Joint Active and Passive Beamforming Design for Intelligent Reflecting Surface Assisted Integrated Sensing and Communications Systems.

Abstract

As a promising emerging technology, the combination of integrated sensing and communications (ISAC) system and intelligent reflecting surface (IRS) can obtain better comprehensive properties for both communication and sensing. To explore the potential ability of multi-IRS assisted ISAC system, both the active transmit matrix and passive reflecting matrix should be delicately jointly optimized for simultaneous communication and sensing enhancement, which introduce additional hardware complexity and difficulty to obtain a solution by the conventional methods. Therefore, this paper propose a successive convex approximation (SAC) and multi-agent deep reinforcement learning (MADRL) combined approach to enhance the communication capability with the target detection beampattern constraint. In particular, numerical results show that the sensing performance can be guaranteed with the boosting of communication capability, especially when the users are not directly visible to BS.