Share Email Print

Proceedings Paper

Adaptive and less-complex path-planning behavior for mobile robots
Author(s): Iraj Mantegh; Michael R. M. Jenkin; Andrew A. Goldenberg
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The objective of path planing is to find a sequence of states that a system has to visit in order to attain the goal state. Because of their real-time efficiency, potential field methods present a powerful heuristic to guide this search. However, potential field approaches can not guarantee goal attainability. They are often referred to as 'local methods' and are used in conjunction with a global path planning method to ensure completeness of the path planning algorithm. The present work introduces a novel methodology for path planing which combines the real- time efficiency of potential field methods with goal-attainability characteristics of global methods. The algorithm of this work is: 1) free from local minima, ii) capable of considering arbitrary-shaped obstacles, iii) computationally less complex than previous search methods; and iv) able to handle obstacle avoidance and goal attainability at the same time. At the first step a new probabilistic scheme, based on absorbing Markov chains, is presented for global planning inside structured environments, such as office, etc. The potential field method is then reformulated for adaptive path planning among modeled and new obstacles.

Paper Details

Date Published: 25 January 1998
PDF: 12 pages
Proc. SPIE 3210, Mobile Robots XII, (25 January 1998); doi: 10.1117/12.299557
Show Author Affiliations
Iraj Mantegh, Univ. of Toronto (Canada)
Michael R. M. Jenkin, York Univ. (Canada)
Andrew A. Goldenberg, Univ. of Toronto (Canada)

Published in SPIE Proceedings Vol. 3210:
Mobile Robots XII
Douglas W. Gage, Editor(s)

© SPIE. Terms of Use
Back to Top