@InProceedings{noda:icra:2020,
  author    = {Noda, Shintaro and Murooka, Masaki and Asano, Yuki and Ishizaki, yusuke and Kawakami, Tomohiro and Watabe, omoki and Okada, Kei and Yoshiike, Takahide and Inaba, Masayuki},
  title     = {Learning of Key Pose Evaluation for Efficient Multi-Contact Motion Planner},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year      = {2020},
  address   = {Paris, France},
  month     = {May},
  keywords  = {Planning, Trajectory, Torque, Legged locomotion, Jacobian matrices, Knee, Collision avoidance},
  doi       = {10.1109/ICRA40945.2020.9197189},
  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.}
}