日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
arXiv:1808.02200

Deep Learning with Predictive Control for Human Motion Tracking

Deep Learning with Predictive Control for Human Motion Tracking

シェア:XThreadsFacebookLINEはてブBluesky

著者: Don Joven Agravante, Giovanni De Magistris, Asim Munawar, Phongtharin Vinayavekhin, Ryuki Tachibana

分類: cs.RO

原文アブストラクト

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.