Abstract
It is difficult to represent the nonlinear characteristics in the dynamics of robot manipulators by means of a mathematical model. An alternative approach of using a neural network to learn the parametric and unstructured uncertainties in robot manipulators is proposed. It is then embedded in the structure of a joint torque perturbation observer to compensate for uncertainties in the robot dynamic model. As the result, an accurate estimate of the joint reaction torque against the environment can be deduced. The approach is applied to monitor the insertion force during electronic components assembly using a SCARA robot. A true teaching signal of neural network for learning the model uncertainties is obtained. Furthermore, a special motion test is conducted to generate the required training data set. After learning, the neural network is capable of reproducing the training data. The generalizing ability of the network enables it to output the correct compensation signal for a trajectory which it has not been trained. With the proposed technique, it is possible to verify the success of component insertion in real time and avoid causing damages to the electronic components.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Armstrong, B.: Friction: Experimental determination, modeling and compensation, inProc. IEEE Int. Conf. on Robot. and Autom., Philadelphia, 1988, pp. 1422–1427.
Bavarian, B.: Introduction to neural networks for intelligent control,IEEE Control Systems Mag., April, 3–7, 1988.
Canudas de Wit, C., Noel, P., Aubin, A. and Brogliato, B.: Adaptive friction compensation in robot manipulators: Low velocities,Int. J. Robot. Res. 10(3) (1991), 189–199.
Chan, S. P., Lee, C. Y. and Mital, D. P.: A disturbance observer for robotic assembly of odd form electronic components,Proc. 19th Annual Meeting of IEEE Industrial Electronics Society, IECON'93, Hawaii, November 1993.
Cooper, D. J., Megan, L. and Hinde Jr., R. F.: Disturbance pattern classification and neuro-adaptive control,IEEE Control Systems (April 1992), 42–48.
Craig, J. J.:Adaptive Control of Mechanical Manipulators, Addison-Wesley, Reading, MA, 1988.
Fu, K. S., Gonzalez, R. C. and Lee, C. S. G.:Robotics — Control, Sensing, Vision and Intelligence, McGraw-Hill, New York, 1987.
Gomes, S. C. P. and Chretien, J. P.: Dynamic modelling and friction compensated control of a robot manipulator joint, inProc. 1992 IEEE Int. Conf. on Robot. and Autom., Nice, France, 1992, pp. 1429–1435.
Held, V. and Maron, C.: Estimation of friction characteristics, inertial and coupling coefficients in robotic joints based on current and speed measurements, inProc. IFAC Robot Control, SYROCO'88, Karlsruhe, 1988, pp. 208–212.
Horne, B., Jamshidi, M. and Vadiee, N.: Neural networks in robotics: A survey,J. Intell. Robot. Systems 3 (1990), 51–66.
Hunt, K. J., Sbarbaro, D., Zbikowski, R. and Gawthrop, P. J.: Neural networks for control systems — A survey,Automatica 28(6) (1992), 1083–1112.
Ishiguro, A., Furuhashi, T., Okuma, S. and Uchikawa, Y.: A neural network compensator for uncertainties of robotics manipulators,IEEE Trans. Ind. Electronics 39(6) (1992), 565–569.
Khosla, P. K.: Estimation of robotic dynamics parameters: Theory and application,Int. J. Robot. Autom. 3(1) (1988), 35–41.
Leahy Jr., M. B., Johnson, M. A. and Rogers, S. K.: Neural network payload estimation for adaptive robot control,IEEE Trans. Neural Network 2(1) (1991), 93–99.
Lee, J.: Apply force/torque sensors to robotic applications,Robotics 3 (1987), 189–194.
Mailisto, J., Sorvari, J. and Koivo, H. N.: Identification of the first joint of the Puma Robot, inProc. Int. Conf. on Ind. Elect. Contr. and Instrum., IECON'91, Kobe, 1991, pp. 1095–1099.
Naghdy, F., Luk, B. and Hoade, K.: Stochastic force control in a robotic arm,Proc. IFAC Robot Control, SYROCO'88, Karlsruhe, 1988, pp. 145–150.
Ohishi, K. Miyazaki, M., Fujita, M. and Ogino, Y.: Force control without force sensor based on mixed sensivityH ∞ design method, inProc. IEEE Int. Conf. Robot. and Autom., Nice, 1992, pp. 1356–1361.
Rumelhart, D., Hinton, G. E. and Williams, R. L.: Learning internal representation by error propagation, in D. E. Rumelhart and J. L. McClelland (eds),Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1:Foundations, MIT Press, MA, 1986.
Schilling, R. J.:Fundamentals of Robotics: Analysis and Control, Prentice-Hall, 1990.
Schroer, B. J. and Stafford, E. F.: Issues in using robots for electronics assembly,Robotics 2 (1986), 225–235.
Slotine, J. J. E. and Li, W.: Adaptive manipulator control: A case study,IEEE Trans. Automat. Contr. AC-33(11) (1988), 995–1003.
Stauffer, R. N.: Robots in electronics assembly,Robotics Today (December 1984), 61–67.
Tsia, T. C.: A new technique for robust control of servo systems,IEEE Trans. Ind. Elect. 36(1) (1989), 1–7.
Tung, E. D., Anwar, G. and Tomizuka, M.: Low velocity friction compensation and feedforward solution based on repetitive control,J. Dynamic Systems, Measurement, and Control 115 (1993), 279–284.
Vos, D. W., Valavani, L. and von Flotow, A. H.: Intelligent model reference nonlinear friction compensation using neural networks and Lyapunov based adaptive control, inProc. 1991 IEEE Int. Symp. Intell. Control, Arlington, VA, (1991), pp. 417–422.
Yu, F., Murakami, T. and Ohnishi, K.: Sensorless force control of direct drive manipulator, inProc. IEEE Int. Symp. Ind. Elect., Xian, 1992, pp. 311–315.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chan, S.P. A neural network compensator for uncertainties in robotic assembly. J Intell Robot Syst 13, 127–141 (1995). https://doi.org/10.1007/BF01254848
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01254848