Haptic-aided robot path planning based on virtual tele-operation

Abstract

The motivation of this work arises from the fact that it is very difficult for an automatic path planning method, e.g. probabilistic roadmap (PRM) to generate an optimized path, and sometimes it even fails for an automatic method to find a collision-free path, due to failure of discovering critical robot configurations. However, these critical configurations might be plain to an operator. Therefore, the advantages of human's intuition are exploited to facilitate the robot path planning process in this research. The objective of this paper is to combine the advantages of human's intuition or experiences and the huge computational power of computers to develop a semi-automatic robot path planner that can generate an user-preferred collision-free robot path. In the path planning process, the user interaction is made easy by the development of a haptically controlled virtual robot. By virtual tele-robot manipulation, a user can define or modify critical robot configurations based on which collision-free robot path can be automatically generated. © 2008 Elsevier Ltd. All rights reserved.