A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments

Authors:
José Del R. Millán;Carme Torras
Affiliations:
Institute for System Engineering and Informatics, Commission of the European Communities, Joint Research Centre, TP 361, 21020 ISPRA (VA), Italy. j_millan@jrc.it;Institut de Cibernètica (CSIC-UPC), Diagonal, 647, 08028 Barcelona, Spain. torras@ic.upc.es
Venue:
Machine Learning
Year:
1992

Citing 0
Cited 7

A Teaching Strategy for Memory-Based Control

Artificial Intelligence Review - Special issue on lazy learning
Continuous-Action Q-Learning

Machine Learning
Neural computing increases robot adaptivity

Natural Computing: an international journal
A Planning Map for Mobile Robots: Speed Control and Paths Finding in a Changing Environment

EWLR-8 Proceedings of the 8th European Workshop on Learning Robots: Advances in Robot Learning
Improving Recurrent CSVM Performance for Robot Navigation on Discrete Labyrinths

CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
A cognitive model of spatial path-planning

Computational & Mathematical Organization Theory
Natural inspiration for artificial adaptivity: some neurocomputing experiences in robotics

UC'05 Proceedings of the 4th international conference on Unconventional Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a reinforcement connectionist system which finds and learns the suitable situation-action rules so as to generate feasible paths for a point robot in a 2D environment with circular obstacles. The basic reinforcement algorithm is extended with a strategy for discovering stable solution paths. Equipped with this strategy and a powerful codification scheme, the path-finder (i) learns quickly, (ii) deals with continuous-valued inputs and outputs, (iii) exhibits good noise-tolerance and generalization capabilities, (iv) copes with dynamic environments, and (v) solves an instance of the path finding problem with strong performance demands.