Tanja Hebecker, Frank Ortmeier: Safe Prediction-Based Local Path Planning using Obstacle Probability Sections. In: Laugier, Christian; Martinet, Philippe; Nunes, Urbano; stiller, Christoph (Hrsg.): Proceedings of the 7th IROS Workshop on Planning, Perception and Navigation for Intelligent Vehicles, S. 183 - 188, 2015.

Abstract

Autonomous mobile robots gain more and more importance. In the nearest future they will be a part of everyday life. Therefore, it is critical to make them as reliable and safe as possible. We present a local path planner that shall ensure safety in an environment cluttered with unexpectedly moving obstacles. In this paper, the motion of obstacles is predicted by generating probability sections, and collision risks of path configurations are checked by determining whether these configurations lead inevitably to a collision or not. The presented approach worked efficiently in scenarios with static and dynamic obstacles.

BibTeX (Download)

@inproceedings{Hebecker2015,
title = {Safe Prediction-Based Local Path Planning using Obstacle Probability Sections},
author = {Tanja Hebecker and Frank Ortmeier},
editor = {Christian Laugier and Philippe Martinet and Urbano Nunes and Christoph stiller },
url = {https://cse.cs.ovgu.de/cse-wordpress/wp-content/uploads/2016/02/hebecker2015_SafePrediction-basedLocalPathPlanningUsingObstacleProbability.pdf},
year  = {2015},
date = {2015-09-28},
booktitle = {Proceedings of the 7th IROS Workshop on Planning, Perception and Navigation for Intelligent Vehicles},
pages = {183 - 188},
abstract = {Autonomous mobile robots gain more and more importance. In the nearest future they will be a part of everyday life. Therefore, it is critical to make them as reliable and safe as possible. We present a local path planner that shall ensure safety in an environment cluttered with unexpectedly moving obstacles. In this paper, the motion of obstacles is predicted by generating probability sections, and collision risks of path configurations are checked by determining whether these configurations lead inevitably to a collision or not. The presented approach worked efficiently in scenarios with static and dynamic obstacles.},
keywords = {local path planning, Obstacle probability sections},
pubstate = {published},
tppubtype = {inproceedings}
}