Joint Path and Push Planning Among Movable Obstacles

TL;DR

This paper introduces a joint path and push planning algorithm for navigating among movable obstacles, combining RRT-based heuristics and physics simulation to improve navigation success in cluttered environments.

Contribution

It presents a novel integrated planning approach that simultaneously determines the path and obstacle pushes, enhancing navigation in complex, cluttered scenarios.

Findings

Outperforms existing planners in high clutter environments (up to 49% success rate).

Uses physics simulation for effective obstacle pushing sequences.

Achieves higher success rates than straight-line push and non-push RRT planners.

Abstract

This paper explores the Navigation Among Movable Obstacles (NAMO) problem and proposes joint path and push planning: which path to take and in what direction the obstacles should be pushed at, given a start and goal position. We present a planning algorithm for selecting a path and the obstacles to be pushed, where a Rapidly-exploring Random Tree (RRT)-based heuristic is employed to calculate a minimal collision path. When it is necessary to apply a pushing force to slide an obstacle out of the way, the planners leverage means-end analysis through a dynamic physics simulation to determine the sequence of linear pushes to clear the necessary space. Simulation experiments show that our approach finds solutions in higher clutter percentages (up to 49%) compared to the straight-line push planner (37%) and RRT without pushing (18%).