Dynamic Modeling and Efficient Data-Driven Optimal Control for Micro Autonomous Surface Vehicles

Micro Autonomous Surface Vehicles (MicroASVs) offer significant potential for operations in confined or shallow waters and swarm robotics applications. However, achieving precise and robust control at such small scales remains highly challenging, mainly due to the complexity of modeling nonlinear hydrodynamic forces and the increased sensitivity to self-motion effects and environmental disturbances, including waves and boundary effects in confined spaces. This paper presents a physics-driven dynamics model for an over-actuated MicroASV and introduces a data-driven optimal control framework that leverages a weak formulation-based online model learning method. Our approach continuously refines the physics-driven model in real time, enabling adaptive control that adjusts to changing system parameters. Simulation results demonstrate that the proposed method substantially enhances trajectory tracking accuracy and robustness, even under unknown payloads and external disturbances. These findings highlight the potential of data-driven online learning-based optimal control to improve MicroASV performance, paving the way for more reliable and precise autonomous surface vehicle operations.

Authors

• Zhiheng Chen
• Wei Wang

Keywords

• Robust control
• Adaptation models
• Sensitivity
• Trajectory tracking
• Simulation
• Optimal control
• Swarm robotics
• Robustness
• Real-time systems
• Vehicle dynamics
• Dynamic Model
• Efficient Control
• Autonomous Surface Vehicles
• Data-driven Optimal Control
• Shallow Water
• Adaptive Control
• External Disturbances
• Optimization Framework
• Boundary Effects
• Environmental Disturbances
• Unknown Disturbances
• Real-time Model
• Unknown External Disturbances
• Equations Of Motion
• Control Input
• Force Generation
• Tracking Error
• Nominal Model
• Two-point Boundary Value Problem
• Linear Quadratic Regulator
• Center-of-mass Frame
• Integration By Parts
• Optimal Control Strategy
• Mass Matrix
• Inertial Frame
• Real-time Dynamics
• Model Predictive Control