Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a di®erent kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by de ̄ning a multi-objective reward function of zero moment point and joint torques to represent the stability and e®ort, we computed reward pro ̄les for each demonstration. Since individual reward pro ̄les show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward pro ̄les of the robot should show the same temporal structure of those of the human, we used di®erential evolution to compute a trajectory that ̄ts all humanoid constraints and minimizes the di®erence between the robot reward pro ̄le and the predicted pro ̄le if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown.