Strategies for Feet Massage Robot to Position the Pelma Acupoints with Model Predictive and Real-time Optimization

다국어 초록 (Multilingual Abstract)

It is one of critical factors for a massage robot to find and position the acupuncture point precisely inorder to cure the diseases. Based on large amount of sample data offline, Chinese medical empirical knowledgeis also introduced to build the prediction model. The massagist prescription and the robot mechanism devise areboth considered for robot positioning. Least squares method is of simplicity, easy to use and high efficiency.
Its real-time calculation is very effective, too. A modeling method for robot positioning is proposed based onleast squares. Knowledge consultation is set for the calculation of acupoint position. The robot needs to get thefeature points of a foot to be massaged. The foot contour sampling data are divided into piecewise curve fitting. Qlearningis adopted to optimize the robot positioning for they are model free. CMAC (Cerebellar Model ArticulationController) cerebellum model is incorporated into the function approximation of Q learning. The learning systemis rewarded by referring to the strengths of instrumental signal. By the direct representation, the model of humanpelma acupoint is expressed with the vector variables and formal computer language. Through prediction model’scalculation, the robot will work out the rough position of acupuncture point. Meanwhile, Q learning does the onlineadjustment for accurate location. These strategies provide for the robot to automatically search and position thepelma acupoint with little real-time computation and storage. The idea of this paper also prompts a research cue forthe development of Chinese medical standardization.

참고문헌 (Reference)

1 J. -G. Wang, "Tracking control of a redundant manipulator with the assistance of tactile sensing" 17 (17): 833-845, 2011

2 G. Du, "The design of searching bodies acupuncture point for Chinese massage robot" 27 (27): 637-640, 2011

3 S. Yu, "Study on a novel series-parallel Chinese massage manipulator" 16 (16): 1773-1777, 2005

4 Y. Lv, "Steady-state detecting method based on piecewise curve fitting" 33 (33): 194-200, 2012

5 J. Wu, "Research on the curve fitting method based on curvature data" 21 (21): 258-262, 2003

6 T. Wang, "Research and realization of the Chinese massage robot based on three-dimensional model" 6493-6497, 2010

7 H. Gao, "Research and development of Chinese medical massage robot" 33 (33): 553-562, 2011

8 R. S. Sutton, "Reinforcement Learning: An Introduction" MIT Press 1998

9 F. Tao, "Recognition and therapeutic apparatus for human body acupuncture points"

10 W. Gao, "Method of deal with data error by subsection curve fitting and discrete degree" 31 (31): 55-56, 2005

11 J. Wang, "Massaging human feet by a redundant manipulator equipped with a tactile sensor" 7-12, 2010

12 J. -G. Wang, "Manipulation of a mobile modular manipulator interacting with the environment with the assistance of tactile sensing feedback" 8 (8): 777-793, 2011

13 K. Mouri, "Identification and hybrid impedence control of human skin muscle by multi-fingered robot hand" 2895-2900, 2007

14 P. Minyong, "Hybrid impedence control for massage system by using humanoid multi-fingered robot hand" 3021-3026, 2007

15 P. Minyong, "Expert massage motion control by multi-fingered robot hand" 3035-3040, 2003

16 H. Koga, "Development of oral rehabilitation robot for massage therapy" 111-114, 2007

17 K. Masao, "Development of a mechanotherapy unit for examing the possibility of an intelligent massage robot" 346-353, 1996

18 C. -G. Kang, "Design of a percussive massage robot rapping human Backs" 962-967, 2007