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

2025-09-08

AI Summary

Micro-autonomous surface vehicles (MicroASVs) hold significant promise for operations in confined/shallow waters and multi-vehicle coordination, yet precise and robust control remains challenging due to strong nonlinear hydrodynamics, boundary effects, and wave-induced disturbances. This paper proposes a hybrid physics-informed and data-driven framework for dynamic modeling and optimal control. Leveraging a weak-form online model learning approach, the method adaptively refines the hydrodynamic physical model of an over-actuated system in real time, enabling compensation for time-varying parameters and unmodeled disturbances. The framework tightly integrates first-principles modeling, weak-form online identification, and data-driven optimal control. In simulation, it achieves markedly improved trajectory tracking accuracy and robustness under unknown payload variations and complex environmental disturbances. The approach establishes a scalable, reliable paradigm for autonomous MicroASV operation in dynamically constrained aquatic environments.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

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

Abstract

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.

Problem

• Modeling nonlinear hydrodynamic forces in micro autonomous surface vehicles
• Achieving precise robust control under environmental disturbances waves
• Overcoming sensitivity self-motion effects confined space operations

Innovation

• Physics-driven dynamics model for over-actuated MicroASV
• Data-driven optimal control with online model learning
• Real-time model refinement for adaptive control