Community Research and Development Information Service - CORDIS

Abstract

This paper proposes an incremental learning approach to control autonomous robots based on local networks. This approach integrates different learning techniques in a conceptually simple architecture. The robot does not learn from scratch, but uses two types of bias: built-in reflexes (domain knowledge) and advice. The robot adds a new unit to the neural network whenever it uses the reflexes or receives advice. This unit is integrated into a topology preserving map and associates a region around the current situation to either the computed reflex or the advice. The resulting reaction rule is then tuned by means of reinforcement learning and self-organizing rules. Experimental results show that the robot TESEO rapidly learns suitable behavioural strategies.

Additional information

Authors: MILLÁN J DEL R, JRC Ispra (IT)
Bibliographic Reference: Paper presented: 7th International Conference on Artificial Neural Networks, Lausanne (CH), 8-10 October 1997
Availability: Available from (1) as Paper EN 40935 ORA
Record Number: 199810199 / Last updated on: 1998-02-12
Category: PUBLICATION
Original language: en
Available languages: en