Abstract
This study aims to solve the problems of poor exploration ability, single strategy, and high training cost in autonomous underwater vehicle (AUV) motion planning tasks and to overcome certain difficulties, such as multiple constraints and a sparse reward environment. In this research, an end-to-end motion planning system based on deep reinforcement learning is proposed to solve the motion planning problem of an underactuated AUV. The system directly maps the state information of the AUV and the environment into the control instructions of the AUV. The system is based on the soft actor–critic (SAC) algorithm, which enhances the exploration ability and robustness to the AUV environment. We also use the method of generative adversarial imitation learning (GAIL) to assist its training to overcome the problem that learning a policy for the first time is difficult and time-consuming in reinforcement learning. A comprehensive external reward function is then designed to help the AUV smoothly reach the target point, and the distance and time are optimized as much as possible. Finally, the end-to-end motion planning algorithm proposed in this research is tested and compared on the basis of the Unity simulation platform. Results show that the algorithm has an optimal decision-making ability during navigation, a shorter route, less time consumption, and a smoother trajectory. Moreover, GAIL can speed up the AUV training speed and minimize the training time without affecting the planning effect of the SAC algorithm.
Highlights
Autonomous underwater vehicles (AUVs) with their autonomy and flexibility play an important role in seabed surveying and mapping, ocean monitoring, underwater structure survey, information collection, and other aspects with the continuous advancement of computer software and hardware and the artificial intelligence (AI) technology in modern times.Intelligence is the overall development trend of the autonomous underwater vehicle (AUV) technology, and motion planning technology is the basis for AUV to autonomously navigate and complete various tasks. iations
Unity software is used for visual simulation, the program is written based on C # and python languages, the neural network is built by torch, and the model is trained by GPU
This research proposes an end-to-end AUV motion planning method based on the soft actor–critic (SAC) algorithm to solve the problems of poor exploration ability, single strategy, and high training cost in AUV motion planning task and overcome certain difficulties, such as multiple constraints and sparse reward environment
Summary
Autonomous underwater vehicles (AUVs) with their autonomy and flexibility play an important role in seabed surveying and mapping, ocean monitoring, underwater structure survey, information collection, and other aspects with the continuous advancement of computer software and hardware and the artificial intelligence (AI) technology in modern times.Intelligence is the overall development trend of the AUV technology, and motion planning technology is the basis for AUV to autonomously navigate and complete various tasks. iations. Motion planning is guided by global path planning, using local environment information obtained online by sensing devices and generating discrete or continuous spatial path points or control information at the bottom of the robot, allowing the planning of the position, speed, and acceleration of the AUV during its motion. This task needs to satisfy two conditions. The motion planning task is divided into two parts, namely, path planning and following, and the design process is complicated These two modules depend on the characteristics of the environment and the dynamic constraints of the system, resulting in a sensitive system. The robot can only obtain strategies in a single environment and lacks adaptability to the environment
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
