CurviTrack: Curvilinear Trajectory Tracking for High-Speed Chase of a USV

2025-02-28

IEEE Robotics and Automation Letters

AI Summary

To address mission interruption caused by unmanned surface vehicle (USV) halting for charging in heterogeneous air–sea robotic coordination, this paper proposes a high-speed curvilinear trajectory tracking and precise landing method operating without inter-vehicle communication. We innovatively formulate a towed-sensing dynamic model and integrate nonlinear model predictive control (MPC) with real-time trajectory optimization to enable robust UAV tracking of highly dynamic, aggressively maneuvering USVs and autonomous landing. The approach eliminates conventional constraints on USV speed and turning rate and requires no UAV–USV communication. Experimental and simulation results demonstrate: a 40% reduction in trajectory prediction error, a threefold increase in prediction confidence, a 30% improvement in tracking accuracy, and a 40% enhancement in landing success rate during aggressive turns. System robustness is validated on two distinct physical USV platforms.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Heterogeneous robot teams used in marine environments incur time-and-energy penalties when the marine vehicle has to halt the mission to allow the autonomous aerial vehicle to land for recharging. In this paper, we present a solution for this problem using a novel drag-aware model formulation which is coupled with MPC, and therefore, enables tracking and landing during high-speed curvilinear trajectories of an USV without any communication. Compared to the state-of-the-art, our approach yields 40% decrease in prediction errors, and provides a 3-fold increase in certainty of predictions. Consequently, this leads to a 30% improvement in tracking performance and 40% higher success in landing on a moving USV even during aggressive turns that are unfeasible for conventional marine missions. We test our approach in two different real-world scenarios with marine vessels of two different sizes and further solidify our results through statistical analysis in simulation to demonstrate the robustness of our method.

Problem

• Enables high-speed curvilinear trajectory tracking for USV.
• Reduces prediction errors by 40% and increases certainty.
• Improves landing success on moving USV by 40%.

Innovation

• Drag-aware model with MPC for tracking
• No communication needed for landing
• Improved prediction and tracking performance