DMVC-Tracker: Distributed Multi-Agent Trajectory Planning for Target Tracking Using Dynamic Buffered Voronoi and Inter-Visibility Cells

2024-11-27

arXiv.org

AI Summary

This paper addresses the distributed trajectory planning problem for multi-UAV cooperative tracking of dynamic targets. We propose a real-time, safety-aware planning method that jointly ensures collision avoidance, occlusion prevention, and optimal observation distance. Our key contributions are: (1) the first integration of Dynamic Buffered Voronoi Cells (DBVC) and Dynamic Inter-Visibility Cells (DIVC) to construct a time-varying safety-perception space; (2) the design of lightweight, non-conservative Bernstein polynomial-based motion primitives, enhancing trajectory flexibility while improving computational efficiency; and (3) a hybrid framework combining distributed optimization with real-time reactive avoidance, enabling sub-5-ms per-UAV trajectory generation on an Intel i7 platform. Extensive evaluations in cluttered environments with dozens of obstacles demonstrate long-term stable target tracking, strong robustness against dynamic disturbances, and high engineering applicability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

This letter presents a distributed trajectory planning method for multi-agent aerial tracking. The proposed method uses a Dynamic Buffered Voronoi Cell (DBVC) and a Dynamic Inter-Visibility Cell (DIVC) to formulate the distributed trajectory generation. Specifically, the DBVC and the DIVC are time-variant spaces that prevent mutual collisions and occlusions among agents, while enabling them to maintain suitable distances from the moving target. We combine the DBVC and the DIVC with an efficient Bernstein polynomial motion primitive-based tracking generation method, which has been refined into a less conservative approach than in our previous work. The proposed algorithm can compute each agent's trajectory within several milliseconds on an Intel i7 desktop. We validate the tracking performance in challenging scenarios, including environments with dozens of obstacles.

Problem

• Distributed trajectory planning for multi-agent aerial tracking.
• Prevent collisions and occlusions using dynamic Voronoi cells.
• Efficient trajectory computation in obstacle-rich environments.

Innovation

• Dynamic Buffered Voronoi Cell for collision avoidance
• Dynamic Inter-Visibility Cell to prevent occlusions
• Bernstein polynomial motion for efficient trajectory generation