Conflict-Based Search as a Protocol: A Multi-Agent Motion Planning Protocol for Heterogeneous Agents, Solvers, and Independent Tasks

2025-09-30

AI Summary

Collision-free coordinated navigation among heterogeneous robots—differing in manufacturer, sensing modalities, and single-agent planning algorithms—remains challenging in shared dynamic environments. Method: This paper proposes a distributed coordination protocol based on Conflict-Based Search (CBS), where CBS is abstracted as a generic communication protocol. A standardized single-agent path-planning interface decouples planner implementations, enabling heterogeneous planners—including A*, RRT, and reinforcement learning agents—to coordinate without exposing internal models or sharing kinematic parameters. A central coordinator invokes the CBS framework to resolve spatiotemporal conflicts, supporting diverse underlying planners (e.g., heuristic search, sampling-based, optimization, and diffusion-based methods). Contribution/Results: Evaluated in dynamic real-world settings (e.g., smart construction sites and hospitals), the approach demonstrates strong compatibility across robot types and scalability to large teams. It significantly enhances openness and deployment flexibility of heterogeneous multi-robot systems while maintaining safety and efficiency.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Coordination and Collaboration
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Imagine the future construction site, hospital, office, or even sophisticated household with dozens of robots bought from different manufacturers. How can we enable these different systems to effectively move in a shared environment, given that each robot may have its own independent motion planning system? This work shows how we can get efficient collision-free movements between algorithmically heterogeneous agents by using Conflict-Based Search (Sharon et al. 2015) as a protocol. At its core, the CBS Protocol requires one specific single-agent motion planning API; finding a collision-free path that satisfies certain space-time constraints. Given such an API, CBS uses a central planner to find collision-free paths - independent of how the API is implemented. We show how this protocol enables multi-agent motion planning for a heterogeneous team of agents completing independent tasks with a variety of single-agent planners including: Heuristic Search (e.g., A*), Sampling Based Search (e.g., RRT), Optimization (e.g., Direct Collocation), Diffusion, and Reinforcement Learning.

Problem

• Enabling collision-free movement for heterogeneous multi-agent systems
• Integrating diverse single-agent motion planning algorithms
• Coordinating independent tasks across algorithmically different robots

Innovation

• Uses Conflict-Based Search as coordination protocol
• Requires single-agent motion planning API
• Works with heterogeneous planning algorithms