Eva-Tracker: ESDF-Update-Free, Visibility-Aware Planning with Target Reacquisition for Robust Aerial Tracking
Yue Lin, Yang Liu, Dong Wang, Huchuan Lu
AI summary
Problem
Existing ESDF-based tracking methods incur high computational overhead from frequent field updates, struggle to maintain continuous visibility in cluttered 3D spaces, and lack reliable mechanisms to recover when targets are lost.
Approach
The framework replaces real-time ESDF updates with a precomputed Field of View ESDF tailored to the camera's viewing cone, paired with a predictive path generator that maintains optimal observation distance and automatically recovers lost targets.
Key results
- Precomputed FoV-ESDF eliminates real-time update overhead
- Visibility-aware path generation with automatic target reacquisition
- Unified differentiable cost functions for occlusion avoidance and pose regulation
- Demonstrated superior robustness and lower computation time in simulations and real-world drone flights
Why it matters
Provides a computationally efficient, deployment-ready solution for autonomous drones to maintain continuous target visibility in complex, dynamic environments.
Abstract
The Euclidean Signed Distance Field (ESDF) is widely used in visibility evaluation to prevent occlusions and collisions during tracking. However, frequent ESDF updates introduce considerable computational overhead. To address this issue, we propose Eva-Tracker, a visibility-aware trajectory planning framework for aerial tracking that eliminates ESDF updates and incorporates a recovery-capable path generation method for target reacquisition. First, we design a target trajectory prediction method and a visibility-aware initial path generation algorithm that maintain an appropriate observation distance, avoid occlusions, and enable rapid replanning to reacquire the target when it is lost. Then, we propose the Field of View ESDF (FoV-ESDF), a precomputed ESDF tailored to the tracker’s field of view, enabling rapid visibility evaluation without requiring updates. Finally, we optimize the trajectory using differentiable FoV-ESDF-based objectives to ensure con- tinuous visibility throughout the tracking process. Extensive simulations and real-world experiments demonstrate that our approach delivers more robust tracking results with lower computational effort than existing state-of-the-art methods.