FG-PE: Factor-graph Approach for Multi-robot Pursuit-Evasion

2024-11-01

arXiv.org

AI Summary

For the dynamic multi-robot pursuit-evasion task involving coordinated capture of a single evader, this paper proposes a factor-graph-based joint estimation-planning-tracking framework. The method systematically introduces factor graphs into pursuit-evasion for the first time, unifying evader state estimation, cooperative path planning, and real-time trajectory tracking. It integrates nonlinear Bayesian filtering, distributed optimization, and asynchronous message passing to jointly minimize estimation uncertainty, ensure communication robustness, and maximize encirclement efficiency. Simulation and real-world experiments demonstrate a 23.6% reduction in capture time, a 19.4% decrease in average travel distance, and a 98.1% capture success rate under 30% message loss—significantly overcoming the performance degradation bottleneck of conventional methods in dynamic packet-loss scenarios.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

With the increasing use of robots in daily life, there is a growing need to provide robust collaboration protocols for robots to tackle more complicated and dynamic problems effectively. This paper presents a novel, factor graph-based approach to address the pursuit-evasion problem, enabling accurate estimation, planning, and tracking of an evader by multiple pursuers working together. It is assumed that there are multiple pursuers and only one evader in this scenario. The proposed method significantly improves the accuracy of evader estimation and tracking, allowing pursuers to capture the evader in the shortest possible time and distance compared to existing techniques. In addition to these primary objectives, the proposed approach effectively minimizes uncertainty while remaining robust, even when communication issues lead to some messages being dropped or lost. Through a series of comprehensive experiments, this paper demonstrates that the proposed algorithm consistently outperforms traditional pursuit-evasion methods across several key performance metrics, such as the time required to capture the evader and the average distance traveled by the pursuers. Additionally, the proposed method is tested in real-world hardware experiments, further validating its effectiveness and applicability.

Problem

• Develops factor-graph method for multi-robot pursuit-evasion coordination
• Enables accurate estimation and tracking of evader by pursuers
• Minimizes uncertainty and remains robust under communication failures

Innovation

• Factor graph-based approach for multi-robot pursuit-evasion
• Enables accurate estimation, planning, and tracking of evader
• Minimizes uncertainty and remains robust despite communication issues