No abstract

No abstract

No abstract

No abstract

This paper adopts Deep Deterministic Policy Gradient (DDPG) algorithm in Deep Reinforcement Learning (DRL) to analyse the eca_a9 Autonomous Underwater Vehicle (AUV) motion attitude control based on Robot Operating System (ROS) and Gazebo simulation platform, within UUV Simulator underwater simulation environment. The heel angle ϕ, pitch angle θ heading angle φ are chosen as the agent state input and control variables, and the output angle of the four rudders is selected as the agent action output. The problem of strong coupling caused by X-type rudder and multi-degree-of-freedom control is solved with reinforcement learning and training. In addition, this paper proposes a multi-state space and multi-action space control scheme, which has achieved remarkable results for the AUV’s fixed speed, constant heel, constant pitch, and constant heading motion control.