MC-Swarm: Minimal-Communication Multi-Agent Trajectory Planning and Deadlock Resolution for Quadrotor Swarm

2025-05-13

AI Summary

This paper addresses trajectory planning and deadlock avoidance for quadrotor swarms operating under fully asynchronous execution and zero runtime communication after initial coordination. Method: We propose a distributed asynchronous planning framework comprising two core modules: a coordination state updater and a trajectory optimizer. The framework integrates distributed optimization, safety-constrained modeling, sampling-based trajectory generation and verification, and a lightweight coordination protocol enabling dynamic re-optimization of sub-goals. Contribution/Results: To the best of our knowledge, this is the first approach to provide theoretical guarantees of deadlock immunity and collision avoidance under zero-runtime-communication assumptions. Extensive evaluations—including random forest and narrow-passage maze simulations, as well as real-world experiments—demonstrate significant reduction in mission completion time, with zero observed deadlocks or collisions. The framework ensures safety, real-time performance, and scalability.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Agentic search

Abstract

For effective multi-agent trajectory planning, it is important to consider lightweight communication and its potential asynchrony. This paper presents a distributed trajectory planning algorithm for a quadrotor swarm that operates asynchronously and requires no communication except during the initial planning phase. Moreover, our algorithm guarantees no deadlock under asynchronous updates and absence of communication during flight. To effectively ensure these points, we build two main modules: coordination state updater and trajectory optimizer. The coordination state updater computes waypoints for each agent toward its goal and performs subgoal optimization while considering deadlocks, as well as safety constraints with respect to neighbor agents and obstacles. Then, the trajectory optimizer generates a trajectory that ensures collision avoidance even with the asynchronous planning updates of neighboring agents. We provide a theoretical guarantee of collision avoidance with deadlock resolution and evaluate the effectiveness of our method in complex simulation environments, including random forests and narrow-gap mazes. Additionally, to reduce the total mission time, we design a faster coordination state update using lightweight communication. Lastly, our approach is validated through extensive simulations and real-world experiments with cluttered environment scenarios.

Problem

• Minimal-communication trajectory planning for quadrotor swarms
• Deadlock resolution under asynchronous agent updates
• Collision avoidance in dynamic and cluttered environments

Innovation

• Distributed trajectory planning with minimal communication
• Deadlock-free asynchronous updates for quadrotor swarms
• Collision avoidance via coordination and trajectory optimization