PECMAN: Perception-enabled Collaborative Multi-Agent Navigation in Unknown Environments

2026-05-10

AI Summary

This work addresses the inefficiency in multi-agent path planning caused by limited perception and insufficient coordination in dynamic, unknown environments. To overcome these challenges, the authors propose a perception-driven cooperative navigation framework based on distributed RRT* trees with local dynamic reconstruction and shared perception. When an agent detects new obstacles or environmental changes, it locally prunes and repairs its search tree while broadcasting critical updates to synchronize team-wide situational awareness, thereby avoiding redundant exploration and replanning. Integrated with an extended SMART-3D algorithm and an efficient communication protocol, the approach reduces collective task completion time by up to 52% across 28,000 simulations while achieving near-perfect success rates, and demonstrates robust performance in real-world experiments with a dual-robot system navigating a building environment.

Abstract

Most path planners assume fully known, static environments, assumptions that fail when robots navigate in dynamic and partially observable environments. SMART-3D addresses these issues by real-time replanning, where it morphs the underlying RRT* tree whenever new obstacles or structures are discovered in the environment. Instead of rebuilding the tree entirely from scratch, SMART-3D prunes invalid nodes and edges and subsequently repairs the disjoint subtrees at hot-nodes to find a new path, thus providing high computational efficiency for real-time adaptability. We extend SMART-3D to perception-enabled collaborative multi-agent navigation (PECMAN) in unknown environments. PECMAN is built upon distributed tree morphing and shared perception strategies, where each agent reacts to environmental changes and morphs its respective tree to replan its path, while simultaneously broadcasting newly discovered structures to other agents, thus enabling them to proactively replan even in areas that have not yet been explored by them. This approach reduces redundant reactions and unnecessary replannings of the agents due to improved situational awareness. The performance of PECMAN was evaluated by 28,000 multi-agent simulations on seven 2D scenarios with different case studies. The results show that PECMAN achieves up to 52% reduction in the team-completion time, while maintaining near 100% success rates. Finally, PECMAN was tested by real experiments on two autonomous robots in a building environment.

Problem

• multi-agent navigation
• unknown environments
• dynamic obstacles
• collaborative planning
• partial observability

Innovation

• distributed tree morphing
• shared perception
• multi-agent navigation
• real-time replanning
• unknown environments