Project website (paper, code, video): http://generalroboticslab.com/DukeHum...

Abstract: We present the Duke Humanoid, an opensource 10degreesoffreedom humanoid, as an extensible platform for locomotion research. The design mimics human physiology, with minimized leg distances and symmetrical body alignment in the frontal plane to maintain static balance with straight knees. We develop a reinforcement learning policy that can be deployed zeroshot on the hardware for velocitytracking walking tasks. Additionally, to enhance energy efficiency in locomotion, we propose an endtoend reinforcement learning algorithm that encourages the robot to leverage passive dynamics. Our experiment results show that our passive policy reduces the cost of transport by up to 50% in simulation and 31% in realworld testing.