Enhancing Randomized Motion Planners: Exploring with Haptic Hints

In this paper, we investigate methods for enabling a human operator and an automatic motion planner to cooperatively solve a motion planning query. Our work is motivated by our experience that automatic motion planners sometimes fail due to the di culty of discovering `critical' con gurationsof the robot that are often naturally apparent to a human observer. Our goal is to develop techniquesby which the automatic planner can utilize easily generated user-input, and determine `natural' ways to inform the user of the progress made by the motion planner. We show that simple randomized techniques inspired by probabilisticroadmap methods are quite useful for transforming approximate, usergenerated paths into collision-freepaths, and describe an iterative transformation method which enables one to transform a solution for an easier version of the problem into a solution for the original problem. We also illustrate that simple visualizationtechniquescan provide meaningful represe...

• Type: Conference
• Year: 2000
• Where: ICRA
• Authors: O. Burçhan Bayazit, Guang Song, Nancy M. Amato
• Keywords: Automatic Motion Planners, ICRA 2000, Motion Planner, Motion Planning Query, Robotics