Abstract
Learning control is a new approach to the problem of skill refinement for robot arms by iterative training. It is considered to be a mathematical model of motor program learning for skilled motions in the central nervous system.
This paper proposes a class of learning control algorithms with a forgetting factor 1»α>0 and without differention of velocity signals, which updates the input command by μ k+1=(1−α)μ k + αμ 0 + Φe k , where μ k and e k stand for command input and velocity error at k-th exercise respectively. The robustness of this learning control with respect to reinitialization errors, fluctuations of robot dynamics, and measurement noises is studied in detail. It is shown that not only the passivity of robot dynamics but also the exponential passivity of displacement dynamics on errors and difference dynamics between consecutive trials play a crucial role in proving the uniform boundedness of transient behaviors and the convergence in the progress of learning. Furthermore, two methods of learning called “interval training” and “selective learning” are proposed, which updates μ 0 in the long-term memory every after several trials by the current command input μ k or by the best command input among the past trials. The effectiveness of these methods in acceleration of the speed of convergence is also discussed.
Preview
Unable to display preview. Download preview PDF.
References
S. Arimoto, S. Kawamura, and F. Miyazaki, “Bettering operation of robots by learning,” Journal of Robotic Systems, Vol. 1, pp. 123–140, 1984.
S. Arimoto, S. Kawamura, and F. Miyazaki, “Bettering operation of robots by learning; A new control theory for servomechanism and mechantronics systems,” Proc. 23rd IEEE Conf. Decision and Control, Las Vegas, NV, pp. 1064–1069, 1984.
, “Can mechanical robots learn by themselves?,” in “Robotic Research” The Second International Symposium, H. Hanafusa & H. Inoue, Eds., MIT Press, Cambridge, Massachusetts, pp. 127–134, 1985.
S. Arimoto, “Mathematical theory of learning with applications to robot control”, Proc. of 4th Yale Workshop on Applications of Adaptive Systems Theory, Yale University, New Haven, Connecticut, pp. 379–388, 1985.
S. Kawamura, F. Miyazaki, and S. Arimoto, “Hybrid position/force control of manipulators based on learning method,” Proc. '85 Inter. Conf. on Advanced Robotics, Tokyo, Japan, pp. 235–242, 1985.
S. Kawamura, F. Miyazaki, and S. Arimoto, “Realization of robot motion based on a learning method,” IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-18, No. 1, pp 126–134, 1988.
S. Arimoto and F. Miyazaki, “Stability and robustness of PID feedback control for robot manipulators of sensory capability,” in “Robotic Research” The First International Symposium, by M. Brady & R.P. Paul, Eds., MIT Press, Cambridge, Massachusetts, pp. 783–799, 1984.
ibid., “Asympototic stability of feedback control laws for robot manipulators,” Proc. IFAC Symp. on Robot Control '85, Barcelona, Spain, pp. 447–452, 1985.
D.E. Koditschek, “Natural motion for robot arms,” Proc. of 23rd IEEE Conf. DEcision and Control, Las Vegas, NV, pp. 733–755, 1987.
P. Bondi, G. Casalino, and L. Gambardella, “On the iterative learning control theory for robotic manipulators,” IEEE J. of Robotics and Automation, Vol. 4, No. 1, pp. 14–22, 1988.
S. Arimoto, S. Kawamura, F. Miyazaki, “Convergence, stability, and robustness of learning control schemes for robot manipulator,” in M.J. Jamshidi, L.Y.S. Luh, and M. Shahinpoor (eds.), Recent Trends in Robotics: Modeling, Control, and Education, pp. 307–316, Elsevier Sciences Publishing Co., Inc., New York, 1986.
G. Heinzinger, D. Fenwick, B. Paden, and F. Miyazaki, “Robust learning control,” Proc. 28th IEEE Conf. Decision and Control, Tampa, Florida, Dec. 13–15, 1989.
S. Arimoto, “Robustness of learning control for robot manipulators,” Proc. of the 1990 IEEE International Conference on Robotics and Automation, pp. 1523–1528, Cincinnati, Ohio, May 13–18, 1990.
Y. Nanjo and S. Arimoto, “Experimental studies on robustness of a learning method with a forgetting factor for robotic motion control,” submitted to '91 ICAR, Pisa, Italy, 1990.
S. Arimoto, “Learning control theory for robotic motion,” International Journal of Adaptive Control and Signal Processing, Vol. 4, No. 6, pp. 543–564, 1990.
S. Arimoto, T. Naniwa, and H. Suzuki, “Robustness of P-type learning control with a forgetting factor for robotic motions,” Proc. of 29th IEEE Conference on Decision and Control, Honolulu, Hawaii, Dec. 5–7, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag
About this paper
Cite this paper
Arimoto, S. (1991). Passivity of robot dynamics implies capability of motor program learning. In: Canudas de Wit, C. (eds) Advanced Robot Control. Lecture Notes in Control and Information Sciences, vol 162. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0039265
Download citation
DOI: https://doi.org/10.1007/BFb0039265
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54169-1
Online ISBN: 978-3-540-47479-1
eBook Packages: Springer Book Archive