Abstract
This paper presents a new approach to learning a compliance control law for robotic assembly tasks. In this approach, a task performance index of assembly operations is defined and the adaptive reinforcement learning algorithm [1] is applied for real-time learning. A simple box palletizing task is used as an example, where a robot is required to move a rectangular part to the corner of a box. In the experiment, the robot is initially provided with only predetermined velocity command to follow the nominal trajectory. However, at each attempt, the box is randomly located and the part is randomly oriented within the grasp of the end-effector. Therefore, compliant motion control is required to guide the part to the corner of the box while avoiding excessive reaction forces caused by the collision with a wall. After repeating failures in performing the task, the robot can successfully learn force feedback gains to modify its nominal motion. Our results show that the new learning method can be used to learn a compliance control law effectively.
Preview
Unable to display preview. Download preview PDF.
References
B.-H. Yang and H. Asada, “Adaptive Reinforcement Learning and Its Application to Robot Control”, DSC-Vol. 49, Advances in Robotics, Mechatronics, and Haptic Interfaces, ASME Winter Annual Meeting, 1993
D. E. Whitney, “Force Feedback Control of Manipulator Fine Motions”, ASME J. of DSMC, vol. 99, no. 2, pp 91–97, 1977
J. K. Salisbury, “Active Stiffness Control of a Manipulator in Cartesian Coordinates”, Proc. of the 19th IEEE Conf. on Decision and Control, pp. 95–100, 1980
M. T. Mason, “Compliance and Force Control for Computer Controlled Manipulators”, IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC-11, no. 6, pp. 418–432, 1981
M. Raibert and J. Craig, “Hybrid Position/Force Control of Manipulators”, ASME J. of DSMC, vol. 102, no. 2, pp. 126–133, 1981
N. Hogan, “Impedance Control: An Approach to Manipulation: Part I–III”, ASME J. of DSMC, vol. 107-1, pp. 1–23, 1985
S. Hirai and K. Iwata, “Derivation of Damping Control Parameters Based on Geometric Model”, Proc. of IEEE Int. Conf. on Robotic and Automation, vol. 2, pp. 87–92, 1993
M. A. Peshkin, “Programmed Compliance for Force Corrective Assembly”, IEEE Trans. on Robotics and Automation, Vol. 6, No. 4, August, 1990
H. Asada, “Teaching and Learning of Compliance Using Neural Nets: Representation and Generation of Nonlinear Compliance”, Proc. of IEEE Int. Conf. on Robotics and Automation, 1990
A. G. Barto, R. S. Sutton and C. W. Anderson, “Neuronlike Elements That Can Solve Difficult Learning Problems”, IEEE Trans. of Systems, Man, and Cybernetics, vol. 13(5), p.p. 835–846, 1983
V. Gullapalli, “A Stochastic Reinforcement Learning Algorithm for Learning Real-Valued Functions”, Neural Networks, Vol. 3, pp. 671–692, 1990
R. J. Williams, “Simple Statistical Gradient-Following Algorithm for Connectionist Reinforcement Learning”, Machine Learning, 8, 1992
P. J. Werbos, “Generalization of Back Propagation with Application to a Recurrent Gas Market Model”, Neural Networks, 1, 1988
M. I. Jordan and D. E. Rumelhart, “Forward Models: Supervised Learning with a Distal Teacher”, Cognitive Science, 16, 1992
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag London Limited
About this paper
Cite this paper
Yang, BH., Asada, H. (1994). Reinforcement learning of assembly robots. In: Yoshikawa, T., Miyazaki, F. (eds) Experimental Robotics III. Lecture Notes in Control and Information Sciences, vol 200. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0027599
Download citation
DOI: https://doi.org/10.1007/BFb0027599
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-19905-2
Online ISBN: 978-3-540-39355-9
eBook Packages: Springer Book Archive