Concurrent Map Building and Behavior Learning for Navigation in Unknown Environments
Abstract:In this paper, we report a robust and low-cost navigation algorithm for an unknown environment based on integration of a grid-based map building algorithm with behavior learning. The study focuses on mobile robots that utilize ultrasonic sensors as their prime interface with the outside world. The proposed algorithm takes into account environmental information to augment the readings from the low angular accuracy sonar measurements for behavior learning. The environmental information is obtained by an online grid-based map learning design that is concurrently operating with the behavior learning algorithm. The proposed algorithm is implemented and tested on an in-house-built mobile robot, and its performance is verified through online navigation in an indoor environment.
Document Type: Research Article
Affiliations: 1: College of Life Sciences & Technology, HKU SPACE, Hong Kong 2: School of Engineering Science, Simon Fraser University, 250-13450, 102 Avenue, Surrey, BC V3T 0A3, Canada 3: Amonics Ltd., Unit 1803-04, Perfect Industrial Building, San Po Kong, Kowloon, Hong Kong
Publication date: July 1, 2010