PEEL: Parallel Extraction for Long-Horizon Disassembly Planning via Scale-Invariant Sampling

2026-08-09

AI Summary

This work addresses the challenge of collision-free disassembly sequence planning for long-horizon, multi-component objects navigating through narrow passages. To tackle this problem, the authors propose a parallel motion planning framework that integrates scale-invariant sampling with a multi-armed bandit–enhanced RRT (MAB-RRT). The approach leverages scale estimation for warm-start initialization, directional sampling to guide exploration, and batched parallel planning to adaptively and efficiently solve complex disassembly tasks. Experimental results demonstrate that the system achieves a 100% planning success rate across 76 single-component scenarios and successfully executes four long-horizon disassembly tasks involving 10 to 17 components on a Fetch robot, thereby validating the robustness and practical applicability of the proposed method.

Abstract

Long-horizon multi-part object disassembly requires robots to compute feasible sequences of collision-free removal motions, even in the presence of tight, narrow escape corridors. To efficiently solve such disassembly problems, we propose Parallel Extraction for Long-Horizon Disassembly (PEEL), an algorithm which efficiently computes disassembly motions for object assemblies and feeds them to a robot manipulator for execution. PEEL uses sampling-based motion planning to compute single-object motions through the use of a scale-invariant sampling scheme, where the object scale is estimated in a burn-in phase and a subsequent directional sampler exploits the scale. This sampling scheme is integrated into a multi-arm bandit rapidly-exploring random tree (MAB-RRT) planner, which switches between different samplers depending on the reward signal received. Using MAB-RRT, the PEEL algorithm runs a batch of planners in parallel to obtain an ordered graph specifying the sequence in which object parts have to be removed. We show that MAB-RRT can efficiently solve single-part disassemblies with 100 percent success rate on 76 assemblies, and that it is robust to its parameters. By integrating MAB-RRT into PEEL, we solve four long-horizon disassembly problems using the Fetch manipulator robot involving 10 to 17 individual object parts.

Problem

• long-horizon disassembly
• collision-free motion planning
• multi-part object disassembly
• narrow escape corridors
• robotic manipulation

Innovation

• scale-invariant sampling
• MAB-RRT
• parallel extraction
• long-horizon disassembly
• multi-arm bandit planning