Neuromorphic Control for Robotic Manipulator
This paper presents a “Hierarchical Hybrid Neuromorphic Control System” for intelligent control of robotic manipulator and for acquiring knowledge and learning. This system comprises two levels: a “learning” level and an “adaptation” level. Neural networks are employed for both levels. The “learning” level has a hierarchical structure and is used for the strategic planning of the robotic manipulation in conjunction with the knowledge base system, in order to enlarge the adaptive range. The learning level can infer an unknown fact from a priori knowledge and visual information for the strategic planning, and is updated by the recent information from the adaptation level through the long term learning process. On the other hand, the adaptation is used for the adjustment of the control law to the current status of the dynamic process. The approximate target and initial states of the adaptation level are given by the learning level.
KeywordsNeural Network Strategic Planning Force Control Inference Rule Adaptation Level
Unable to display preview. Download preview PDF.
- T. Fukuda, T. Shibata, M. Tokita and T. Mitsuoka, Neural Network Applications for Robotic Motion Control; Adaptation and Learning, Proc. of UCNN ‘80 - San Diego, pp. 447–451 (1990)Google Scholar
- T. Fukuda and T. Shibata, Neural Network Applications for Robotic Motion Control, IEEE, Proc. of IEEE Int. Workshop on Intelligent Motion Control, SL31–SL36 (1990)Google Scholar
- H. Asada and S. Liu, Transfer of Human Skills to Neural Net Robot Controllers, Proc. of Robotics and Automation, pp. 2442–2448 (1991)Google Scholar
- H. Asada and S. Hirai, “Towards A Symbolic-Level Force Feedback: Recognition of Assembly Process States,” Proc. of Int. Symp. on Robotic Research, pp. 341–346 (1990)Google Scholar
- A. Waibel, T. Hanazawa, G. Hinton, K. Shikano and K. Lang, Phenome recognition: Neural networks versus hidden Markov models, in Proc. 1988 IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. 5, pp. 107–110 (1988)Google Scholar
- T. Fukuda and T. Shibata, “Neuromorphic Control for Robotic Manipulators; position, force and impact control”, IEEE, Proc. of Fifth IEEE Int. Symp. on Intelligent Control, pp 310–315 (1990)Google Scholar
- T. Fukuda, T. Shibata, M. Tokita and T. Mitsuoka, “Adaptation and Learning by Neural Network for Robotic Manipulator”, IMACS, Proc. of Int. Symp. on Mathematical and Intelligent Models in System Simulation, I.B.2.1–5 (1990)Google Scholar