Minimizing Energy Consumption in Mobile Robotics with STAR-RIS in Smart Factories

The integration of robots into networks, forming connected robots, holds great promise as the technology for upcoming smart factories. These robots offer cost-effective solutions and demonstrate exceptional maneuverability. However, the stability and quality requirements of communication links between the access point (AP) and the robots pose issues that restrict their applicability in factory environments. These limitations arise especially in scenarios where obstacles may obstruct wireless connections. To tackle these issues, we propose a system that adopts a Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) to improve connectivity between the AP and the robot. Subsequently, we formulate an optimization problem that seeks to enhance the robot’s trajectory, optimize the transmitted power of the AP, and the transmission and reflection amplitude and phase shift of the STAR-RIS. The goal is to minimize the total energy consumption of the system while ensuring compliance with obstacle avoidance constraints and meeting the required data rate threshold. We efficiently solve this joint optimization problem using a deep reinforcement learning method. Simulation results showcase the efficacy of our proposed system and algorithm, particularly in terms of energy efficiency and robot movement within smart factory environments.