Community Research and Development Information Service - CORDIS


This paper describes a reinforcement connectionist learning mechanism that allows a goal-directed autonomous mobile robot to adapt to an unknown indoor environment in a few trials. As a result, the robot learns efficient reactive behavioural sequences. The learning mechanism is based on three main ideas. The first idea applies when the neural network does not react properly to the current situation: a fixed set of basic reflexes suggests where to search for a suitable action. The second is to use a resource-allocating procedure to build automatically a modular network with a suitable structure and size. Each module codifies a similar set of reaction rules. The third idea concentrates on the exploration of the action space around the best actions currently known. The paper also reports experimental results obtained with a real mobile robot that demonstrate the feasibility of the approach.

Additional information

Authors: MILLAN J DEL R, JRC Ispra (IT)
Bibliographic Reference: Paper presented: 3rd International Conference on Simulation of Adaptive Behavior, Brighton (GB), August 8-12, 1994
Availability: Available from (1) as Paper EN 38490 ORA
Record Number: 199411081 / Last updated on: 1994-11-28
Original language: en
Available languages: en