Philippe Lucidarme | Université d'Angers (original) (raw)

Uploads

Papers by Philippe Lucidarme

Computational Optimization and Applications, 2015

In this communication, the characterization of mobile sources is studied. A quasi online identifi... more In this communication, the characterization of mobile sources is studied. A quasi online identification method based on the iterative regularization of ill-posed inverse problem is proposed in order to monitor an evolutionary phenomenon. Several strategies related to sensors choice (adaptive selection of relevant sensors within the fixed network or mobile sensors management) are discussed. To illustrate the investigated approaches, an experimental prototype has been developed in the context of thermal sciences. The experiment is described: design, characterization, exchanges protocols for signals acquisition, movement of mobile elements (sources and sensors).

Dans cette communication, la caractérisation de sources mobiles est étudiée. Pour ce faire, une m... more Dans cette communication, la caractérisation de sources mobiles est étudiée. Pour ce faire, une méthode d'identification quasi en ligne est développée. Basée sur la régularisation itérative d'un problème inverse mal posé, elle permet le suivi de phénomènes évolutifs. Plusieurs stratégies de choix de capteurs (sélection adaptative des capteurs pertinents au sein d'un réseau fixe ou gestion d'une meute de capteurs mobiles) sont discutées. Afin d'illustrer les approches retenues, un prototype expérimental a été conçu dans le cadre du génie thermique. L'ensemble de l'expérimentation est décrit : conception, dimensionnement, caractérisation, protocoles d'échanges pour l'acquisition des signaux, déplacement des éléments mobiles (sources et capteurs) et enfin gestion de l'ensemble du prototype.

This chapter deals with the combination between multi-agent systems and evolutionary computation.... more This chapter deals with the combination between multi-agent systems and evolutionary computation. The first section describes an experiment of the evolutionary learning of an autonomous obstacle avoidance behavior. This first experiment proves the possibility of distributing a genetic algorithm into a real robot population. In the proposed architecture, new crossovers and mutation techniques have been proposed allowing the distribution of the algorithm. The second part of the chapter deals with the decomposition of a unique robot into a multiagent system. In the distributed proposed architecture, the behavior of the robot is dependant from a set of coefficients influencing the motion of each agent. These coefficients are evolutionary optimized. Several fitness functions have been experimented: time, distance and energy. Simulation results show that minimizing the energy is the best strategy, the system may be fault tolerant and the computation of the algorithm is very fast. Future w...

In this paper, a distributed architecture for redun dant robot is presented. In the proposed appr... more In this paper, a distributed architecture for redun dant robot is presented. In the proposed approach, each actuator is respectively associated with an agent and each agent acts independently from the other to reach a common goal . The architecture has been simulated on the model of the humanoid robot HRP2. The architect ure has to deal with a multi-objective

International Conference on Informatics in Control, Automation and Robotics, 2008

This paper presents a survey on the generic evolution of mobile robot' neurocontrollers with ... more This paper presents a survey on the generic evolution of mobile robot' 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

International Conference on Intelligent RObots and Systems - IROS, 2003

This paper presents a method based on simulated annealing to learn reactive behaviors. This work ... more This paper presents a method based on simulated annealing to learn reactive behaviors. This work is related with multi-agent systems. It is a first step towards automatic generation of sensorimotor control architectures for completing complex cooperative tasks with simple reactive mobile robots. The controller of the agents is a neural network and we use simulated annealing techniques to learn the

International Conference on Informatics in Control, Automation and Robotics, 2005

This paper presents a human-scale multi-modal virtual environment. User interacts with virtual wo... more This paper presents a human-scale multi-modal virtual environment. User interacts with virtual worlds using a large-scale bimanual haptic interface called the SPIDAR-H. This interface is used to track user's hands movements and to display various aspects of force feedback associated mainly with contact, weight, and inertia. In order to increase the accuracy of the system, a calibration method is proposed.

2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Proceedings (Cat. No.01TH8556), 2001

This paper presents the implementation of an experimental setup to study the behavior of a group ... more This paper presents the implementation of an experimental setup to study the behavior of a group of purely reactive mobile robots subject to serious unrecoverable failures: some of them have lost mobility, others have lost infrared vision. To survive, each robot must reach a supply center. The eventually degraded mission uses complementary capabilities of the two types of robots by

Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180), 2001

This paper addresses a fast method for optimizing and sizing a multi-robot system. To demonstrate... more This paper addresses a fast method for optimizing and sizing a multi-robot system. To demonstrate the performance of such an approach, a complex heterogeneous system is considered here. It is composed of two populations of robots, having different but complementary abilities. It is shown that it is possible to find the optimum criteria to execute the mission and obtain the best probable solution. It is based on the stochastic model of the Markov chains. The method is applied to a generic mission of multi-robot cooperation. The mission has also been simulated several thousand hundred times on a computer to compare the results and validate the model. It is also possible, with this model, to quickly predict the system evolution from different initial states and study the impact of the variation of some parameters on the global result. Some ongoing experimentations are also introduced.

This project is intended to develop a comprehensive methodology (theory and numerical methods) in... more This project is intended to develop a comprehensive methodology (theory and numerical methods) in order to achieve an optimal design of experiments in the context of nonlinear ill posed problems related to the evaluation of parameters in systems described by partial differential equations (PDE). An experimental prototype will be developed in order to validate the performance of different strategies to identify location of one (or more) heating source using a set of mobile sensors.

Au cours des dernières années, les roboticiens ont pris conscience de l'importance d'implémenter ... more Au cours des dernières années, les roboticiens ont pris conscience de l'importance d'implémenter les méthodes et algorithmes proposés par la recherche sur de véritables robots afin de valider et de compléter les résultats de simulations. Le robot Type 1 ), présenté ici, est un robot mobile de petite taille permettant de réaliser en laboratoire de nombreuses expériences. Ce papier présente et justifie dans un premier temps les choix techniques lors de la conception du robot. La seconde partie du papier présente des extensions qui ont été ajoutées au robot : une caméra, un bras manipulateur miniature et une caméra panoramique. La dernière partie décrit quelques expériences qui ont été menées à l'aide de ce robot depuis sa création.

ABSTRACT à Angers (France) du 12/06 au 13/06/2013

2012 1st International Conference on Systems and Computer Science (ICSCS), 2012

ABSTRACT An object recognition strategy based on artificial radial basis functions neural network... more ABSTRACT An object recognition strategy based on artificial radial basis functions neural networks is presented in this paper. The general context of this work is to recognize object from captures made by a mobile robot. Unlike classical approaches which always select the closest object, our method outputs a set of potential candidates if the input information is not enough discriminant. There are three main steps in our approach: objects segmentation, signature extraction and classification. Segmentation is inspired from previous works and is shortly described. Signature extraction based on global geometric and color features is detailed. Classification based on artificial neural networks is also explained and architecture of the network is justified. Finally a real experiment made with a RGB-D camera mounted on a mobile robot is presented and classification results is criticized.

International Journal of Virtual Reality, 2006

This paper presents a human-scale virtual environment (VE) with haptic feedback along with two ex... more This paper presents a human-scale virtual environment (VE) with haptic feedback along with two experiments performed in the context of product design. The user interacts with a virtual mock-up using a large-scale bimanual string-based haptic interface called SPIDAR (Space Interface Device for Artificial Reality). An original self-calibration method is proposed. A vibro-tactile glove was developed and integrated to the SPIDAR