Abstract
One of the most significant cost factors in robotics applications is the design and development of real-time robot control software. Control theory helps when linear controllers have to be developed, but it doesn't sufficiently support the generation of non-linear controllers, although in many cases (such as in compliance control), nonlinear control is essential for achieving high performance. This paper discusses how Machine Learning has been applied to the design of (non-)linear controllers. Several alternative function approximators, including Multilayer Perceptrons (MLP), Radial Basis Function Networks (RBFNs), and Fuzzy Controllers are analyzed and compared, leading to the definition of two major families: Open Field Function Approximators and Locally Receptive Field Function Approximators. It is shown that RBFNs and Fuzzy Controllers bear strong similarities, and that both have a symbolic interpretation. This characteristic allows for applying both symbolic and statistic learning algorithms to synthesize the network layout from a set of examples and, possibly, some background knowledge. Three integrated learning algorithms, two of which are original, are described and evaluated on experimental test cases. The first test case is provided by a robot KUKA IR-361 engaged into the peg-into-hole task, whereas the second is represented by a classical prediction task on the Mackey-Glass time series. From the experimental comparison, it appears that both Fuzzy Controllers and RBFNs synthesised from examples are excellent approximators, and that, in practice, they can be even more accurate than MLPs.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Alpaydin, E. (1991). GAL: Networks that grow when they learn and shrink when they forget. Technical Report TR–91–032, International Computer Science Institute, Berkeley, USA.
Asada, H. (1990). Teaching and learning of compliance using neural nets: Representation and generation of nonlinear compliance. In Proceedings of the 1990 IEEE International Conference on Robotics and Automation, pages 1237–1244.
Barto, A., Sutton, R., & Watkins, C. (1990). Sequential decision problems and neural networks. In Advances in neural information processing system, volume 2. Morgan Kauffman, San mateo, Ca.
Barto, A. G., Sutton, R. S., & Anderson, C. W. (1983). Neuronlike elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man and Cybernetics, pages 835–846.
Berenji, H. (1990). Machine learning in fuzzy control. In International Conference on Fuzzy Logic & Neural Networks, pages 231–234, Iizuka, Fukuoka, Japan.
Berenji, H. (1992). Fuzzy logic controllers. In Yager, R. and Zadeh, L., editors, An Introduction to Fuzzy Logic Applications in Intelligent Systems. Kluwer Academic Publishers.
Berenji, H. & Khedkar, P. (1992). Learning and tuning fuzzy controllers through reinforcements. IEEE Transactions on neural networks, 3(5):724–740.
Bergadano, F. & Giordana, A. (1988). A knowledge intensive approach to concept induction. In Proceedings of the 5th International Conference on Machine Learning, pages 305–317, Ann Arbor, MI. Morgan Kauffman.
Bergadano, F., Giordana, A., & Saitta, L. (1988). Learning concepts in noisy environment. IEEE Transaction on Pattern Analysis and Machine Intelligence, pages 555–578.
Berthold, M. (1994). A time delay radial basis function network for phoneme recognition. In IEEE International Conference on Neural Networks, Orlando, Florida.
Bonissone, P. & Chiang, K. (1993). Fuzzy logic controllers: from development to deployment. In IEEE International Conference on Neural Networks, volume 2, San Francisco, CA.
Botta, M. & Giordana, A. (1993). SMART+: A multi-strategy learning tool. In IJCAI-93, Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, volume 2, Chambéry, France.
Breiman, L., Friedman, J., Ohlsen, R., & Stone, C. (1984). Classification And Regression Trees. Wadsworth & Brooks, Pacific Grove, CA.
Cramer, H. (1974). Mathematical Methods of Statistics. Princeton University Press.
Crowder, R. (1990). Predicting the mackey-glass time series with cascade-correlation learning. In D. Touretzky, G. H. and T. Sejnovsky, editors, Proceedings of the 1990 Connectionist Models Summer School, pages 117–123. Carnegie Mellon University.
De Schutter, J. & Van Brussel, H. (1988). Compliant robot motion II, a control approach based on external control loops. The International Journal of Robotics Research, 7(4).
De Schutter, J., Witvrouw, W., Van De Poel, P., & Bruyninckx, H. (1993). Rosi: a task specification and simulation tool for force sensor based robot control. In 24th International Symposium on Industrial Robots.
del R. Millán, J. (1994). Learning efficient reactive behavioral sequences from basic reflexes in a goal-directed autonomous robot. In Proceedings of the third International Conference on Simulation of Adaptive Behavior.
del R. Millán, J. & Torras, C. (1992). A reinforcement connectionist approach to robot path finding in non-maze-like environments. Machine Learning, 8:363–395.
ERA (1995). Neural Networks: Producing Dependable Systems, Solihull, West Midlands, UK. ERA Technology.
Fahlmann, S. E. & Lebiere, C. (1989). The cascade-correlation learning architecture. In Advances in Neural Information Processing Systems 2 (NIPS-2), Denver, Colorado.
Fritzke, B. (1993). Growing cell structure: A self-organizing network for unsupervised and supervised learning. Technical Report TR–93–026, International Computer Science Institute.
Gullapalli, V. (1990). A stochastic reinforcement learning algorithm for learning real valued functions. Neural Networks, 3:671–692.
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feed-forward networks are universal approximators. Neural Networks, 2:359–366.
Jang, J. (1993). ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man and Cybernetics, SMC-23(3):665–687.
Jones, R., Lee, Y., Barnes, C., Flake, G., Lee, K., & Lewis, P. (1990). Function approximation and time series prediction with neural networks. In Proceedings of IEEE International Joint Conference on Neural Networks, pages I–649–665.
Kaiser, M., Camarinha-Matos, L., Giordana, A., Klingspor, V., del R. Millàn, J., Nuttin, M., & Suarez, R. (1994). Robot learning-three case studies in robotics and machine learning. In Proceedings of the IVAR '94, Leuven, Belgium.
Kaiser, M., Friedrich, H., & Dillmann, R. (1995a). Obtaining good performance from a bad teacher. In International Conference on Machine Learning, Workshop on Programming by Demonstration, Tahoe City, California.
Kaiser, M., Klingspor, V., del R. Millàn, J., Accame, M., Wallner, F., & Dillmann, R. (1995b). Using machine learning techniques in real-world mobile robots. IEEE Expert.
Kaiser, M. & Kreuziger, J. (1994). Integration of symbolic and connectionist processing to ease robot programming and control. In ECAI'94 Workshop on Combining Symbolic and Connectionist Processing, pages 20–29.
Kaiser, M., Retey, A., & Dillmann, R. (1995c). Robot skill acquisition via human demonstration. In Proceedings of the International Conference on Advanced Robotics (ICAR '95).
Lapedes, A. & Farber, R. (1987). Nonlinear signal processing using neural networks: Prediction and system modeling. Technical Report LA-UR–87–2662, Los Alamos National Laboratory.
Mason, M. (1981). Compliance and force control for computer controlled manipulators. IEEE Transactions on Systems, Man and Cybernetics, 11.
Miller, W. T., Sutton, R. S., & Werbos, P. J. (1990). Neural networks for control. The MIT Press.
Moody, J. (1989). Fast learning in multi-resolution hierarchies. In Touretzky, D., editor, Advances in Neural Information Processing. Morgan Kaufmann.
Moody, J. & Darken, C. (1988). Learning with localized receptive fields. In Sejnowski, T., Touretzky, D., and Hinton, G., editors, Connectionist Models Summer School, Carnegie Mellon University.
Moody, J. & Darken, C. (1989). Fast learning in networks of locally tuned units. Neural Computations, 1(2):281–294.
Musavi, M., Ahmed, W., Chan, K., Faris, K., & Hummels, D. (1992). On the training of radial basis function classifiers. Neural Networks, 5:595–603.
Nuttin, M., Van Brussel, H., Baroglio, C., & Piola, R. (1994). Fuzzy controller synthesis in robotic assembly: Procedure and experiments. In FUZZ-IEEE-94: Third IEEE International Conference on Fuzzy Systems, World Congress on Computational Intelligence.
Nuttin, M., Van Brussel, H., Peirs, J., Soembagijo, A. S., & Sonck, S. (1995). Learning the peg-into-hole assembly operation with a connectionist reinforcement technique. In Second International CIRP Workshop on Learning in Intelligent Manufacturing Systems, pages 335–357, Budapest, Hungary.
Park, J. & Sandberg, W. (1993). Universal approximation using radial-basis functions. Neural Computation, 5.
Pazzani, M. & Kibler, D. (1992). The utility of knowledge in inductive learning. Machine Learning, 9:57–94.
Peng, J. & Williams, R. (1992). Efficient learning and planning within the Dyna framework. In Proceedings of the Second International Conference on Simulation of Adaptive Behavior, Honolulu, HI.
Poggio, T. & Girosi, F. (1990). Networks for approximation and learning. Proceedings of the IEEE, 78(9):1481–1497.
Quinlan, J. (1993). Combining instance-based and model-based learning. In Proceedings of the 10 th machine learning conference, pages 236–243, Amherst, MA.
Quinlan, R. (1990). Learning logical definitions from relations. Machine Learning, 5:239–266.
Rumelhart, D., Hinton, G., & Williams, R. (1985). Learning internal representations by error propagation. Technical Report 8506, Institute for Cognitive Science, La Jolla: University of California, San Diego.
Rumelhart, D. E. & McClelland, J. L. (1986). Parallel Distributed Processing: Explorations in the Microstructure of Coginition, Parts I &II. MIT Press, Cambridge, Massachusetts.
Sammut, C., Hurst, S., Kedzier, D., & Michie, D. (1992). Learning to fly. In Sleeman, D. and Edwards, P., editors, Machine Learning-Proceedings of the Ninth International Workshop (ML92), pages 385–393. Morgan Kaufmann.
Sanger, T. (1991). A tree-structured adaptive network for function approximate in high-dimensional spaces. IEEE Transactions on Neural Networks, 2(2):285–293.
Specht, D. (1988). Probabilistic neural networks for classification mapping, or associative memory. In IEEE International Conference on Neural Networks, volume 1, pages 525–532.
Specht, D. (1990). Probabilistic neural networks. Neural Networks, 3:109–118.
Sutton, R. & Barto, A. (1987). A temporal-difference method of classical conditioning. In proceedings of the Ninth Annual Conference of the Cognitive Science Society, pages 355–378, Seattle, WA. Lawrence Erlbaum.
Towell, G. & Shavlik, J. (1993). Extracting refined rules from knowledge-based neural networks. Machine Learning, 13(1):71–101.
Towell, G., Shavlik, J., & Noordwier, M. (1990). Refinement of approximate domain theories by knowledge-based neural networks. In Proceedings of the 8th National Conference on Artificial Intelligence AAAI'90, pages 861–866.
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on acoustics, speech and signal processing, pages 328–339.
Wettschereck, D. & Dietterich, T. (1991). Improving the performance of radial basis function networks by learning center locations. In Advances in Neural Information Processing Systems 4 (NIPS-4).
Weymaere, N. & Martens, J. (1991). A fast and robust learning algorithm for feedforward neural networks. Neural Networks, 4.
Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, pages 229–256.
Wilpon, J. & Rabiner, L. (1985). A modified k-means clustering algorithm for use in isolated work recognition. IEEE transactions on acoustics, speech and signal processing, ASSP-33:587–594.
Yih, J. & Shieh, J. (1992). On the development of a fuzzy model-based controller for robotic manipulators. In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, Raleigh, NC.
Zadeh, L. (1992). Knowledge representation in fuzzy logic. In Yager, R. and Zadeh, L., editors, An Introduction to Fuzzy Logic Applications in Intelligent Systems. Kluwer Academic Publishers.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Baroglio, C., Giordana, A., Piola, R. et al. Learning Controllers for Industrial Robots. Machine Learning 23, 221–249 (1996). https://doi.org/10.1023/A:1018228822027
Issue Date:
DOI: https://doi.org/10.1023/A:1018228822027