Computing High-Quality Clutter Removal Solutions for Multiple Robots

TL;DR

This paper develops efficient algorithms for multi-robot clutter removal, enabling high-quality solutions in complex scenarios, validated through simulations with multiple robots, despite the problem's computational intractability.

Contribution

It introduces novel search algorithms for multi-robot clutter removal that outperform single robot approaches and demonstrates their effectiveness in realistic simulations.

Findings

Algorithms produce solutions for tens of objects efficiently.

Multi-robot solutions outperform single robot solutions.

Deciding the optimal sequence is computationally intractable.

Abstract

We investigate the task and motion planning problem of clearing clutter from a workspace with limited ingress/egress access for multiple robots. We call the problem multi-robot clutter removal (MRCR). Targeting practical applications where motion planning is non-trivial but is not a bottleneck, we focus on finding high-quality solutions for feasible MRCR instances, which depends on the ability to efficiently compute high-quality object removal sequences. Despite the challenging multi-robot setting, our proposed search algorithms based on A*, dynamic programming, and best-first heuristics all produce solutions for tens of objects that significantly outperform single robot solutions. Realistic simulations with multiple Kuka youBots further confirms the effectiveness of our algorithmic solutions. In contrast, we also show that deciding the optimal object removal sequence for MRCR is computationally intractable.