Abstract
Machine learning can be a most valuable tool for improving the flexibility and efficiency of robot applications. Many approaches to applying machine learning to robotics are known. Some approaches enhance the robot’s high-level processing, the planning capabilities. Other approaches enhance the low-level processing, the control of basic actions. In contrast, the approach presented in this paper uses machine learning for enhancing the link between the low-level representations of sensing and action and the high-level representation of planning. The aim is to facilitate the communication between the robot and the human user. A hierarchy of concepts is learned from route records of a mobile robot. Perception and action are combined at every level, i.e., the concepts are perceptually anchored. The relational learning algorithm GRDT has been developed which completely searches in a hypothesis space, that is restricted by rule schemata, which the user defines in terms of grammars.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Badler, N.I., Webber, B.L., Kalita, J. & Esakov, J. (1991). Animation from instructions. In N.I. Badler, B.A. Barsky, and D. Zeltzer, editors, Making Them Move: Mechanics, Control, and Animation of Articulated Figures, pages 51–93. Morgan Kaufmann, San Mateo, CA.
Baroglio, C., Giordana, A. & Piola, R. (1994). Learning control functions for industrial robots. In MLC-COLT ‘84 Robot Learning Workshop.
Bennett, S.W. (1989). Learning uncertainty tolerant plans through approximation in complex domains. Technical Report UILU-ENG-89–2204, The Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign.
Bergadano F. & Gunetti, D. (1993). An interactive system to learn functional logic programs. In Procs. 13th IJCAI, pages 1044–1049. Morgan Kaufmann.
Brooks, R.A. (1991). The role of learning in autonomous robots. In Procs. COLT 91, pages 5 - 10.
Cohen, W.W. (1994). Grammatically biased learning: Learning logic programs using an explicit antecedent description language. Artificial Intelligence, 68 (2): 243–302.
De Raedt, L. (1992). Interactive Theory Revision: an Inductive Logic Programming Approach. Academic Press.
DeJong, G. & Bennett, S. (1993). Permissive planning – a machine learning approach to linking internal and external worlds. In Procs. 11th AAAI, pages 508–513.
Dillmann, R. Kreuziger, J. & Wallner, F. (1993). PRIAMOS - an experimental platform for reflexive navigation. In Groen, Hirose, and Thorpe, editors, JAS-3: Intelligent Autonomous Systems, chapter 18, pages 174–183. IOS Press.
Doyle, R.J., Atkinson, D.J. & Doshi, R.S. (1986). Generating perception requests and expectations to verify the execution of plans. In Procs. of the AAAI, pages 81–88.
Dzeroski, S., Muggleton, S. & Russell, S. (1992). PAC-learnability of determinate logic programs. Procs. of 5th COLT, pages 128–135.
Gervasio, M. & DeJong, G. (1994). An incremental learning approach to completable planning. In W. Cohen and H. Hirsh, editors, Procs. 11th Int. Machine Learning Conf, pages 78–86.
Gil, Y. (1994). Learning by experimentation – incremental refinement of incomplete planning. In W. Cohen and H. Hirsh, editors, Procs. 11th Int. Machine Learning Conf:, pages 87–95.
Hamad, S. (1990). The symbol grounding problem. Physica D, 42: 335–346.
Helft, N. (1989). Induction as nonmonotonic inference. In Procs. of the 1st Int. Conf. on Knowledge Representation and Reasoning
Jelinek, F. (1976). Continuous speech recognition by statistical methods. Procs. of the IEEE, 64: 532–556.
Kaelbling, L.P. & Rosenschein, S.J. (1990). Action and planning in embedded agents. Robotics and Autonomous Systems, 6: 35–48.
Kietz, J. & Wrobel, S. (1992). Controlling the complexity of learning in logic through syntactic and task-oriented models. In Stephen Muggleton, editor, Inductive Logic Programming, chapter 16, pages 335–360. Academic Press, London.
Milldn, J. & Torras, C. (1992). A reinforcement connectionist approach to robot path finding in non-maze-like environments. Machine Learning, 8: 363–395.
Mitchell, T.M. & Thrun, S.B. (1993). Explanation-based neural network learning for robot control. In C. L. Giles, S. J. Hanson, and J. D. Cowan, editors, Advances in Neural Information Processing Systems 5, San Mateo, CA. Morgan Kaufmann.
Mitchell, T. (1990). Becoming increasingly reactive. In Procs. 8th AAAI, pages 1051–1058.
Morik, K., Wrobel, S., Kietz, J.-U. & Emde, W. (1993). Knowledge Acquisition and Machine Learning - Theory, Methods, and Applications. Academic Press, London.
Muggleton, S. & De Raedt, L. (1993). Inductive logic programming: Theory and methods. Technical Report CW 178, Department of Computing Science, K.U. Leuven.
Muggleton, S., editor. (1992). Inductive Logic Programming. Academic Press.
Nilsson, N.J. (1984). Shakey the robot. Technical Note 323, Artificial Intelligence Center, SRI International, Menlo Park, CA.
Plotkin, G.D. (1970). A note on inductive generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence, chapter 8, pages 153–163. American Elsevier.
Plotkin, G.D. (1971). Automatic methods of inductive inference. PhD thesis, University of Edinburgh. Quinlan, J.R. (1990). Learning logical definitions from relations. Machine Learning, 5 (3): 239–266.
Rieger, A. (1995a). Data preparation for inductive learning in robotics. In Working Notes of the IJCAI-Workshop on Data Engineering for Inductive Learning. also available as LS8-Report 19, University of Dortmund.
Rieger, A. (1995b). Inferring probabilistic automata from sensor data for robot navigation. In Procs. of the 3rd European Workshop on Learning Robots. also available as LS-8 Report 18, University of Dortmund.
Segre. A. (1988). Machine Learning of Robot Assembly Plans. Kluwer, Boston.
Shen, W.-M. (1993). Discovery as autonomous learning from the environment. Machine Learning, 12: 143–165.
Silverstein, G. & Pazzani, M.J. (1991). Relational clichés: Constraining constructive induction during relational learning. In L. Birnbaum and G. Collins, editors, Machine Learning: Procs. of the 8th Int. Workshop, pages 298–302, San Mateo, CA. Morgan Kaufmann.
Steels, L. (1993). Building agents out of autonomous behavior systems. In L. Steels and R. Brooks, editors, The ‘artificial life’ route to ‘artificial intelligence’ - Building situated embodied agents. Lawrence Erlbaum, New Haven.
Stopp, E., Gapp, K.-P., Herzog, G., Laengle, T. & Lueth, T. (1994). Utilizing spatial relations for natural language access to an autonomous mobile robot. In KI-94, - Procs. of the German Conference on AI, Berlin. Springer.
Tausend, B. (1993). Representing biases for inductive logic programming. In Pavel Brazdil, editor, Machine Learning-Procs. of ECML-93, Lecture Notes in Artificial Intelligence, pages 427–430, Berlin, Heidelberg, New York. Springer.
Wessel, S. (1995). Lernen qualitativer Merkmale aus numerischen Robotersensordaten. Master’s thesis, Universität Dortmund.
Wrobel, S. (1987). Higher-order concepts in a tractable knowledge representation. In K. Morik, editor, GWAI-87–11th German Workshop on Artificial Intelligence, pages 129–138, Berlin, New York, Tokyo. Springer Verlag.
Wrobel, S. (1991). Towards a model of grounded concept formation. In Procs. 12th IJCAI, pages 712–719, Los Altos, CA. Morgan Kaufman.
Zercher, K. (1992). Wissensintensives Lernen für zeitkritische technische Diagnoseaufgaben. infix, Sankt Augustin, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Kluwer Academic Publishers
About this chapter
Cite this chapter
Klingspor, V., Morik, K.J., Rieger, A.D. (1996). Learning Concepts from Sensor Data of a Mobile Robot. In: Franklin, J.A., Mitchell, T.M., Thrun, S. (eds) Recent Advances in Robot Learning. The Kluwer International Series in Engineering and Computer Science, vol 368. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-0471-5_8
Download citation
DOI: https://doi.org/10.1007/978-1-4613-0471-5_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-9745-8
Online ISBN: 978-1-4613-0471-5
eBook Packages: Springer Book Archive