Learning of Key Pose Evaluation for Efficient Multi-contact Motion Planner
Shintaro Noda, Masaki Murooka, Yuki Asano, Ryusuke Ishizaki, Tomohiro Kawakami, Tomoki Watabe, Kei Okada, Takahide Yoshiike
Abstract
It is necessary to use not only foot but also hand, knee and other body parts to support body weight for locomotion in uneven terrain. Such multi-contact motion planning is an important research topic including lots of previous works; however, a problem of computational speed of planning is still remaining. In this paper, we propose a learning-based algorithm to speed up the planning. The algorithm reduces replanning of contact states by learning an evaluation function of key pose to reach goal. We investigated the learning performance by comparing three neural network configurations and two activation function. This research aims at achieving robust robotics system in unknown environments.
BibTeX
@inproceedings{icra2020_learningofkeypos,
title = {Learning of Key Pose Evaluation for Efficient Multi-contact Motion Planner},
author = {Shintaro Noda and Masaki Murooka and Yuki Asano and Ryusuke Ishizaki and Tomohiro Kawakami and Tomoki Watabe and Kei Okada and Takahide Yoshiike and Masayuki Inaba},
booktitle = {ICRA 2020},
year = {2020}
}