROBOT Author(s): Frederico C. Vieira, Adelardo A. D. Medeiros, Pablo J. Alsina and Antônio P. Araújo Jr. Abstract: This paper addresses the dynamic stabilization problem of a two-wheeled differentially driven nonholonomic mobile robot. The proposed strategy is based on changing the robot control variables from x, y and theta to s and theta, where s represents the robot linear displacement. Using this model, the nonholonomic constraints disappear and we show how the linear control theory can be used to design the robot controllers. This control strategy only needs the robot localization (x, y, theta), not requiring any velocity measurement or estimation. The complete derivation of the control strategy and some simulated results are presented. Title: AUTOMATIC ANALYSIS AND VERIFICATION OF MSC-SPECIFIED TELECOMMUNICATION SYSTEM Author(s): Lyudmila Matvyeyeva, Sergiy Kryvyy and Mariya Lopatina Abstract: Last 20 years formal methods are being used widely to specify formally, analyze, verify and test software and hardware systems, particularly, telecommunication protocols [1]. In this paper automated system is presented which specify formally and verify the telecommunication system. The automated system applies the formal modeling technique of Petri nets and is based on linear algebra methods of analysis in order to research some properties of telephone system. Title: PET-TYPE ROBOT COMMUNICATION SYSTEM FOR MENTAL CARE OF SINGLE-RESIDENT ELDERIES Author(s): Toshiyuki Maeda, Kazumi Yoshida, Hisao Niwa and Kazuhiro Kayashima Abstract: This paper presents a pet-type robot communication system for mental care of single-resident elderies. The robot can communicate with the people autonomously, and also it is Internet-accessible and so that allows the people to communicate with others, directly or using the communication server. The system consists of pet-type robots and the information center. The pet-type robot can treat not only as an information terminal, but as a pet, which can talk to user(s), give information of the local communities, watch over them and send some information to carers at the information center if needed. Considering necessity and sufficiency, the robot has four motors; one for both ears, one for both eyes, one for the nose, and one for the neck. Motions generated by the motors symbolize emotions of the robot, which is essential for our object. We have demonstrated and examined some features of this robot system for elderies and got some good evaluation. Title: VISION-BASED HAND GESTURES RECOGNITION FOR HUMAN-ROBOT INTERACTION Author(s): M. Hasanuzzaman, M. A. Bhuiyan, V. Ampornaramveth, T. Zhang, Yoshiaki Shirai and Haruki Ueno Abstract: This paper presents a vision-based hand gesture recognition system for interaction between human and robot. A real-time two hands gestures recognition system has been developed by combining three larger components analysis based on skin-color segmentation and multiple features based template-matching techniques. Gesture commands are generated and issued whenever the combinations of three skin-like regions at a particular frame match with the predefined gestures. These gesture commands are sent to robots through TCP-IP network for human-robot interaction. A method has also been proposed to detect left hand and right hand relative to face position, as well as, to detect the face and locate its position. The effectiveness of our method has been demonstrated over the interaction with a robot named ROBOVIE. Title: STEREOVISION APPROACH FOR OBSTACLE DETECTION ON NON-PLANAR ROADS Author(s): Sergiu Nedevschi, Radu Danescu, Dan Frentiu, Tiberiu Marita, Florin Oniga, Ciprian Pocol, Rolf Schimidt and Thorsten Graf Abstract: This paper presents a high accuracy stereovision system for obstacle detection and vehicle environment perception in various driving scenarios. The system detects obstacles of all types, even at high distance, outputting them as a list of cuboids having a position in 3D coordinates, size, speed and orientation. For increasing the robustness of the obstacle detection the non-planar road model is considered. The stereovision approach was considered to solve the road-obstacle separation problem. The vertical profile of the road is obtained by fitting a first order clothoid curve on the stereo detected 3D road surface points. The obtained vertical profile is used for a better road-obstacle separation process. By consequence the grouping of the 3D points above the road in relevant objects is enhanced, and the accuracy of their positioning in the driving environment is increased. Title: STRUCTURED LIGHT BASED STEREO VISION FOR COORDINATION OF MULTIPLE ROBOTS Author(s): Gui Yun Tian and Duke Gledhill Abstract: This paper reports a method of coordinating multiple robots for 3D-object handling using structured light based stereo vision. The system structure of using two robots (puma and staubli) for playing chess has been proposed. The key techniques for surface reconstruction and rejection of ‘spike’ are discussed. The feature of the active vision system for 3D object acquisition and their application for robotics and automation are introduced. Following experimental studies, conclusion and further work have been derived. Title: MORPHOLOGICAL CHOICE OF PLANAR MECHANISMS IN ROBOTICS Author(s): Peter Mitrouchev Abstract: In this paper a morphological confined choice for kinematic mechanisms in robotics is presented. It is based on symmetries of structures. Pairs of groups of mutually symmetrical mechanisms are detected. Thus, the number of possible configurations is confined by eliminating the symmetrical ones. Different cases of symmetries have been studied. An expression for the calculation of the number of frames and end-effectors is presented. It enables the reduction of the number of structures by avoiding those that are isomorphic. Following this, examples for applications for various kinematic structures are presented, enabling the field of research to be restricted to the possible solutions. Title: A FUZZY INTEGRATED APPROACH TO IMPEDANCE CONTROL OF ROBOT MANIPULATORS Author(s): Silvério J. C. Marques, Luis F. Baptista and José M. G. Sá da Costa Abstract: This paper presents an integrated fuzzy approach to recover the performance in impedance control, reducing the errors in position and force, considering uncertainties in the parameters of the manipulator dynamic model and contact surface or environment model. This integrated strategy considers a fuzzy adaptive compensator in the outer control loop that adjusts the manipulator tip position to compensate for uncertainties present in the environment. In the inner loop, a fuzzy sliding mode-based impedance controller compensates for uncertainties in the model of the manipulator, based on an inverse dynamics control law. The system error, defines the sliding surfaces of the fuzzy sliding controller as the difference between the desired and actual impedances. In order to evaluate the force/position tracking performance and to validate the proposed control structure, simulations results are presented with a three-degree-of freedom (3-DOF) PUMA robot manipulator. Title: TOWARDS IMPROVING ROBOTIC SOFTWARE REUSABILITY WITHOUT LOSING REAL-TIME CAPABILITIES Author(s): Frederic Pont and Roland Siegwart Abstract: We aim at improving sharability and reusability of software for autonomous mobile robots without sacrificing real-time capabilities. As a first step towards this goal, we focus on real-time Linux and we introduce the concept of a robotic hardware abstraction layer that provides for software reusability on different types of hardware and in real-time or non real-time context. We also present a preliminary implementation using RTAI Linux on the tour-guiding robot RoboX. Title: A REAL TIME GESTURE RECOGNITION SYSTEM FOR MOBILE ROBOTS Author(s): Vanderlei Bonato, Adriano K. Sanches, Márcio M. Fernandes, João M. P. Cardoso, Eduardo D. V. Simões and Eduardo Marques Abstract: This paper presents a vision system to be embedded in a mobile robot, both of them implemented using reconfigurable computing technology. The vision system captures gestures by means of a digital color camera, and then performs some pre-processing steps in order to use the image as input to a RAM-based neural network. The set of recognized gestures can be defined using the system on-chip training capabilities. All the above functionality has been implemented in a single FPGA chip. Experimental results have shown the system to be robust, with enough performance to meet real-time constraints (30 fps), and also high efficiency in the recognition process (true recognition rate of 99.57\%) Title: ROBUST SENSOR BASED NAVIGATION FOR AUTONOMOUS MOBILE ROBOT Author(s): Immanuel Ashokaraj, Antonios Tsourdos, Peter Silson and Brian White Abstract: This paper describes a new approach for mobile robot navigation using an interval analysis based adaptive mechanism for an Unscented Kalman filter. The robot is equipped with inertial sensors, encoders and ultrasonic sensors. The map used for this study is two-dimensional and it is assumed to be known a-priori. Multiple sensor fusion for robot localisation and navigation has attracted a lot of interest in recent years. An Unscented Kalman Filter (UKF) is used here to estimate the robots position using the inertial sensors and encoders. Since the UKF estimates are affected by bias, drift etc, we propose an adaptive mechanism using interval analysis with ultrasonic sensors to correct these defects in estimates. Interval analysis has been already successfully used in the past for robot localisation using time of flight sensors. But this IA algorithm has been extended to incorporate the sensor range limitation as in many real world sensors such as ultrasonic sensors. Additionally the conservativeness in the robot interval position are reduced by taking multiple sets of ultrasonic sensor measurements which are then fused using confidence weights, which depends on the area of intersection with all the other interval robot positions. One of the problems of the use of interval analysis sensor based navigation and localisation is that it can be applicable only in the presence of land marks. This problem is overcome here using additional sensors such as encoders and inertial sensors, which gives an estimate of the robot position using an Unscented Kalman filter in the absence of land marks. In the presence of land marks the complementary robot position information from the Interval analysis algorithm using ultrasonic sensors is used to estimate and bound the errors in the UKF robot position estimate. Title: LINEAR MODELLING AND IDENTIFICATION OF A MOBILE ROBOT WITH DIFFERENTIAL DRIVE Author(s): Patrícia N. Guerra, Pablo J. Alsina, Adelardo A. D. Medeiros and Antônio P. Araújo Abstract: This paper presents a modelling and identification method for a wheeled mobile robot, including the actuator dynamics. Instead of the classic modelling approach, where the robot position coordinates (x,y) are utilized as state variables (resulting in a non linear model), the proposed discrete model is based on the travelled distance increment delta l. Thus, the resulting model is linear and time invariant and it can be identified through classical methods such as Recursive Least Mean Squares. This approach has a problem: delta l can not directly measured. In this paper, this problem is solved using an estimate delta l based on a second order curve approximation. Experimental data were colected and the proposed method was used to identify the model of a real robot. Title: MULTILEVEL DARWINIST BRAIN IN ROBOTS - Initial Implementation Author(s): Francisco Bellas and Richard J. Duro Abstract: In this paper we present a Cognitive Mechanism called MDB (Multilevel Darwinist Brain) based on Darwinist theories and its initial application to autonomous learning by robotic systems. The mechanism has been designed to permit an agent to adapt to its environment and motivations in an autonomous way. The general structure of the MDB is particularized into a two level architecture: reasoning and interaction. This structure corresponds to a generic cognitive model where world, internal and satisfaction models are used to select strategies that fulfil the motivation of the agent. The main idea behind the proposal is that all of the components of the mechanism are obtained and modified through interaction with the environment in real time by means of on line Darwinist processes, allowing for a natural learning curve. The mechanism is able to provide solutions based on experience or original solutions to new situations. The knowledge used by the agent is acquired automatically and not imposed by the designer. Here we discuss the basic operation of the mechanism and demonstrate it through a real example in which a hexapod robot is taught to walk efficiently and to reach an objective around it Title: REALWORLD ROBOT NAVIGATION BY TWO DIMENSIONAL EVALUATION REINFORCEMENT LEARNING Author(s): Hiroyuki Okada Abstract: The trade-off of exploration and exploitation is present for a learnig method based on the trial and error such as reinforcement learning. We have proposed a reinforcement learning algorism using reward and punishment as repulsive evaluation(2D-RL). In the algorithm, an appropriate balance between exploration and exploitation can be attained by using interest and utility. In this paper, we applied the 2D-RL to a navigation learning task of mobile robot, and the robot found a better path in real world by 2D-RL than by traditional actor-critic model. Title: ACTIVE SENSING STRATEGIES FOR ROBOTIC PLATFORMS, WITH AN APPLICATION IN VISION-BASED GRIPPING Author(s): Benjamin Deutsch, Frank Deinzer, Matthias Zobel and Joachim Denzler Abstract: We present a vision-based robotic system which uses a combination of several active sensing strategies to grip a free-standing small target object with an initially unknown position and orientation. The object position is determined and maintained with a probabilistic visual tracking system. The cameras on the robot contain a motorized zoom lens, allowing the focal lengths of the cameras to be adjusted during the approach. Our system uses an entropy-based approach to find the optimal zoom levels for reducing the uncertainty in the position estimation in real-time. The object can only be gripped efficiently from a few distinct directions, requiring the robot to first determine the pose of the object in a classification step, and then decide on the correct angle of approach in a grip planning step. The optimal angle is trained and selected using reinforcement learning, requiring no user-supplied knowledge about the object. The system is evaluated by comparing the experimental results to ground-truth information. Title: SCAN MATCHING WITHOUT ODOMETRY INFORMATION Author(s): Francesco Amigoni, Simone Gasparini and Maria Gini Abstract: We present an algorithm for merging two partial maps obtained with a laser range scanner into a single map. The most unique aspect of our algorithm is that it does not require any information on the position where the scans were collected. The algorithm operates by performing a geometric match of the two scans and returns the best fused map obtained by merging the two partial maps. The algorithm attempts to reduce the number of segments in the fused map, by replacing overlapping segments with a single segment. We present heuristics to speed up the computation, and experimental results obtained with a mobile robot in an indoor environment. Title: A MOBILE ROBOT MAPPING SYSTEM WITH AN INFORMATION-BASED EXPLORATION STRATEGY Author(s): Francesco Amigoni, Vincenzo Caglioti and Umberto Galtarossa Abstract: The availability of efficient mapping systems to produce accurate representations of initially unknown environments is undoubtedly one of the main requirements for autonomous mobile robots. This paper presents a mapping system that has been implemented on a mobile robot equipped with a laser range scanner. The system builds geometrical maps of the environment employing an exploration strategy that takes into account both the distance travelled and the information gathered to determining the observation positions. This strategy is based on stronger mathematical foundations than the exploration strategies proposed in literature: this is the distinctive feature of our approach and constitutes the main original contribution of this paper. Title: FROM PETRI NETS TO EXECUTABLE SYSTEMS: AN ENVIRONMENT FOR CODE GENERATION AND ANALYSIS Author(s): Joao Paulo Barros, Luís Gomes, Rui Pais and Rui Dias Abstract: There is an increased awareness regarding the importance of executable system's specifications, in particular, graphical specifications. Although most Petri nets variants are recognised as a versatile formalism, with an intuitive graphical specifications and a precise semantics, most Petri nets tools limit themselves to graphical editing and some type of simulation, system analysis, or both. This paper presents a new development environment based on Petri nets. This environment enables the use of \emph{ad-hoc} Petri net classes as domain specific languages and allows the net models compositions and evolution through a set of orthogonal and generic modification operations. It also generates ANSI C code (or other executable code) amenable to be implemented in general-purpose hardware platforms, without sophisticated resources available. Additionally, one major environment feature is the use of the same generated executable code, both for simulation and for analysis purposes. Title: ABOUT NATURE OF EMERGENT BEHAVIOR IN MICRO-SYSTEMS Author(s): Sergey Kornienko, Olga Kornienko and Paul Levi Abstract: Micro-robotic systems have very limited computational and communicating resources on board. However they have a broad spectra of tasks (surface cleaning, micro-assembling, collective perception) to be solved. One of approaches to solve these tasks by such capability-restricted systems consists in utilizing emergent properties of many interacting robots. In the presented work we consider the questions what is the emergent behavior in technical systems and how this artificial emergence differs from the natural analogue ? These points are discussed on examples of spatial and functional emergence in micro-systems. Title: ON THE RECONSTRUCTION PERFORMANCE OF COMPRESSED ORTHOGONAL MOMENTS Author(s): George A. Papakostas, Yiannis S. Boutalis, D. A. Karras and B. G. Mertzios Abstract: In this paper, a wavelet-based technique is applied to three moment feature vectors corresponding to three different families of orthogonal moments. The resulted compressed vectors are studied experimentally, in order to extract useful information about their behaviour to a reconstruction procedure. The reconstruction performance of these moments is identical to the amount of image information that they contain to certain moment orders. Since the moment vectors are imposed to compression at the high frequency components, a conclusion about their information redundancy can be also determined. The most efficient moment family, by means of the reconstruction error, will form feature vectors with low dimension, yet with high information content and thus will be very useful for pattern recognition applications, guarantying high recognition rates. Title: AUTOMATIC VISION-BASED MONITORING OF THE SPACECRAFT DOCKING APPROACH WITH THE INTERNATIONAL SPACE STATION Author(s): Andrey A. Boguslavsky, Victor V. Sazonov, Sergey M. Sokolov, Alexandr I. Smirnov and Khamzat S. Saigiraev Abstract: The software package allowing automating the visual monitoring of the spacecraft docking approach with the international space station is considered. The initial data for this complex is the video signal received from the TV-camera, mounted on board the spacecraft. The offered algorithms of this video signal processing in real time allow restoring the basic characteristics of spacecraft motion with respect to international space station. The results of experiments with the described software and real video data about docking approach of the spacecraft Progress with international space station are presented. The accuracy of the estimation of the motion characteristics and perspectives the use of the package are discussed. Title: A CONCEPT LEARNING BASED APPROACH TO MOTION CONTROL FOR HUMANOID ROBOTS Author(s): Kiyotake Kuwayama, Shohei Kato and Hidenori Itoh Abstract: This paper proposes a concept learning-based approach to motion control for humanoid robots. In this approach, the motion control system is implemented with "decision tree learner" for the acquisition of balancing property of itself body and movement and "depth first search technique" for the motion control based on the knowledge concerning balance and stability in the motion. Some performance results by humanoid robot HOAP-1 is reported: stable and anti-tumble motions to stand up from a chair. This paper also reports some performance for the change in the environments; stand up from a chair on slope and different in height. Title: DEAD RECKONING FOR MOBILE ROBOTS USING TWO OPTICAL MICE Author(s): Andrea Bonarini, Matteo Matteucci and Marcello Restelli Abstract: In this paper, we present a dead reckoning procedure to support reliable odometry on mobile robot. It is based on a pair of optical mice rigidly connected to the robot body. The main advantages are that: 1) the measurement given by the mice is not subject to slipping, since they are independent from the traction wheels, nor to crawling, since they measure displacements in any direction, 2) this localization system is independent from the kinematics of the robot, 3) it is a low-cost solution. We present the mathematical model of the sensor, its implementation, and some empirical evaluations. Title: A INTERPOLATION-BASED APPROACH TO MOTION GENERATION FOR HUMANOID ROBOTS Author(s): Koshiro Noritake, Shohei Kato and Hidenori Itoh Abstract: This paper proposes a static posture based motion generation system for humanoid robots. The system generates a sequence of motion from given several postures, and the motion is smooth and stable in the balance. We have produced all the motions of Tai Chi Chuan by the system. Motion generation for humanoids has been studied mainly based on the dynamics. Dynamic based method has, however, some defects: e.g., numerous parameters which can not be always prepared, expensive computational cost and no guarantee that the motions are stable in balance. We have, thus, studied less dependent-on-dynamics approach. A motion is described as a sequence of postures. Our system figure out if we need extra postures to insert for stability. This method enables humanoid robot, HOAP-1 to do Tai Chi Chuan. Title: AUTOLOCALIZATION USING THE CONVOLUTION OF THE EXTENDED ROBOT Author(s): Eduardo Espino, Vidal Moreno, Belen Curto and Ramiro Aguilar Abstract: In order to construct autonomous robots which they move in a indoor environment, it is necessary to solve several problems such as the autolocalization. The problem of the autolocalization in a robot mobile consists of it must find its location within an apriori known map of its surroundings using the perceived distances by its sensors and also taking into account the control signals that drive their wheels. The difficulties come from the fact that the signals of the sensors have noise, as well as the control signals and also the map could differ from the reality of the surroundings. The method which we presented joins the measures of the sensors and the signals of control in the called map of the extended robot; through of the convolution of this map and the a priori map of the environment, we can find the best matching between them, after a search into this calculated values, the location is obtained as a configuration that corresponds to the global maximum convolution. The method was implemented in an sonar-based robot, with kinematics differential. The results have validated widely our proposal. Title: SUPERVISION AND TELECONTROL OF A RADIO BROADCASTING SYSTEM VIA INTERNET Author(s): Joan Aranda and Eduard Sanz Abstract: In this paper a recent application is showed that uses Internet as a supervision tool and remote control of a network of radio-TV relay stations to offer a better service to future clients. The relay stations network occupies a region of about 30.000 km2. The operator of this telecommunications network counts with a SCADA system which permits to the operator monitoring and control of the whole network. With the presented application users of the network can access to real time information about relevant aspects of the emission or change some parameters at anytime and from anywhere thanks to internet. The application has been implemented on a PC equipped with Windows NT 4.0 and it has been developed using VisualStudio 6.0 tools. The aspects of access security and safe communications have been taken care specially. Title: REALISTIC DYNAMIC SIMULATION OF AN INDUSTRIAL ROBOT WITH JOINT FRICTION Author(s): Ronald G. K. M. Aarts, Ben J. B. Jonker and Rob R. Waiboer Abstract: This paper presents a realistic dynamic simulation of the closed-loop tip motion of a rigid-link manipulator with joint friction. The results from two simulation techniques are compared with experimental results. A six-axis industrial Stäubli robot is modelled. The LuGre friction model is used to account both for the sliding and pre-sliding regime. The manipulation task implies transferring a laser spot along a straight line with a trapezoidal velocity profile. Firstly, a non-linear finite element method is used to formulate the dynamic equations of the manipulator mechanism. In a closed-loop simulation the driving torques are generated by the control system. The computed trajectory tracking errors agree well with the experimental results. Unfortunately, the simulation is very time-consuming due to the small time step of the discrete-time controller. Secondly, a perturbation method has been applied. In this method the perturbed motion of the manipulator is modelled as a first-order perturbation of the nominal manipulator motion. Friction torques at the actuator joints are introduced at the stage of perturbed dynamics. A substantial reduction of the computer time is achieved without loss of accuracy. Title: CONSTRUCTION OF THE VORONOI DIAGRAM BY A TEAM OF COOPERATIVE ROBOTS Author(s): Flavio S. Mendes, Júlio S. Aude, Paulo C. V. Pinto and Eliana P.L. Aude Abstract: This paper presents a method for cooperation in the construction of Voronoi diagrams which is suitable for use in dangerous tasks performed by a team of robots. The algorithm has been implemented on a network of eight workstations using the MPI library. Two implementation approaches have been used. In the first one, no communication among the robots is required but some degree of redundancy in the work performed by the robots may result. In the second approach, a more cooperative scheme is adopted and, as a consequence, communication among the robots increases but the work performed by each one is reduced. In both approaches, the calculation time decreases almost linearly when adding robots to the team. Nevertheless, the second approach, more cooperative, has consistently produced better results. With the achieved speed-up, it is possible to use this algorithm in applications where the obstacle configuration within the robot team working area changes with time. Title: DYNAMIC TOOLS TO CONTROL COMPLEX SYSTEMS Author(s): Mahfoud Mabed Abstract: The idea of complex sequencing is strongly related to scheduling and real time systems. It appears when a resource has to be shared by more than one user or when a job must be handled by some concurrent entities. The originality of our research is mainly to build a dynamic link between a scheduling solution and a simulation approach based on Petri Nets (PN). This paper addresses with the modeling of an electroplating line with max plus algebra theory and Petri Nets. As a schedule representing a sequence that contains a series of jobs, we can obtain a corresponding polynomial by using Lagrange interpolation. Then, we can use these polynomials to ensure a real time connection between a schedule procedure and a Petri nets simulation. The use of this approach will lead us to deal with different disturbances. Indeed, for any disturbance we should calculate a new schedule and a new polynomial will be found. This polynomial will be assigned to Petri nets model without modifying its structure. Title: SIMULATION , DESIGN AND PRACTICAL IMPLEMENTATION OF A MOBILE WIRELESS AUTONOMOUS SURVEILLANCE SYSTEM Author(s): T.C. Manjunath, P.S. Shingare and S. Janardhanan Abstract: The paper presents the design, implementation of the a unique type of computer controlled wireless mobile surveillance robot equipped with intelligence. Building an experimental autonomous mobile wireless vehicle, which has the ability to perform in real time environments is both a technical and scientific challenge and demands the development of systems for perception, modeling, planning and navigation. Within this scope, this paper describes the construction of a low cost mobile autonomous robot, intended for educational and surveillance purposes. This is a technology demonstration work. The objective of the work is to design, fabricate each part and construct a mobile robot and control it with a computer through wireless link which would accomplish two dimensional motion on a horizontal plane, moving from one place to another, avoiding obstacles in its path of motion by using infra-red sensors and performing the pick and place motion. The work was undertaken as a sponsored consultation based project under the guidance of the author in the institute. Title: A SKELETON BASED METHOD FOR EFFICIENT 3D OBJECT LOCALIZATION - Application to teleoperation Author(s): Djamel Merad, Narjes Khezami, Malik Mallem and Samir Otmane Abstract: Our aim is to develop a vision system for teleoperation to localize an object. This system has to be used through Internet connection. The recognition problem addressed in this paper is to localize a 3D free-form object from a single 2D view of 3D scene. Using a skeletonization process allows to obtain two graphs, the first one representing an object in the scene (2D skeleton) and the second one representing a database object (3D homotopic skeleton). The method encodes geometric and topological information in the form of a skeletal graph and uses graph isomorphism techniques to match the skeletons and find the one-to-one correspondences of nodes in order to estimate the object’s pose. Knowing skeleton is a set of lines centred within the 3D/2D objects, our method transforms the problem of free form object localization into points and lines pose estimation. Some experimental results on real Images demonstrate the robustness of the proposed method with regard to occlusion, cluster, shadows … Title: A NEW PARADIGM FOR SHIP HULL INSPECTION USING A HOLONOMIC HOVER-CAPABLE AUV Author(s): Robert Damus, Samuel Desset, James Morash, Victor Polidoro, Franz Hover, Chrys Chryssostomidis, Jerome Vaganay and Scott Willcox Abstract: The XXX Lab, in collaboration with YYY, has undertaken the task of designing a new autonomous underwater vehicle (AUV), a holonomic hover-capable robot capable of performing missions where an inspection capability similar to that of a remotely operated vehicle (ROV) is the primary goal. Some shortcomings of the most common torpedo-like AUV have become clear, as interest has increased in using AUVs for new applications – those demanding close inspection, slow movement, and precise positioning. One of the primary issues in this mode of operating AUVs is how the robot perceives its environment and thus navigates. The predominant choices for navigating in close proximity to large iron structures, which precludes accurate fluxgate compass measurements, are all methods that require an AUV to receive position information updates from an outside source (i.e. LBL or USBL assisted location). The new paradigm we present in this paper divorces our navigation routines from any absolute reference frame except the depth of the robot. We argue that this technique offers substantial benefits over assistive-technology approaches, and will present the current status of our project. Title: AUTONOMOUS NAVIGATION ROBOTIC SYSTEM TO RECOGNIZE IRREGULAR PATTERNS Author(s): Danny Dos Santos, Rafael Peñalver and Wilmer Pereira Abstract: This paper presents an approximation of navigation problem under unknown environment using reinforcement learning. The motivation is to represent a robot that can move in a world with streets and intersections. Each intersection has a different quantity of streets (irregular blocks). The selected algorithms were Q-Learning and Value Iteration. The robot was programmed only with Q-Learning and we developed a simulation with both of them. This simulation allows making comparisons in order to determinate in which situation each algorithm is appropriate. Title: ROBUST IMAGE SEGMENTATION BY TEXTURE SENSITIVE SNAKE UNDER LOW CONTRAST ENVIRONMENT Author(s): Shu-Fai Wong and Kwan-Yee Kenneth Wong Abstract: Robust image segmentation plays an important role in a wide range of daily applications, like visual surveillance system, computer-aided medical diagnosis, etc. Although commonly used image segmentation methods based on pixel intensity and texture can help finding the boundary of targets with sharp edges or distinguished textures, they may not be applied to Images with poor quality and low contrast. Medical Images, Images captured from web cam and Images taken under dim light are examples of Images with low contrast and with heavy noise. To handle these types of Images, we proposed a new segmentation method based on texture clustering and snake fitting. Experimental results show that targets in both artificial Images and medical Images, which are of low contrast and heavy noise, can be segmented from the background accurately. This segmentation method provides alternatives to the users so that they can keep using imaging device with low quality outputs while having good quality of image analysis result. Title: VISUAL HAND MOVEMENTS FOR MACHINE CONTROL Author(s): Sanjay Kumar, Dinesh Kant Kumar and Arun Sharma Abstract: A new technique for automated classification of human hand gestures for robotics and computer control applications is presented. It uses view-based approach for representation, and statistical technique for classification. This approach uses a cumulative image-difference technique where the time between the sequences of Images is implicitly captured in the representation of action. This results in the construction of Temporal History Templates (THTs). These THT’s are used to compute the 7 Hu image moments that are invariant to scale, rotation and translation. The recognition criterion is established using K-nearest neighbor (K-NN) mahalanobis distance. The preliminary experiments show that such a system can classify human hand gestures with a classification accuracy of 92%. Our research has been carried on in the robotics framework. The overall goal of our research is to test for accuracy of the recognition of hand gestures using this computationally inexpensive way of dimensionality-reduced representation of gestures for its suitability for robotics. Title: ELECTROMYOGRAPHY BASED FINGER MOVEMENT IDENTIFICATION FOR HUMAN COMPUTER INTERFACE Author(s): Pah Nemuel D and Kumar Dinesh K Abstract: This paper reports experiments conducted to classify single channel Surface Electromyogram recorded from the forearm with the flexion and extension of the different fingers. Controlled experiments were conducted where single channel SEMF was recorded from the flexor digitorum superficialis muscle for various finger positions from the volunteers. A modified wavelet network called Thresholding Wavelet Networks that has been developed by the authors [10] has been applied for this classification. The purpose of this research was towards developing a reliable man machine interface that could have applications for rehabilitation, robotics and industry. The network is promising with accuracy better than 85%. Title: Eye Gaze for Computer Control Author(s): Dinesh Kant Kumar and E. Poole Abstract: This paper reports the results of experiments that were conducted with five subjects to determine the reliability of the use of Electroocular gram (EOG) for controlling computers. Experiments included vertical and horizontal eye motion. Consideration was given to identify a relationship between the angle of the gaze and signal that could be applied to cover all test subjects and generate the required spatial control signals. The results obtained are encouraging. An assessment of the data has concluded that the EOG can be successfully utilised for spatial control applications. The study recommends the choice of bandwidth for the recording, inter and intra subject reliability and difference between the vertical and horizontal movement control. Title: A VISUAL SERVOING ARCHITECTURE USING PREDICTIVE CONTROL FOR A PUMA560 ROBOT Author(s): Paulo Ferreira and João C. Pinto Abstract: A control system for a six degrees freedom Puma robot using a Visual Servoing architecture is presented. Two different predictive controllers, GPC and MPC, are used. A comparison between these two ones and the classical PI controller is performed. A new Robot puma model used as platform for the development of the control algorithms is presented. In this system the camera is placed on the robot’s end-effector and the goal is to control the robot pose to follow a target. A control law based on features extracted from camera Images is used. Simulation results show that the strategy works well and that visual servoing predictive control is faster than a PI control. Title: DIMSART: A REAL TIME - DEVICE INDEPENDENT MODULAR SOFTWARE ARCHITECTURE FOR ROBOTIC AND TELEROBOTIC APPLICATIONS Author(s): Jordi Artigas, Detlef Reintsema, Carsten Preusche and Gerhard Hirzinger Abstract: In this paper a Software Architecture for Robotic and Telerobotic applications will be described. The software is device and platform independent, and is distributed control orientated. Thus, the package will be suitable for any Real Time system configuration. The Architecture will allow designers to easily build complex Control Schemes, easily control and manage them, for any hardware device, and to communicate with other devices with a plug-in/plug-out modular concept. The need to create a platform where control engineers/ designers could freely implement their algorithms, without needing to worry about the device driver and about programing related topics, brought another goal to this project. Implementing a new control algorithm with the Software Architecture, here described, means just to follow a template where, the code itself that the designer has to write, is reduced to the implement the functions which have to do with the controller. We conducted several Teleopertation schemes, which will be here presented as some configuration example. Title: WIRELESS REMOTE MONITORING SYSTEM WITH FLEXIBLY CONFIGURABLE MULTIVISION Author(s): Shinichi Masuda and Tetsuo Hattori Abstract: Novel remote monitoring system for all day outdoor observation using wireless communication is proposed. It consists of three parts: a host station that is PC, remote station (camera and CPU) attached by solar cell and battery for power supply, and wireless sensor with ID signal. The remote station usually performs based on the event driven method by the sensor signal. It also can control the camera according to the sensor’s ID. So the multivision monitoring system is flexibly configurable. This paper describes the details of the system and evaluates the maximum number of connectable remote stations. Since the systems are now really running at many places in Japan, we regard that the fact shows its effectiveness in a practical sense. Title: A METHOD FOR HANDWRITTEN CHARACTERS RECOGNITION BASED ON A VECTOR FIELD Author(s): Tetsuya Izumi, Tetsuo Hattori, Hiroyuki Kitajima and Toshinori Yamasaki Abstract: In order to obtain a low computational cost method for automatic handwritten characters recognition, this paper proposes a combined system of two rough classification methods based on features of a vector field: one is autocorrelation matrix method, and another is a low frequency Fourier expansion method. In each method, the representation is expressed as vectors, and the similarity is defined as a weighted sum of the squared values of the inner product between input pattern and the reference patterns that are normalized eigenvectors of KL (Karhunen-Loeve) expansion. This paper also describes a way of deciding the weight coefficients based on linear regression, and shows the effectiveness of the proposed method by illustrating some experimentation results for 3036 categories of handwritten Japanese characters.

Area 3 - Signal Processing, Systems Modeling and Control