Co-Management of Computational and Mechanical Energy in Mobile Robots Using Reinforcement Learning

Optimizing energy consumption is a critical challenge in autonomous mobile robotics, essential for extending battery life. Mechanical and computational components are the primary energy consumers, and studies show that dynamically co-managing their power usage—such as adjusting processing frequency relative to mechanical speed—significantly improves efficiency. This improvement is primarily due to the relationship between decision-making processes based on mechanical speed and computational workload. In this paper, we propose an agile reinforcement learning algorithm for dynamic co-management, tested on a rover equipped with a brushless motor, a Jetson TX2 processor, and an event-based camera. Our approach effectively addresses scalability and accuracy issues in prior methods, achieving energy efficiency improvements between 16.98% and 60.86% compared to the most efficient existing techniques.