Collision Prediction Among Rigid and Articulated Obstacles with Unknown Motion

Abstract

Collision prediction is a fundamental operation for planning motion in dynamic environment. Existing methods usually exploit complex behavior models or use dynamic constraints in collision prediction. However, these methods all assume simple geometry, such as disc, which significantly limit their applicability. This paper proposes a new approach that advances collision prediction beyond disc robots and handles arbitrary polygons and articulated objects. Our new tool predicts collision by assuming that obstacles are adversarial. Comparing to an online motion planner that replans periodically at fixed time interval and planner that approximates obstacle with discs, our experimental results provide strong evidences that the new method significantly reduces the number of replans while maintaining higher success rate of finding a valid path. Our geometric-based collision prediction method provides a tool to handle highly complex shapes and provides a complimentary approach to those methods that consider behavior and dynamic constraints of objects with simple shapes.

This work is supported in part by NSF IIS-096053, CNS-1205260, EFRI-1240459, AFOSR FA9550-12-1-0238.