Design of a skill-learning system based on human-motion reproduction

Professional human skills are important in many works. Accordingly, professional skill learning is also an important issue to improve quality of a human work such as medical care. This paper proposes a human-motion-reproduction method which has different learning structures. To consider both position and force information of human motions, a motion-copying system which stores and reproduces human motions based on a bilateral control structure is employed in the proposed control system. Modal space to design the structure of the proposed motion-reproduction method is also introduced. Experiments verified a learning example using several structures of the proposed motion-reproduction.

[1]  Guang-Zhong Yang,et al.  Imitation of Dynamic Walking With BSN for Humanoid Robot , 2015, IEEE Journal of Biomedical and Health Informatics.

[2]  Kiyoshi Ohishi,et al.  Stability Analysis and Experimental Validation of a Motion-Copying System , 2009, IEEE Transactions on Industrial Electronics.

[3]  Kouhei Ohnishi,et al.  Motion control for advanced mechatronics , 1996 .

[4]  Kiyoshi Ohishi,et al.  Fine Force Reproduction Based on Motion-Copying System Using Acceleration Observer , 2014, IEEE Transactions on Industrial Electronics.

[5]  Rajiv Kapoor,et al.  Integrated approach for human action recognition using edge spatial distribution, direction pixel and -transform , 2015, Adv. Robotics.

[6]  Emre Sariyildiz,et al.  Stability and Robustness of Disturbance-Observer-Based Motion Control Systems , 2019, IEEE Transactions on Industrial Electronics.

[7]  K. Ohnishi,et al.  Reproducibility and operationality in bilateral teleoperation , 2004, The 8th IEEE International Workshop on Advanced Motion Control, 2004. AMC '04..

[8]  Seiichiro Katsura,et al.  Synthesis of Motion-Reproduction Systems Based on Motion-Copying System Considering Control Stiffness , 2016, IEEE/ASME Transactions on Mechatronics.

[9]  Atsushi Nakazawa,et al.  Task model of lower body motion for a biped humanoid robot to imitate human dances , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Toshiyuki Murakami,et al.  Stability analysis of disturbance observer based controllers for two-wheel wheelchair systems , 2014, Adv. Robotics.

[11]  Rong-Jyue Wang,et al.  Image Recognition and Force Measurement Application in the Humanoid Robot Imitation , 2012, IEEE Transactions on Instrumentation and Measurement.

[12]  Nariman Sepehri,et al.  Selection of Network Parameters in Wireless Control of Bilateral Teleoperated Manipulators , 2015, IEEE Transactions on Industrial Informatics.

[13]  Lei Guo,et al.  Disturbance-Observer-Based Control and Related Methods—An Overview , 2016, IEEE Transactions on Industrial Electronics.

[14]  Ko Yamamoto,et al.  Humanoid motion analysis and control based on COG viscoelasticity , 2017, Adv. Robotics.

[15]  Andrej Gams,et al.  Real-time full body motion imitation on the COMAN humanoid robot , 2014, Robotica.

[16]  Kao-Shing Hwang,et al.  Motion Segmentation and Balancing for a Biped Robot's Imitation Learning , 2017, IEEE Transactions on Industrial Informatics.

[17]  Jun-Ho Oh,et al.  Humanoid state estimation using a moving horizon estimator , 2017, Adv. Robotics.

[18]  Bram Vanderborght,et al.  Development of a generic method to generate upper-body emotional expressions for different social robots , 2015, Adv. Robotics.

[19]  Ales Hace,et al.  Pseudo-Sensorless High-Performance Bilateral Teleoperation by Sliding-Mode Control and FPGA , 2014, IEEE/ASME Transactions on Mechatronics.

[20]  Toshiyuki Murakami,et al.  Torque sensorless control in multidegree-of-freedom manipulator , 1993, IEEE Trans. Ind. Electron..