Turning Disturbances into Actuation: Hierarchical Environment-Assisted MPC for USV Fault Recovery
Yang Hu, Sara Aldhaheri, Yanchao Wang, Peng Wu, Yuanchang Liu
AI summary
Problem
Traditional fault-tolerant control rejects environmental disturbances and assumes sufficient actuator redundancy, causing twin-thruster USVs to lose controllability and abort missions during severe thruster failures.
Approach
A hierarchical environment-assisted MPC framework that adaptively modulates wind and wave force utilization based on fault severity and prediction confidence, transforming natural disturbances into virtual actuators for emergency maneuvering.
Key results
- 91.25% mission success under 95% thruster degradation
- Confidence-aware adaptive policy scaling assistance with fault severity
- Reachability-based planning expanding feasible maneuvering zones
- Theoretical practical input-to-state stability bounds quantifying degradation
Why it matters
Enables autonomous marine vehicles to operate safely beyond traditional fault margins in remote waters by converting environmental forces into reliable backup control.
Abstract
Thruster failures in unmanned surface vehicles (USVs) can critically compromise mission completion, partic- ularly when severe degradation eliminates controllability in essential degrees of freedom. While traditional fault-tolerant control treats environmental disturbances as impediments to be rejected, this paper presents a novel approach: strategically exploiting wind and wave forces as virtual actuators for emergency harbor return. The proposed environment-assisted model predictive control (EAMPC) framework adaptively mod- ulates environmental force utilization factors based on fault severity and the environmental force prediction confidence, transforming natural disturbances into environmental assis- tance. The hierarchical architecture integrates state estima- tion and prediction with physics-informed learning for short- term environmental forces, and reachability-based trajectory planning that exploits environmental forces to expand feasi- ble zones. Theoretical analysis establishes practical input-to- state stability with explicit bounds quantifying degradation. Extensive validation across 320 trials demonstrates 91.25% mission success under 95% thruster degradation compared to 0% for baseline methods. This work demonstrates that strategic environmental exploitation fundamentally transforms fault recovery capabilities in marine robotics.