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

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.

[1]  Woo-Keun Yoon,et al.  Task Skill Transfer Method Using a Bilateral Teleoperation , 2007 .

[2]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[3]  T. Fukuda,et al.  Manipulation of deformable linear objects using knot invariants to classify the object condition based on image sensor information , 2006, IEEE/ASME Transactions on Mechatronics.

[4]  Katsushi Ikeuchi,et al.  Toward an assembly plan from observation. I. Task recognition with polyhedral objects , 1994, IEEE Trans. Robotics Autom..

[5]  Katsushi Ikeuchi,et al.  A sensor fusion approach for recognizing continuous human grasping sequences using hidden Markov models , 2005, IEEE Transactions on Robotics.

[6]  Joris De Schutter,et al.  Contact State Segmentation Using Particle Filters for Programming by Human Demonstration in Compliant Motion Tasks , 2006, ISER.

[7]  Taketoshi Mori,et al.  Online Segmentation of Actions Using Hidden Markov Models and Conceptional Relations of Daily Actions , 2007 .

[8]  Yoshihiko Nakamura,et al.  An Integrated Model of Imitation Learning and Symbol Emergence based on Mimesis Theory , 2004 .

[9]  Hidefumi Wakamatsu,et al.  Topological Manipulation Planning for Knotting and Tightening of Deformable Linear Objects Based on Knot Theory , 2006 .

[10]  Hiroshi Kimura,et al.  Understanding of Human Assembly Tasks for Robot Execution Generation of Optimal Trajectories Based on Transitions of Contact Relations , 2004 .

[11]  Richard A. Volz,et al.  Acquiring robust, force-based assembly skills from human demonstration , 2000, IEEE Trans. Robotics Autom..

[12]  Yasuo Kuniyoshi,et al.  Dynamic Roll-and-Rise Motion by an Adult-Size Humanoid Robot , 2004, Int. J. Humanoid Robotics.

[13]  Yoshihiko Nakamura,et al.  Embodied Symbol Emergence Based on Mimesis Theory , 2004, Int. J. Robotics Res..

[14]  H. Harry Asada,et al.  Teaching and program generation for the hybrid position/force control via the measurement of human manipulation tasks. , 1987 .

[15]  Yasuyoshi Yokokohji,et al.  Origami folding by a robotic hand , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Jian Huang,et al.  Model-Based Intelligent Fault Detection and Diagnosis for Mating Electric Connectors in Robotic Wiring Harness Assembly Systems , 2008, IEEE/ASME Transactions on Mechatronics.

[17]  Blake Hannaford,et al.  Hidden Markov Model Analysis of Force/ Torque Information in Telemanipulation , 1989, ISER.

[18]  Geir Hovland,et al.  Hidden Markov Models as a Process Monitor in Robotic Assembly , 1998, Int. J. Robotics Res..

[19]  Shinichi Hirai,et al.  Human-demonstration Based Approach to the Object Motion Design and the Recognition of Process State Transitions in Insertion of Deformable Tubes , 1997 .

[20]  Zhi-Wei Luo,et al.  Whole Body Manipulation Using Tactile Information , 2008 .

[21]  Katsushi Ikeuchi,et al.  Representation for knot-tying tasks , 2006, IEEE Transactions on Robotics.

[22]  Yangsheng Xu,et al.  Stochastic similarity for validating human control strategy models , 1998, IEEE Trans. Robotics Autom..

[23]  Hidefumi Wakamatsu,et al.  Linear Object Manipulation Including Knotting/Unknotting , 2005 .

[24]  Blake Hannaford,et al.  Hidden Markov Model Analysis of Force/Torque Information in Telemanipulation , 1991, Int. J. Robotics Res..