Path Planning for Ferry Crossing Inland Waterways Based on Deep Reinforcement Learning

Path planning is a key issue for safe navigation of inland ferries. With the development ship intelligence, how to enhance decision–support system ferry in complex environment one issues. The ferries need cross channel frequently and, thus, risky encounters with target ships waterway are more frequent, so they an intelligent that can deal situations. In this study, reinforced deep learning method proposed path during crossing waterways. state space, action space and reward function Deep Q-network (DQN) model designed improved establish autonomous considering both economy safety. DQN also takes into account behavior, Finally, applied case studies verify its effectiveness.