Multi-Agent Visual Coordination using Optical Wireless Communication

Communication is a key element in applying multi-agent reinforcement learning to wide range of real-world scenarios. We focus on optical wireless communication (OWC), which practical solution be used various real situations where radio not available, such as underwater or lot noise environment. OWC method communicating only with other agents visual using light, unlike wave like mostly assumed existing research learning. Due limited communication, when used, overall performance generally degraded from the case full communication. In this paper, we propose that learns coordination behavior OWC. Our proposed visually cooperative enables equipped field view (FOV) cameras efficiently comprehend and imagine their surrounding environment through Experimental results simulation demonstrated that, method, multi-agents general FOV show comparable those Additionally, it has been can improve algorithms. also implement devices mobile robots operation.