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 synaptic weights. We'll first present the results obtained with a classical simulated annealing procedure, and secondly an improved version that is able to adapt the controller to failures or changes in the environment. All the results have been experimented under simulation and with a real robot.

We have developed an agent's architecture towards the goal of building efficient, robust and safe multi-robot systems considered as cooperating distributed reactive agents. This architecture is based on satisfaction and altruism allowing the agents to amend their low-level behavior like goal seeking and collision avoidance in order to solve more complex problems. We demonstrate in particular that local conflicting and locking situations are automatically avoided or made repulsive. Computer simulations of tasks in complex environments confirm it. The designed mini-robots, the implementation of their architecture, and the communication protocol are described. The same hardware is shared between communication, collision avoidance, and task achievement. Experiments using two mobile robots and a test bed confirm the theoretical and simulation results.

This paper shows how a probabilistic model is able to predict the evolution of most multi-robot systems and thus to save a lot of simulation time. To demonstrate the performance of this approach, a complex heterogeneous system is considered. It is composed of two populations of robots, having different but complementary abilities. They must survive by finding supply centers in the environment. It is shown how to model the process by a stochastic Petri net and its associated Markov chain. The latter allows one to compute the time evolution of the system. The process includes several sink states, which correspond to a singular problem. However, comparisons of simulation and theoretical results show very close values of the state probabilities when the agents are initially located at random positions. The number of agents is varied in order to obtain the most favorable terminal state: the Markovian analysis is shown to help one to determine the best parameters. Finally, the hardware used in experiments is described.

The paths generated by a high-level planner consist of sequences of positions and headings, i.e. configurations, that need a proper interpolation procedure for providing continuous controls of the vehicles. In the case of motions at constant speed, Nelson (1989) has proposed continuous-curvature paths using polar polynomials for describing the turns between two straight line segments. The corresponding curves have closed-form equations and are easy to compute. In this paper, we address the general case of interpolation between two consecutive segments travelled at different speeds, while taking into account the kinematic and dynamic limitations on the break angle, speed and acceleration. The generalized polar polynomials are thus obtained, which allow the planning of fast motions. Important properties of the polynomials are demonstrated and their use provides a method for computing the best motion consistent with the constraints. Examples are presented to illustrate the theoretical results.

This paper concerns the performance comparison of different control structures based on various sensors for an agricultural mobile manipulator. The robot's mobile platform is continuously advancing, pulled by a tractor while the manipulator executes local tasks. Therefore, an existing prototype has been entirely modelled which allowed us to test each control structure using a dynamic simulator. The simulation results permit to identify the best control structure for the given constraints.

The paper deals with the problem of the multiple solutions of the coordinate transformations for an n-link robot manipulator. Aspect decomposition of the admissible domain of the joint space is introduced and an algorithm for automatic computation of Aspect decomposition is presented. This decomposition takes into account the morphology of the robot arm and the kinematic task definition as well. Two fields of applications are then investigated : - automatic generation of the end effector workspace, - predetermination of trajectories which avoid mechanical limits of the manipulator actuators. Finally an implementation of these methods and algorithms in the CATIA CAD system is given.