Safe Interval RRT* for Scalable Multi-Robot Path Planning in Continuous Space

2024-04-02

arXiv.org

AI Summary

Addressing the dual challenges of combinatorial explosion and collision avoidance in continuous-space multi-robot path planning (MRPP), this paper introduces the first modular two-layer framework. At the lower layer, we propose Safety-Interval RRT* (SI-RRT*), the first RRT*-based planner to explicitly embed safety-interval constraints—enabling rigorous modeling of continuous-time collision avoidance and highly efficient sampling that yields high-quality, collision-free trajectories with minimal samples. At the upper layer, the framework integrates either Safety-Interval Conflict-Based Prioritization (SI-CPP) for scalability or Safety-Interval Conflict-Based Search (SI-CCBS) for solution optimality—adapting to large-scale or high-quality requirements, respectively. Experiments demonstrate that SI-CPP achieves significant speedups on thousand-robot instances, while SI-CCBS surpasses all state-of-the-art continuous-space planners in solution quality on standard benchmarks. The framework ensures scalability, solution quality, and theoretical soundness.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In this paper, we consider the problem of Multi-Robot Path Planning (MRPP) in continuous space. The difficulty of the problem arises from the extremely large search space caused by the combinatorial nature of the problem and the continuous state space. We propose a two-level approach where the low level is a sampling-based planner Safe Interval RRT* (SI-RRT*) that finds a collision-free trajectory for individual robots. The high level can use any method that can resolve inter-robot conflicts where we employ two representative methods that are Prioritized Planning (SI-CPP) and Conflict Based Search (SI-CCBS). Experimental results show that SI-RRT* can quickly find a high-quality solution with a few samples. SI-CPP exhibits improved scalability while SI-CCBS produces higher-quality solutions compared to the state-of-the-art planners for continuous space.

Problem

• Multi-Robot Path Planning in continuous space
• Large search space due to combinatorial nature
• Collision-free trajectory for individual robots

Innovation

• Safe Interval RRT* planner
• Prioritized Planning method
• Conflict Based Search technique