D. Fox, W. Burgard, S. Thrun, and A.B. Cremers

A Hybrid Collision AvoidanceMethod For Mobile Robots

Proc. of the IEEE International Conference on Robotics and Automation (ICRA'98)


 

Abstract

This paper proposes a hybrid approach to the problem of collision avoidance for indoor mobile robots.  The model-based dynamic window approach integrates sensor data from various sensors with information extracted from a map of the environment, to generate collision-free motion.  A novel integration ruleensures that with high likelihood, the robot avoids collisions with obstacles not detectable with its sensors, even if it is uncertain about its position.  The approach was recently implemented and tested extensively as part of an installation, in which a mobile robot gave interactive tours to visitorsofthe ``Deutsches Museum Bonn.'' Here our approach was essential for thesuccessof the entiremission, because a large number of ill-shaped obstaclesprohibitedthe use of purely sensor-based methods for collision avoidance.

Download

Full paper [.ps.gz](1048 kb, 6 pages)
Slides of the talk [.ps.gz] (1408 kb,24 pages)


Bibtex

@INPROCEEDINGS{Fox98Hyb,
  AUTHOR    = {Fox, D. and Burgard, W. and Thrun, S. andCremers, A.B.},
  TITLE     = {A Hybrid Collision Avoidance Method For Mobile Robots},
  BOOKTITLE = {Proc.~of the IEEE International Conference on Robotics \& Automation},
  YEAR      = {1998}
}