학술대회논문

실감교류인체감응솔루션연구단의 주요 학술대회 성과를 소개합니다.

Learning Basis Skills by Autonomous Segmentation of Humanoid Motion Trajectories

Learning Basis Skills by Autonomous Segmentation of Humanoid Motion Trajectories
국내/국제 국제 국가명 일본
국제공동연구 Istituto Italiano di Tecnologia(Italy), Lund Univ.(Sweden)
학술대회명 International Conference on Humanoid Robots(Humanoid) 2012 개최연월 2012-11

저자 SangHyoung Lee, IlHong Suh, Sylvain Calinon, Rolf Johansson
초록
Manipulation tasks are characterized by continuous motion trajectories containing a set of key phases. In this paper, we propose a probabilistic method to autonomously segment the motion trajectories for estimating the key phases embedded in such a task. The autonomous segmentation process relies on principal component analysis to adaptively project into one of the low-dimensional subspaces, in which a Gaussian mixture model is learned based on Bayesian information criterion and expectation-maximization algorithms. The basis skills are estimated by a set of Gaussians approximating quasi-linear key phases, and those times spent calculated from the segmentation points between two consecutive Gaussians representing the local changes of dynamics and directions of the trajectories. The basis skills are then used to build novel motion trajectories with possible motion alternatives and optional parts. After sequentially reorganizing the basis skills, a Gaussian mixture regression process is used to retrieve smooth motion trajectories. Two experiments are presented to demonstrate the capability of the autonomous segmentation approach.
키워드 Humanoid Motion Trajectories, Learning Basis Skills

과제명 사용자 행동양식의 모방 학습 기반 휴먼 아바타의 창발적 복합행동 생성 기술
연구기관 한양대학교 연구책임자 서일홍