Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a hybrid learning-control architecture that combines Dynamical Systems (DS)-based Imitation Learning (IL) with a neuroadaptive controller to enhance trajectory recovery in Unmanned Surface Vehicles (USVs) during repetitive maritime operations. The approach addresses the trade-off between global target convergence and localized trajectory fidelity, enabling USVs to dynamically align with human-like behaviors even in the presence of persistent marine disturbances. Validation through the Marine Systems Simulator (MSS) demonstrates significant improvements in trajectory tracking fidelity compared to traditional control methods, showcasing the framework's effectiveness in complex maneuvering tasks.
A novel hybrid control architecture allows USVs to maintain human-like trajectory fidelity even under challenging marine conditions, outperforming standard methods.
Repetitive maritime operations can be effectively learned using the Imitation Learning (IL) paradigm, which transfers human expertise directly to Unmanned Surface Vehicle (USV) control systems. Dynamical Systems (DS) are widely used to model non-linear human demonstrations while offering inherent stability guarantees. However, real-world execution under persistent marine perturbations reveals a critical trade-off: standard DS-based IL approaches prioritize global target convergence at the expense of localized trajectory reproduction fidelity. To address this limitation, we present a hybrid learning-control architecture that integrates a DS-based IL reference generator with a neuroadaptive controller. Our approach introduces a control action that drives the USV back to the demonstrated path following exogenous disturbances, enabling dynamic human-like reactive alignment-termed behavioral tracking. The proposed methodology is validated using the Marine Systems Simulator (MSS) toolbox. Simulation results confirm that the framework generalizes complex maneuvering tasks while substantially improving trajectory tracking fidelity under disturbances compared to alternative control strategies.