Skip to Main content Skip to Navigation
Conference papers

Learning Reactive Neurocontrollers Using Simulated Annealing for Mobile Robots

Résumé : 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 a 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download
Contributor : Christine Carvalho de Matos <>
Submitted on : Thursday, April 3, 2008 - 8:12:19 AM
Last modification on : Wednesday, October 23, 2019 - 3:31:10 PM
Long-term archiving on: : Friday, May 21, 2010 - 1:15:37 AM


Files produced by the author(s)




Philippe Lucidarme, Alain Liégeois. Learning Reactive Neurocontrollers Using Simulated Annealing for Mobile Robots. IROS: Intelligent Robots and Systems, Oct 2003, Las Vegas, NV, United States. pp.674-679, ⟨10.1109/IROS.2003.1250707⟩. ⟨lirmm-00269482⟩



Record views


Files downloads