To address the dynamic obstacle environment collision avoidance challenge of the marine autonomous surface ships (MASS), a decision-making method based on the deep Q-learning (DQN) and velocityobstacle (VO) algorithm...
详细信息
To address the dynamic obstacle environment collision avoidance challenge of the marine autonomous surface ships (MASS), a decision-making method based on the deep Q-learning (DQN) and velocityobstacle (VO) algorithm is proposed. Firstly, the encounter situation identification criteria are optimized, and a method for random collision scenario generation is designed. The model's performance is comprehensively evaluated by generating a wide variety of random collision scenarios which provide a broader assessment compared to manually set scenarios. Furthermore, a complete reward function for the dynamic collision avoidance problem is proposed, in which combines ship collision risk, the velocityobstacle method, and the International Regulations for Preventing Collisions at Sea (COLREGs). The MASS is not only guided towards the target by this reward function but is also ensured to comply with COLREGs during the collision avoidance process. It is worth noting that the trained model does not require retraining when faced with different numbers of target ships (TS). Simulation experiments are conducted with the trained model, involving random encounters with 1 to 10 TS in open waters. The results indicate that the proposed method demonstrates better collision avoidance performance compared to the DQN and proximal policy optimization algorithms.
Many Collision Avoidance Systems (CAS) for autonomous ships usually presume that a ship's dynamics are completely known in advance. However, precise parameters for ships in different operating conditions are, in f...
详细信息
Many Collision Avoidance Systems (CAS) for autonomous ships usually presume that a ship's dynamics are completely known in advance. However, precise parameters for ships in different operating conditions are, in fact, uncertain and unknown. The parameter identification of ship dynamics is challenging and time-consuming. Thus, uncertainties in the ship dynamic model are inevitable, which can lead to errors between real trajectories and predicted trajectories. These errors might result in an unexpected collision between ships. Therefore, it is necessary to consider tracking errors in the CAS, which is missing in most existing CAS. This article proposes a way to incorporate the errors in CAS. Specifically, a velocityobstacle (VO) algorithm is employed to find collision-free velocities with estimated tracking errors. Firstly, the ship is assumed to be a "black box" whose inputs and outputs are observable, while the internal workings are unknown. Secondly, parameters optimization of a PID controller are employed to determine the best feedback gains for tracking given trajectories;Thirdly, the maximal tracking errors for controlling the ship to arbitrary velocities are estimated. Finally, the maximal error is added to the safety distance and the VO algorithm is employed to find a collision-free solution. The proposed Unknown-Dynamics CAS (UD-CAS) can support the upgrade of existing conventional ships to Type I-III maritime autonomous surface ship. Copyright (C) 2020 The Authors.
Many Collision Avoidance Systems (CAS) for autonomous ships usually presume that a ship’s dynamics are completely known in advance. However, precise parameters for ships in different operating conditions are, in fact...
详细信息
Many Collision Avoidance Systems (CAS) for autonomous ships usually presume that a ship’s dynamics are completely known in advance. However, precise parameters for ships in different operating conditions are, in fact, uncertain and unknown. The parameter identification of ship dynamics is challenging and time-consuming. Thus, uncertainties in the ship dynamic model are inevitable, which can lead to errors between real trajectories and predicted trajectories. These errors might result in an unexpected collision between ships. Therefore, it is necessary to consider tracking errors in the CAS, which is missing in most existing CAS. This article proposes a way to incorporate the errors in CAS. Specifically, a velocityobstacle (VO) algorithm is employed to find collision-free velocities with estimated tracking errors. Firstly, the ship is assumed to be a “black box” whose inputs and outputs are observable, while the internal workings are unknown. Secondly, parameters optimization of a PID controller are employed to determine the best feedback gains for tracking given trajectories; Thirdly, the maximal tracking errors for controlling the ship to arbitrary velocities are estimated. Finally, the maximal error is added to the safety distance and the VO algorithm is employed to find a collision-free solution. The proposed Unknown-Dynamics CAS (UD-CAS) can support the upgrade of existing conventional ships to Type I-III maritime autonomous surface ship.
暂无评论