HBO-PID for UAV Trajectory Tracking
Published:Dec 30, 2025 14:21
•1 min read
•ArXiv
Analysis
This paper introduces a novel control algorithm, HBO-PID, for UAV trajectory tracking. The core innovation lies in integrating Heteroscedastic Bayesian Optimization (HBO) with a PID controller. This approach aims to improve accuracy and robustness by modeling input-dependent noise. The two-stage optimization strategy is also a key aspect for efficient parameter tuning. The paper's significance lies in addressing the challenges of UAV control, particularly the underactuated and nonlinear dynamics, and demonstrating superior performance compared to existing methods.
Key Takeaways
- •HBO-PID integrates Heteroscedastic Bayesian Optimization with a PID controller.
- •The method addresses challenges of UAV control, such as underactuated and nonlinear dynamics.
- •A two-stage optimization strategy is used for efficient parameter tuning.
- •Significant performance improvements are demonstrated over SOTA methods in both simulation and real-world scenarios.
Reference
“The proposed method significantly outperforms state-of-the-art (SOTA) methods. Compared to SOTA methods, it improves the position accuracy by 24.7% to 42.9%, and the angular accuracy by 40.9% to 78.4%.”