Machine learning-based energy harvesting for wearable exoskeleton robots

Abstract

Wearable exoskeleton robot can provide additional movement assistance for the wearer in many fields and enhance their movement ability. Reduce the degree of long-term exercise fatigue and avoid injury during exercise. However, due to the limitation of battery technology and battery capacity, it is difficult for exoskeleton robots to work continuously for a long time. Therefore, the energy management and optimization of wearable exoskeleton robot become an important way to break through the bottleneck of its future development. In order to optimize the energy management system of exoskeleton robot, an energy management control strategy based on machine learning and a SOC11SOC: State of Charge. value prediction model were proposed. Based on the structure of composite power supply, this paper selects Q-learning in machine learning to build the battery energy management strategy system, and introduces the time difference reinforcement learning algorithm. The experimental results show that the energy management optimization system can effectively shorten the response time of the robot system, reduce the prediction error value of SOC value, and provide more accurate electricity information for the management and control system. At the same time, the system in this paper shows good energy management control under different working conditions, and can realize dynamic energy management and improve energy utilization according to the actual power demand and power supply operation of the exoskeleton robot.