Decentralized Uncertainty-Aware Multi-Agent Collision Avoidance With Model Predictive Path Integral

2025-07-27

AI Summary

This work addresses the safety-critical collision avoidance challenge in decentralized multi-agent navigation under uncertainty, where kinematic constraints and sensor/actuation noise degrade performance. We propose a fully decentralized framework integrating Model Predictive Path Integral (MPPI) control with Probabilistic Reciprocal Optimal Collision Avoidance (PROCA). Our key innovation embeds probabilistic safety constraints directly into the MPPI sampling process and enforces local robustness and feasibility in real time via Second-Order Cone Programming (SOCP). The method operates solely on noisy local observations, requiring no global communication or centralized coordination. Extensive Gazebo simulations demonstrate significantly higher success rates than ORCA-DD and B-UAVC in high-density dynamic environments. Hardware experiments on differential-drive robots validate its practical deployability. The core contribution is a noise-aware, computationally efficient, provably safe, and fully decentralized multi-agent navigation solution.

Technology Category

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

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Decentralized multi-agent navigation under uncertainty is a complex task that arises in numerous robotic applications. It requires collision avoidance strategies that account for both kinematic constraints, sensing and action execution noise. In this paper, we propose a novel approach that integrates the Model Predictive Path Integral (MPPI) with a probabilistic adaptation of Optimal Reciprocal Collision Avoidance. Our method ensures safe and efficient multi-agent navigation by incorporating probabilistic safety constraints directly into the MPPI sampling process via a Second-Order Cone Programming formulation. This approach enables agents to operate independently using local noisy observations while maintaining safety guarantees. We validate our algorithm through extensive simulations with differential-drive robots and benchmark it against state-of-the-art methods, including ORCA-DD and B-UAVC. Results demonstrate that our approach outperforms them while achieving high success rates, even in densely populated environments. Additionally, validation in the Gazebo simulator confirms its practical applicability to robotic platforms.

Problem

• Decentralized multi-agent navigation under uncertainty
• Collision avoidance with kinematic and noise constraints
• Safe navigation using probabilistic safety constraints

Innovation

• Integrates MPPI with probabilistic ORCA adaptation
• Uses Second-Order Cone Programming for safety
• Decentralized navigation with local noisy observations