Obstacle Avoidance by Means of an Operant Conditioning Model
Date
1995-02
DOI
Authors
Zalama, Eduardo
Gaudino, Paolo
Coronado, Juan López
Version
OA Version
Citation
Abstract
This paper describes the application of a model of operant conditioning to the problem of obstacle avoidance with a wheeled mobile robot. The main characteristic of the applied model is that the robot learns to avoid obstacles through a learning-by-doing cycle without external supervision. A series of ultrasonic sensors act as Conditioned Stimuli (CS), while collisions act as an Unconditioned Stimulus (UCS). By experiencing a series of movements in a cluttered environment, the robot learns to avoid sensor activation patterns that predict collisions, thereby learning to avoid obstacles. Learning generalizes to arbitrary cluttered environments. In this work we describe our initial implementation using a computer simulation.
Description
License
Copyright 1995 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.