Randomized Physics-based Motion Planning for Grasping in Cluttered and Uncertain Environments

TL;DR

This paper introduces p-KPIECE, a randomized physics-based motion planner that effectively handles grasping in cluttered, uncertain environments by simulating complex interactions without explicit high-level reasoning.

Contribution

It presents a novel physics-based motion planning algorithm, p-KPIECE, that improves success rates and efficiency in cluttered, uncertain scenarios by integrating physics simulation into kinodynamic planning.

Findings

p-KPIECE outperforms ontological physics-based planners in success rate.

The approach reduces planning time significantly.

It achieves higher quality solution paths in complex scenarios.

Abstract

Planning motions to grasp an object in cluttered and uncertain environments is a challenging task, particularly when a collision-free trajectory does not exist and objects obstructing the way are required to be carefully grasped and moved out. This paper takes a different approach and proposes to address this problem by using a randomized physics-based motion planner that permits robot-object and object-object interactions. The main idea is to avoid an explicit high-level reasoning of the task by providing the motion planner with a physics engine to evaluate possible complex multi-body dynamical interactions. The approach is able to solve the problem in complex scenarios, also considering uncertainty in the objects pose and in the contact dynamics. The work enhances the state validity checker, the control sampler and the tree exploration strategy of a kinodynamic motion planner called KPIECE. The enhanced algorithm, called p-KPIECE, has been validated in simulation and with real experiments. The results have been compared with an ontological physics-based motion planner and with task and motion planning approaches, resulting in a significant improvement in terms of planning time, success rate and quality of the solution path.