Multi-AUV cooperative underwater data acquisition method based on DQN and matrix completion

• Main Authors: CAO RUNQI, WANG HAIHONG, NIU QIUNA, LI SHUANG, WANG JINGJING, YU ZEHUI, LIU SHUAI, XU JINYUN, SHI WEI
• Format: Patent
• Language: Chinese; English
• Published: 28.03.2023
• Subjects: GYROSCOPIC INSTRUMENTS; MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC ORINFRASONIC WAVES; MEASURING; MEASURING DISTANCES, LEVELS OR BEARINGS; NAVIGATION; PHOTOGRAMMETRY OR VIDEOGRAMMETRY; PHYSICS; SURVEYING; TESTING

The invention discloses a multi-AUV cooperative underwater data acquisition method based on DQN and matrix completion, and belongs to the technical field of ocean data acquisition. The method comprises the following steps: firstly, arranging underwater acoustic sensor nodes, calculating the value of information generated by each region according to the correlation and timeliness between node generated data and data required by application, and applying the value to follow-up path planning of an AUV (Autonomous Underwater Vehicle); then, a deep reinforcement learning method is used for planning information collection paths of the multiple AUVs, and the navigation tracks of the multiple AUVs are continuously corrected in the driving process of the AUVs; finally, a matrix completion type data acquisition method is designed, so that the AUV only needs to acquire data generated by key nodes, and the workload of data acquisition is reduced. According to the invention, multiple AUVs can be effectively cooperated to