This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion...This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion equations and hydrodynamic coefficients to create a realistic simulation.Although conventional model-based and visual servoing approaches often struggle in dynamic underwater environments due to limited adaptability and extensive parameter tuning requirements,deep reinforcement learning(DRL)offers a promising alternative.In the positioning stage,the Twin Delayed Deep Deterministic Policy Gradient(TD3)algorithm is employed for synchronized depth and heading control,which offers stable training,reduced overestimation bias,and superior handling of continuous control compared to other DRL methods.During the searching stage,zig-zag heading motion combined with a state-of-the-art object detection algorithm facilitates docking station localization.For the docking stage,this study proposes an innovative Image-based DDPG(I-DDPG),enhanced and trained in a Unity-MATLAB simulation environment,to achieve visual target tracking.Furthermore,integrating a DT environment enables efficient and safe policy training,reduces dependence on costly real-world tests,and improves sim-to-real transfer performance.Both simulation and real-world experiments were conducted,demonstrating the effectiveness of the system in improving AUV control strategies and supporting the transition from simulation to real-world operations in underwater environments.The results highlight the scalability and robustness of the proposed system,as evidenced by the TD3 controller achieving 25%less oscillation than the adaptive fuzzy controller when reaching the target depth,thereby demonstrating superior stability,accuracy,and potential for broader and more complex autonomous underwater tasks.展开更多
Ships experience rolling motion under the action of sea waves and may even face the risk of capsizing.Anti-rolling devices are designed to reduce this motion and enhance vessel safety.This is especially critical for e...Ships experience rolling motion under the action of sea waves and may even face the risk of capsizing.Anti-rolling devices are designed to reduce this motion and enhance vessel safety.This is especially critical for engineering ships operating at sea under zero-speed conditions,where a stable posture is essential for efficient performance.Gyro stabilizers can suppress roll motion at zero speed;however,their high cost typically makes them unsuitable for large civilian vessels.Additionally,most existing anti-rolling devices rely on a certain water speed to function,which results in increased drag.In this study,an anti-rolling system incorporating swing control is proposed.Inspired by the human body's ability to maintain balance by swinging arms during walking or running,the system generates an antirolling moment by oscillating a water tank.This approach operates independently of water speed and does not generate additional drag.The mechanical design of the anti-rolling system is introduced,and a corresponding control system model is derived.The swing-tank mechanism provides phase lead compensation and reduces the system's sensitivity to wave disturbances.To enhance performance,robust control techniques are applied.Simulation results demonstrate that the proposed anti-rolling system delivers effective roll reduction for ships.展开更多
基金supported by the National Science and Technology Council,Taiwan[Grant NSTC 111-2628-E-006-005-MY3]supported by the Ocean Affairs Council,Taiwansponsored in part by Higher Education Sprout Project,Ministry of Education to the Headquarters of University Advancement at National Cheng Kung University(NCKU).
文摘This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion equations and hydrodynamic coefficients to create a realistic simulation.Although conventional model-based and visual servoing approaches often struggle in dynamic underwater environments due to limited adaptability and extensive parameter tuning requirements,deep reinforcement learning(DRL)offers a promising alternative.In the positioning stage,the Twin Delayed Deep Deterministic Policy Gradient(TD3)algorithm is employed for synchronized depth and heading control,which offers stable training,reduced overestimation bias,and superior handling of continuous control compared to other DRL methods.During the searching stage,zig-zag heading motion combined with a state-of-the-art object detection algorithm facilitates docking station localization.For the docking stage,this study proposes an innovative Image-based DDPG(I-DDPG),enhanced and trained in a Unity-MATLAB simulation environment,to achieve visual target tracking.Furthermore,integrating a DT environment enables efficient and safe policy training,reduces dependence on costly real-world tests,and improves sim-to-real transfer performance.Both simulation and real-world experiments were conducted,demonstrating the effectiveness of the system in improving AUV control strategies and supporting the transition from simulation to real-world operations in underwater environments.The results highlight the scalability and robustness of the proposed system,as evidenced by the TD3 controller achieving 25%less oscillation than the adaptive fuzzy controller when reaching the target depth,thereby demonstrating superior stability,accuracy,and potential for broader and more complex autonomous underwater tasks.
基金supported by the Jiangxi University of Water Resources and Electric Power Doctoral Research Initiation Fund(Grant No.2024kyqd030)。
文摘Ships experience rolling motion under the action of sea waves and may even face the risk of capsizing.Anti-rolling devices are designed to reduce this motion and enhance vessel safety.This is especially critical for engineering ships operating at sea under zero-speed conditions,where a stable posture is essential for efficient performance.Gyro stabilizers can suppress roll motion at zero speed;however,their high cost typically makes them unsuitable for large civilian vessels.Additionally,most existing anti-rolling devices rely on a certain water speed to function,which results in increased drag.In this study,an anti-rolling system incorporating swing control is proposed.Inspired by the human body's ability to maintain balance by swinging arms during walking or running,the system generates an antirolling moment by oscillating a water tank.This approach operates independently of water speed and does not generate additional drag.The mechanical design of the anti-rolling system is introduced,and a corresponding control system model is derived.The swing-tank mechanism provides phase lead compensation and reduces the system's sensitivity to wave disturbances.To enhance performance,robust control techniques are applied.Simulation results demonstrate that the proposed anti-rolling system delivers effective roll reduction for ships.
