JRM Vol.2 No.4 pp. 258-265
doi: 10.20965/jrm.1990.p0258


Motor Schema Model Learned by Structural Neural Networks

Toshio Tsuji*, Yusuke Ishida*, Koji Ito*, Mitsuo Nagamachi* and Tatsuo Nishino**

*Faculty of Engineering, Hiroshima University, Higashi-Hiroshima-shi, 724 Japan

**Department of Industrial Engineering, Hiroshima Institute of Technology Hiroshima-shi, 731-51 Japan

August 20, 1990
Human beings remember plans concerning typical motions which occur frequently as schema, and by selecting suitable schema depending on conditions, generate muscular motion almost unconsciously. Though a motor schema represents typical motions, it is equipped with superior plan structure taking into consideration the concurrency and seriality of motions as seen in grasping actions and walking motions, and the structure of plans can be acquired by learning. In this paper, a study is made of the modeling of such motor schema with the use of neural networks. For this purpose, the neural network is structured beforehand into the part which generates action sequences in the form containing concurrency (concurrent action generation part) and the part which modifies the action sequences to satisfy constraints which cannot be executed concurrently (constraint representation part). After learning in each part model the neural network can generate motion sequences while taking into consideration the seriality and concurrency of motion by combining the parts at the time of execution. Finally, this model is applied to the formation of typewriting action motor schema, and it is demonsted that generates motion sequences which take into consideration the constraint of the motion system accompanying the execution of motion.
Cite this article as:
T. Tsuji, Y. Ishida, K. Ito, M. Nagamachi, and T. Nishino, “Motor Schema Model Learned by Structural Neural Networks,” J. Robot. Mechatron., Vol.2 No.4, pp. 258-265, 1990.
Data files:

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jun. 03, 2024