DRL-Based Joint Trajectory Planning and Beamforming Optimization in Aerial RIS-Assisted ISAC System
Xipeng Chen, Xiaowen Cao, Lifeng Xie, Yejun He
Abstract
In this paper, we consider a reconfigurable intelligent surface (RIS) enabled integrated sensing and communication (ISAC) system, where the RIS is mounted on an unmanned aerial vehicle (UAV) to enhance signal quality and connectivity coverage by exploring the flexible mobility and adjusting the phase and amplitude of reflected signals. Towards this end, a communication rate max-min problem is formulated by jointly optimizing the beamforming vector, RIS phase shift and UAV trajectory under the constrains of power consumption and sensing requirement. However, due to the coupled variables, this problem is a non-convex problem and hard to be optimally solved. Hence, we reformulate the primary problem as a sequential decision-making problem and exploit a deep reinforcement learning (DRL)-based solution to find a tractable solution. Numerical results validate the effectiveness and the superiority of the proposed algorithm compared with the benchmark schemes.