Abstract
This paper explores a stepwise learning approach based on a system's decomposition into functional subsystems. Two case studies are examined: a visually guided robot that learns to track a maneuvering object, and a robot that learns to use the information from a force sensor in order to put a peg into a hole. These two applications show the features and advantages of the proposed approach: i) the subsystems naturally arise as functional components of the hardware and software; ii) these subsystems are building blocks of the robot behavior and can be combined in several ways for performing various tasks; iii) this decomposition makes it easier to check the performances and detect the cause of a malfunction; iv) only those subsystems for which a satisfactory solution is not available need to be learned; v) the strategy proposed for coordinating the optimization of all subsystems ensures an improvement at the task-level; vi) the overall system's behavior is significantly improved by the stepwise learning approach.
Similar content being viewed by others
References
Powell, B.: The ‘spider’ and the yen, Newsweek 7 (August 1995), 46.
Kreuziger, J.: Application of machine learning to robotics - An analysis, in: 2nd Int. Conf. on Automation, Robotics and Computer Vision, 1992, pp. RO:15.4.1–RO:15.4.5.
Connell, J. H. and Mahadevan, S. (eds): Robot Learning, Kluwer Academic Publishers, Dordrecht, 1993.
Special issue on learning robots, Stud. Inform. Control 5(3) (1996).
Monostori, L., Markus, A., Van Brussel, H., and Westkämper, E.: Machine learning approaches to manufacturing, Ann. of CIRP 45(2) (1996).
Brooks, R. A. and Mataric, M. J.: Real robots, real learning problems, in: J. H. Connell and S. Mahadevan (eds), Robot Learning, Kluwer Academic Publishers, Dordrecht, 1993.
Nuttin, M. and Van Brussel, H.: Learning assembly operations: A case study with real-world objects, Stud. Inform. Control 5(3) (1996), 205–221.
Bernstein, N.: The Coordination and Regulation of Movements, Pergamon, Oxford, 1967.
Connell, J. H. and Mahadevan, S.: Rapid task learning for real robots, in: J. H. Connell and S. Mahadevan (eds), Robot Learning, Kluwer Academic Publishers, Dordrecht, 1993.
Brooks, R. A.: A robust layered control system for a mobile robot, IEEE J. Robotics Automat. 2(1) (1986).
Mataric, M. J.: Learning in multi-robot systems, in: G. Weiss and S. Sen (eds), Adaptation and Learning in Multi-Agent Systems, Vol. 1042, Springer, Berlin, 1996, pp. 152–163.
Floreano, D. and Mondada, F.: Evolution of homing navigation in a real mobile robot, IEEE Trans. Systems Man Cybernet. 26(3) (1996), 396–407.
Chatila, R.: Deliberation and reactivity in autonomous mobile robots, Robotics and Autonom. Systems 16 (1995), 197–211.
Van Brussel, H.: Holonic manufacturing systems - the vision matching the problem, in: Proc. of the 1st European Conf. on Holonic Manufacturing Systems, Hannover, Germany, 1994.
Abraham, R. and Marsden, J. E.: Foundation of Mechanics, Benjamin/Cummings, 1978.
Lan, C.: Neural Networks, Theoretical Foundations and Analysis, 1990.
Driankov, D., Hellendoorn, H., and Reinfrank, H.: An Introduction to Fuzzy Control, Springer, Berlin, 1993, 186–194.
Zadeh, L. A.: Fuzzy logic, neural networks and soft computing, Commun. ACM 37(3) (1994), 77–84.
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J.: Classification and Regression Trees, Wadsworth Statistics/Probability Series, Wadsworth, Belmont, CA, 1984.
Bryson, A. E. and Ho, Y. C.: Applied Optimal Control, Halsted Press, New York, 1975.
Bischop, C. M.: Neural Networks for Pattern Recognition, Oxford Univ. Press, Oxford, 1995.
An, C. H., Atkenson, C. G., and Hollerbach, J. M.: Model-based Control of a Robot Manipulator, MIT Press, Cambridge, MA, 1988.
Slotine, J.-J. E. and Li, W.: Applied Nonlinear Control, Prentice-Hall, Englewood Cliffs, NJ, 1991.
Rumelhart, D. E., McClelland, J. L., and the PDP Research Group, Parallel Distributed Processing, MIT Press, Cambridge, MA, 1986.
Goldberg, D. E.: Genetic Algorithms in Search Optimization and Machine Learning, Addison-Wesley, Reading, MA, 1989.
Aboaf, E. W., Drucker, S. M., and Atkeson, C. M.: Task-level robot learning: Juggling a tennis ball more accurately, in: IEEE Int. Conf. on Robotics and Automation, 1989, pp. 1290–1295.
Wen, J.: Hybrid approach of neural networks with knowledge-based explicit models, PhD Thesis, ETH, Zuerich, 1995.
Ferrigno, G. and Pedotti, A.: ELITE: A digital dedicated hardware system for movement analysis via real-time TV signal processing, IEEE Trans. Biomedical Engineering BME-32(11) (1985), 943–950.
Papanikolopoulos, N. P. and Khosla, P. K.: Adaptive robotic visual tracking: Theory and experiments, IEEE Trans. Automat. Control 38(3) (1993), 429–445.
Burdet, E. and Luthiger, J.: Learning the coordination of robots motion with vision processes, subm. to IEEE Trans. Robotics Automat., (1998).
Burdet, E. and Koeppe, R.: A method for expecting the features of objects and enabling realtime vision processing, in: Int. Conf. on Intelligent Robots and Systems, 1996.
Kohonen, T.: Self-Organization and Associative Memory, Springer, Berlin, 1984.
Ritter, H., Martinez, T., and Schulten, K.: Neuronale Netze, Addison-Wesley, Reading, MA, 1991.
Bennett, D. J., Geiger, D., and Hollerbach, J. M.: Autonomous robot calibration for hand-eye coordination, Internat. J. of Robotics Res. 10(5) (1991), 550–559.
Burdet, E.: Algorithms of human motor control and their implementation in robotics, PhD Thesis, ETH, Zuerich, 1996.
Singer, R. A.: Estimating optimal tracking filter performance for manned maneuvering targets, IEEE Trans. Aerospace Electronic Systems AES-6(4) (1970), 473–483.
Burdet, E. and Mueller, J.: A robot learning reaching motions (video), in: IEEE Int. Conf. on Robotics and Automation, 1996.
Hoff, B. R.: A computational description of the organization of human reaching and prehension, PhD Thesis, University of Southern California, 1992.
Bobrow, J. E.: Optimal robot path planning using the minimum-time criterion, IEEE J. of Robotics Automat. 4(4) (1988), 443–451.
Timcenko, A. and Allen, P. K.: Modeling dynamic uncertainty in robot motions, in: IEEE Int. Conf. on Robotics and Automation, Vol. 3, 1993, pp. 531–536.
Burdet, E. and Codourey, A.: Evaluating nonlinear adaptive control experimentally, in: IEEE Control Systems Magazine (April 1998), 39–47.
Allen, P. K., Timcenko, A., Yoshimi, B., and Michelman, P.: Automated tracking and grasping of a moving object with a robotic hand-eye system, IEEE Trans. Robotics Automat. 9(2) (1993),152–165.
Buttazo, G. C., Allotta, B., and Fanizza, P.: Mousebuster: A robot for real-time catching, IEEE Robotics and Automation Magazine, (February 1994), pp. 49–55.
De Schutter, J. and Van Brussel, H.: Compliant robot motion I: A formalism for specifying compliant motion tasks, Internat. J. of Robotics Res. 7(4) (1988), 3–17.
De Schutter, J. and Van Brussel, H.: Compliant robot motion II: A control approach based on external control loops, Internat. J. of Robotics Res. 7(4) (1988), 18–33.
Asada, H.: Teaching and learning of compliance using neural nets: Representation and generation of nonlinear compliance, in: Proc. of the 1990 IEEE Int. Conf. on Robotics and Automation, 1990, pp. 1237–1244.
Nuttin, M. and Van Brussel, H.: Learning the peg-into-hole assembly operation with a connectionist reinforcement technique, Computers in Industry 33(1) (1997), 101–109.
Witvrouw, W., Van De Poel, P., Bruyninckx, H., and De Schutter, J.: ROSI: A task specification and simulation tool for force sensor based robot control, in: 24th Int. Symp. on Industrial Robots, November 1993.
Witvrouw, W.: Development of experiments for sensor controlled robot tasks, PhD Thesis, Katholieke Universiteit Leuven, Department of Mechanical Engineering, Division PMA, Belgium, 1996.
Williams, R. J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning, Machine Learning 8 (1992), 229–256.
Fahlman, S. E.: An empirical study of learning speed in back propagation networks, Technical Report CMU-CS-88-162, Carnegie-Mellon University, 1988.
Wirth, N.: Algorithms and Data Structures, Prentice-Hall, Englewood Cliffs, NJ, 1986.
Suárez, R., Basañez, L., Nuttin, M., Van Brussel, H., and Rosell, J.: Learning versus analytical approach to contact estimation in assembly tasks with robots, in: Proc. of 7th ICAR, 1995, pp. 769–775.
Tschichhold-Guerman, N. N.: The neural network model RuleNet and its application to mobile robot navigation, Fuzzy Sets and Systems 85 (1997), 287–303.
Baroglio, C., Giordana, A., Kaiser, M., Nuttin, M., and Piola, R.: Learning controllers for industrial robots, in: J. A. Franklin, T. M. Mitchell, and S. Thrun (eds), Recent Advances in Robot Learning, Kluwer Academic Publishers, Dordrecht, 1996, pp. 105–133.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Burdet, E., Nuttin, M. Learning Complex Tasks Using a Stepwise Approach. Journal of Intelligent and Robotic Systems 24, 43–68 (1999). https://doi.org/10.1023/A:1008058131402
Issue Date:
DOI: https://doi.org/10.1023/A:1008058131402