DDQN path planning for unmanned aerial underwater vehicle (UAUV) in underwater acoustic sensor network

Human exploration of the ocean has never stopped. A large number of sensors are placed in the ocean to establish ocean sensor networks to obtain more information about the marine environment, crustal dynamic changes and so on. With the development of science and technology, Autonomous Underwater Vehicles (AUV) appear and are widely used in marine sensor networks. Due to the complex and changeable ocean environment, the slow speed of traditional and the lack of reasonable path planning and other reasons, AUV waste a lot of time and energy, which cannot efficiently collect information. In this paper, the Unmanned Aerial Underwater Vehicle (UAUV) is introduced into the ocean sensor network. Establish a two-dimensional scene model, find the best water entry point for UAUV to complete the task in the shortest time and minimum power consumption by traversing the search algorithm, and compare the performance of UAUV cross domain mode and underwater mode to collect marine sensor data. Meanwhile, establishing three-dimensional ocean sensor scene model, and using DDQN algorithm to solve the path planning problem of UAUV. The results show that the cross-domain mode of UAUV in the two-dimensional scene model saves 74.7% times and 24.34% energy compared with the traditional underwater mode. In the three-dimensional scene model, the UAUV is trained to the optimal path by the DDQN algorithm, which saves 60.94% of the time and 20.26% of the energy compared to the traditional underwater mode. The results prove the feasibility, stability and efficiency of UAUV introduction into marine sensor network, the effectiveness of DDQN algorithm to solve UAUV path planning problems.