A deep reinforcement learning based distributed multi-UAV dynamic area coverage algorithm for complex environment.

Dynamic area coverage algorithm is often used in multiple unmanned aerial vehicle (multi-UAV) systems to realize searching or monitoring an area of interest (AOI). Improving coverage efficiency is one of the important research issues of dynamic area coverage. In this paper, we propose a distributed dynamic area coverage algorithm based on a reinforcement learning (RL) algorithm to enhance the coverage efficiency in complex application environments. A coverage information fusion based discrete soft actor–critic algorithm (herein FDSAC) is proposed to solve the non-stationary problem of RL algorithm in area coverage task under the communication constraint environment. Considering the equivalence of UAVs in the area coverage tasks, we introduce a multi-UAV cooperative learning method for FDSAC by sharing the strategy and experience of the UAVs to accelerate the learning speed of FDSAC in multi-UAV system. With the FDSAC algorithm, the UAVs can intelligently select the best coverage points and achieve almost optimal coverage point planning for the entire coverage process. In addition, we also provide a coverage point adjustment method based on the distribution of obstacles to enable the proposed algorithm adapt to obstacle environments. The experimental results demonstrate that the proposed algorithm can efficiently complete the area coverage task in complex communication and stochastic control noise environment. The good scalability, environment adaptability, and practicality of our algorithm have been also confirmed in different complex environments of different experimental platforms. [ABSTRACT FROM AUTHOR]