Large language models coordinate multi-robot navigation with conflict detection
Verifier-Mediated Multi-LLM Coordination for Multi-Robot Path Planning
Robotics
Summary
Planning paths for multiple robots is tricky because their movements can interfere with each other. The authors studied how using several large language models (LLMs) to plan robot paths can be coordinated. Instead of one model doing all the planning, each robot suggests a plan independently, then a separate checker verifies if these plans cause collisions. If conflicts appear, the system tells the models to adjust their plans until they fit together safely. This method was tested both in computer simulations and on flying drones.
What this means in practice
- •For robotics engineers: Coordinate multiple robots’ navigation plans using independent planners verified for collisions to improve safety and effectiveness.
- •For drone operation teams: Plan and verify aerial drone flight paths with conflict detection to enable safer multi-drone missions.
Authors
Vivek Khatana, Zijian Song, Naira Hovakimyan, Petros Voulgaris
Abstract
Foundation models are increasingly used for high-level multi-robot task planning, yet independently generated symbolic plans can become jointly infeasible after geometric grounding because of shared spatial and temporal constraints. We study execution-aware coordination of large-language-model (LLM) planners for multi-robot navigation. We compare a centralized architecture, in which one LLM jointly reasons over the robot team, with a decentralized multi-LLM architecture in which each robot independently proposes a task plan. A geometric verifier grounds the candidate plans into robot trajectories, detects predicted inter-robot conflicts, and converts conflict information into structured feedback for targeted replanning. This verifier-mediated architecture separates semantic task reasoning from execution-level feasibility while enabling iterative coordination among LLM planners. Experiments in CARLA and on Crazyflie aerial robots evaluate coordination performance as task complexity increases and characterize the trade-offs between centralized reasoning, decentralized verifier-mediated coordination, and physical executability.