Homotopy-aware Multi-agent Navigation via Distributed Model Predictive Control

2025-07-26

AI Summary

Multi-agent systems frequently encounter deadlock in densely cluttered environments due to path conflicts, especially in narrow passages. To address this, we propose a real-time trajectory planning framework integrating global homotopy-class-aware path planning with distributed model predictive control (MPC). Our key innovation lies in incorporating time-aware homotopy class features into global path selection—explicitly distinguishing topologically equivalent yet temporally conflicting paths—to proactively prevent deadlocks at the planning stage. This is synergistically combined with online-replanning-enabled local MPC for safety and real-time responsiveness under dynamic conditions. Evaluated in randomized dense simulation and physical experiments, our method increases task success rate from 4%–13% to over 90%. Results demonstrate substantial improvements in deadlock mitigation, passage efficiency, and overall system robustness.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Multi-agent trajectory planning requires ensuring both safety and efficiency, yet deadlocks remain a significant challenge, especially in obstacle-dense environments. Such deadlocks frequently occur when multiple agents attempt to traverse the same long and narrow corridor simultaneously. To address this, we propose a novel distributed trajectory planning framework that bridges the gap between global path and local trajectory cooperation. At the global level, a homotopy-aware optimal path planning algorithm is proposed, which fully leverages the topological structure of the environment. A reference path is chosen from distinct homotopy classes by considering both its spatial and temporal properties, leading to improved coordination among agents globally. At the local level, a model predictive control-based trajectory optimization method is used to generate dynamically feasible and collision-free trajectories. Additionally, an online replanning strategy ensures its adaptability to dynamic environments. Simulations and experiments validate the effectiveness of our approach in mitigating deadlocks. Ablation studies demonstrate that by incorporating time-aware homotopic properties into the underlying global paths, our method can significantly reduce deadlocks and improve the average success rate from 4%-13% to over 90% in randomly generated dense scenarios.

Problem

• Address deadlocks in multi-agent navigation in dense environments
• Bridge global path and local trajectory cooperation gaps
• Improve coordination via homotopy-aware and time-aware path planning

Innovation

• Homotopy-aware global path planning
• Distributed Model Predictive Control
• Online replanning for dynamic adaptability