SEARCH
MENU

History of Robotics Research and Development of Japan2008ManipulationDesired Trajectory and Sensory Feedback Control Law Synthesis for an Origami-Folding Robot based on the Statistical Feature of Direct Teaching by a Human

Kenta TanakaKyoto University(currently Honda R&D Co., Ltd.)
Yasuyuki KiharaKyoto University(currently IHI Corporation)
Yasuyoshi YokokohjiKyoto University(currently Kobe University)
We developed a robotic hand that folds an origami form “Tadpole”. However, the robot, which simply replays a given trajectory, often fails in folding due to the fluctuation of origami paper behavior. In this paper, we propose a novel method to synthesize a desired trajectory and sensory feedback control laws for robots based on the statistical feature of direct teaching data demonstrated by a human. Hidden Markov Model (HMM) is used to model the statistical feature of human motion. Nominal desired trajectory is obtained by temporally normalizing and spatially averaging the teaching data. Sensory feedback control laws are then synthesized based on the output probability density function parameters of the HMM. Considering velocity variance and canonical correlation between velocity and force of the teaching data, important motion segments are extracted and feedback control laws are applied only for those segments. Experimental results showed that the success rate and folding quality of “Valley-fold” were improved by the proposed method. The proposed method enables robot motion teachers to simply perform direct teaching several times to transfer their skill, which is difficult to describe explicitly, to the robot. 24th RSJ Best Paper Award in 2010.
折り紙ロボット概観
Overview of an Origami-Folding Robot
直接教示
Direct Teaching

Movies

photo
Direct Teaching
photo
Experiment of the generated trajectory

Correspondence papers

Kenta Tanaka, Yasuyuki Kihara, Yasuyoshi Yokokohji：Desired Trajectory and Sensory Feedback Control Law Synthesis for an Origami-Folding Robot based on the Statistical Feature of Direct Teaching by a Human

Journal of the Robotics Society of Japan, vol27, no6, pp585-695, 2009 (in Japanese).

Kenta Tanaka, Yasuyoshi Yokokohji：Motion Generation Method for an Origami Folding Robot Based on the Direct Teaching Data by a Human

Proc. of RSJ2007 (in Japanese).

Related papers

[1] Masaki Onishi, Tadashi Odashima, Zhiwei Luo: “Cognitive Integrated Motion Generation for Environmental Adaptive Robots”, The transactions of the Institute of Electrical Engineers of Japan，Vol.125-C, No.6, pp.856–862, 2005 (in Japanese).

[2] Yasuo Kuniyoshi, Yoshiyuki Ohmura, Koji Terada, Akihiko Nagakubo: “Dynamic Roll-and-Rise Motion by an Adult-Size Humanoid Robot”, Journal of the Robotics Society of Japan, vol23, no6, pp856-862, 2005 (in Japanese).

[3] T. Inamura, I. Toshima, H. Tanie, and Y. Nakamura:“Embodied Symbol Emergence Based on MimesisTheory,” International Journal of Robotics Research,Vol.23,No.4-5, pp.363–377, 2004.

Related Article

記事はありません。