Sub-1.5 Time-Optimal Multi-Robot Path Planning on Grids in Polynomial Time

TL;DR

This paper introduces a polynomial-time algorithm for multi-robot path planning on grids that guarantees near-optimal makespan solutions with high probability, enabling scalable logistics applications in large robotic warehouses.

Contribution

The authors propose the RTH algorithm, the first low polynomial-time method achieving 1--1.5 asymptotic optimality guarantees for high-density multi-robot routing on grids.

Findings

RTH computes solutions with makespan close to optimal for large grids.

The algorithm scales to over 45,000 robots on 450x300 grids.

RTH outperforms existing methods like ECBS and DDM in scalability and solution quality.

Abstract

Graph-based multi-robot path planning (MRPP) is NP-hard to optimally solve. In this work, we propose the first low polynomial-time algorithm for MRPP achieving 1--1.5 asymptotic optimality guarantees on makespan for random instances under very high robot density, with high probability. The dual guarantee on computational efficiency and solution optimality suggests our proposed general method is promising in significantly scaling up multi-robot applications for logistics, e.g., at large robotic warehouses. Specifically, on an $m_1\times m_2$ gird, $m_1 \ge m_2$, our RTH (Rubik Table with Highways) algorithm computes solutions for routing up to $\frac{m_1m_2}{3}$ robots with uniformly randomly distributed start and goal configurations with a makespan of $m_1 + 2m_2 + o(m_1)$, with high probability. Because the minimum makespan for such instances is $m_1 + m_2 - o(m_1)$, also with high probability, RTH guarantees $\frac{m_1+2m_2}{m_1+m_2}$ optimality as $m_1 \to \infty$ for random instances with up to $\frac{1}{3}$ robot density, with high probability. $\frac{m_1+2m_2}{m_1+m_2} \in (1, 1.5]$. Alongside this key result, we also establish a series of related results supporting even higher robot densities and environments with regularly distributed obstacles, which directly map to real-world parcel sorting scenarios. Building on the baseline methods with provable guarantees, we have developed effective, principled heuristics that further improve the computed optimality of the RTH algorithms. In extensive numerical evaluations, RTH and its variants demonstrate exceptional scalability as compared with methods including ECBS and DDM, scaling to over $450 \times 300$ grids with $45,000$ robots, and consistently achieves makespan around $1.5$ optimal or better, as predicted by our theoretical analysis.