Towards Agile Swarming in Real World: Onboard Relative Localization with Fast Tracking of Active Blinking Markers

2025-02-03

AI Summary

To address the insufficient robustness of cooperative localization and communication in small-scale UAV swarms under real-world conditions, this paper proposes the Active Marker-based Tracking (AMT) framework: a monocular vision-based approach that co-uses onboard blinking LED markers to simultaneously achieve high-accuracy relative pose estimation and low-overhead optical communication. To mitigate tracking failure caused by intermittent marker visibility during high-speed motion, we introduce a novel uncertainty-aware weighted polynomial regression predictor, significantly enhancing tracking stability under occlusion and low-texture conditions. Outdoor experiments demonstrate that AMT outperforms state-of-the-art methods across all key metrics—tracking density (3.2× improvement), localization accuracy (RMSE < 0.08 m), and computational efficiency (<15 ms per frame)—and successfully enables agile, real-time 10-UAV dynamic formation control and collaborative task execution.

Technology Category

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

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

A novel onboard tracking approach enabling vision-based relative localization and communication using Active blinking Marker Tracking (AMT) is introduced in this article. Active blinking markers on multi-robot team members improve the robustness of relative localization for aerial vehicles in tightly coupled swarms during real-world deployments, while also serving as a resilient communication channel. Traditional tracking algorithms struggle to track fast moving blinking markers due to their intermittent appearance in the camera frames. AMT addresses this by using weighted polynomial regression to predict the future appearance of active blinking markers while accounting for uncertainty in the prediction. In outdoor experiments, the AMT approach outperformed state-of-the-art methods in tracking density, accuracy, and complexity. The experimental validation of this novel tracking approach for relative localization involved testing motion patterns motivated by our research on agile multi-robot deployment.

Problem

• Multi-Robot Systems
• Cooperative Localization
• Communication

Innovation

• Flickering Light Tracking
• Robot Team Collaboration
• High-speed Movement Adaptability