Deep Learning with Predictive Control for Human Motion Tracking

Abstract

We propose to combine model predictive control with deep learning for the task of accurate human motion tracking with a robot. We design the MPC to allow switching between the learned and a conservative prediction. We also explored online learning with a DyBM model. We applied this method to human handwriting motion tracking with a UR-5 robot. The results show that the framework significantly improves tracking performance.

To appear in 36th Annual Conference of the Robotics Society of Japan (RSJ 2018)