Optimizing Human Motion for the Control of a Humanoid Robot

Alla Safonova and Nancy S. Pollard and Jessica K. Hodgins

Sarcos humanoid robot at ATR (DB) tracking motion capture data of a human actor

Using pre-recorded human motion and trajectory tracking, we can control the motion of a humanoid robot for freespace, upper body gestures. However, the number of degrees of freedom, range of joint motion, and achievable joint velocities of today’s humanoid robots are far more limited than those of the average human subject. In this paper, we explore a set of techniques for limiting human motion of upper body gestures to that achievable by a Sarcos humanoid robot located at ATR. In particular we have found that it is important to preserve the configuration of the hands and head for upper body motion. We assess the quality of the results by comparing the motion of the human actor to that of the robot, both visually and quantitatively.

paper (pdf)

We tested these techniques with fourteen motion sequences from seven professional actors. Each subject performed to the same audio track of the children’s song, “I’m a little teapot.” We chose this selection because it was familiar enough that most actors would perform the motion in a similar but not identical way. It was our hope that an individual’s style would be preserved through the transformations necessary to allow the robot to perform the motion.

movie for actor 1 (9MB)
movie for actor 3 (11MB)
movie for actor 5 (8MB)