Abstract
This paper is a survey of some recentconnectionist approaches to the design and developmentof behaviour-based mobile robots. The research isanalysed in terms of principal connectionist learningmethods and neurological modeling trends. Possibleadvantages over conventionally programmed methods areconsidered and the connectionist achievements to dateare assessed. A realistic view is taken of theprospects for medium term progress and someobservations are made concerning the direction thismight profitably take.
Similar content being viewed by others
References
Ackley, D. H. & Littman, M. L. (1990). Generalization and Scaling in Reinforcement Learning. In Touretsky, D. S. (ed.) Advances in Neural Information Processing Systems 2, 550–557. Morgan Kaufman: San Mateo, CA.
Almassy, N. & Verschure, P. (1992). Optimizing Self-Organizing Control Architectures with Genetic Algorithms: The Interaction Between Natural Selection and Ontogenesis. Proceedings of the Second Conference on Parallel Problem Solving from Nature, 451–460. Elsevier.
Barto, A. G. (1990a). Connectionist Learning for Control: An Overview. In Miller, W. T., Sutton, R. S. & Werbos, P. J. (eds.) Neural Networks for Control. MIT Press: Cambridge, MA.
Barto, A. G. (1990b). Some Learning Tasks from a Control Perspective. COINS Technical Report 90122, Computer and Information Science Department: University of Massachusetts.
Beer, D., Chiel, H. J. & Sterling, L. S. (1990). A Biological Perspective on Autonomous Agent Design. In Maes, P. (ed.) Designing Autonomous Agents, 169–186. MIT Press.
Brooks, R. A. (1986). A Robust Layered Control System for a Mobile Robot. IEEE Journal of Robotics and Automation: 14–23.
Brooks, R. A. (1991). Intelligence Without Representation. Artificial Intelligence 47: 139–159.
Brooks, R. A. (1994). Coherent Behaviour from Many Adaptive Processes. In From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behavior, 22–29. MIT Press.
Brooks, R. A. & Mataric, M. J. (1993). Real Robots, Real Learning Problems. In Connell, J. H. & Mahadevan, S. (eds.) Robot Learning, 193–213. Kluwer Academic Publishers.
Buhlmeier, A. (1994). Conditioning and Robot Control. Proceedings of the International Conference on Artificial Neural Networks, 1283–1286. Springer-Verlag.
Chandrasekeran, B. & Josephson, S. G. (1993). Architecture of Intelligence: The Problems and Current Approaches to Solutions. Current Science 64(6).
Chesters, W. & Hayes, G. (1994). Connectionist Environment Modelling in a Real Robot. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 189–187. MIT Press.
Connell, J. H. & Mahadevan, S. (1993). Introduction to Robot Learning. In Connell J. H. & Mahadevan, S. (eds.) Robot Learning, 1–17. Kluwer Academic Publishers.
Copeland, J. (1993). Artificial Intelligence: A Philosophical Introduction. Blackwell: Oxford.
Elman, J. L. (1990). Finding Structures in Time. Cognitive Science 14: 179–212.
Fagg, A. H., Lotspeich, D. & Beckey, G. A. (1994). A Reinforcement Learning Approach to Reactive Control Policy Design for Autonomous Robots and Automation. Proceedings of the IEEE Conference on Robotics.
Franchi, P., Morasso & Vercelli, G. (1994). A Hybrid Self-Organizing Architecture for Autonomous Mobile Robots. Proceedings of the International Conference on Artificial Neural Networks, 1283–1286.
Gaussier, P. & Zrehen, S. (1994). A Topological Neural Map for On-Line Learning. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 275–281. MIT Press.
Hallam, B., Halperin, J. R. P. & Hallam, J. C. T. (1994). An Ethological Model of Learning and Motivation for Implementation in Mobile Robots, Research Paper 629. Department of AI: Edinburgh University.
Hartson, C. (1990). Application of Neural Networks to Robotics. In Maren, A., Hartson C. & Pap, R. (eds.) Handbook of Neural Computing Applications, 381–391. Academic Press.
Harvey, I., Husbands, P. & Cliff, D. (1993). Issues in Evolutionary Robotics. From Animals to Animats 2: Proceedings of the Second International Conference on the Simulation of Adaptive Behaviour, 364–373. MIT Press.
Haykin, S. (1994). Neural Networks: A Comprehensive Introduction. Macmillan, New York.
Jordon, M. I. & Jacobs, R. A. (1992). Hierarchies of Adaptive Experts. In Moody, J. E., Hanson, S. J. & Lippmann, R. P. (eds.) Advances in Neural Information Processing Systems 4, 985–992. Morgan Kaufmann.
Khatib, O. (1986). Real-Time Obstacle Avoidance for Manipulators and Mobile Robots. International Journal of Robotics Research 5(1): 90–98.
Kohonen, T. (1982). Self-Organized Formation of Topographically Correct Feature Maps. Biological Cybernetics 43: 59–69.
Lin, L. J. (1991). Programming Robots Using Reinforcement Learning and Teaching. Proceedings of AAAI91: 781–786.
Lin, L. J. (1993). Hierarchical Learning of Robot Skills by Reinforcement. Proceedings of IEEE Conference on Neural Networks: 181–187.
MacFarland, D. & Bösser, T. (1993). Intelligent Behaviour in Animals and Robots. MIT Press.
Maes, P. (1990). Situated Agents Can Have Goals. Robotics and Autonomous Systems 6: 49–70.
Maes, P. (1995). Modeling Adaptive Autonomous Agents. In Langton, C. G. (ed.) Artificial Life: An Overview, 135–162. MIT Press.
Maes, P. & Brooks, R. A. (1990). Learning to Coordinate Behaviours. In Proceedings of AAAI90, 796–802.
Mahadevan, J. H. & Connell, J. (1992). Automatic Programming of Behaviour-Based Robots Using Reinforcement Learning. Artificial Intelligence 55: 311–365.
Mataric, M. J. (1990). A Distributed Model for Mobile Robot Environment Learning and Navigation. Technical Report 1228, AI Lab, MIT.
Meeden, L., Mcgraw, G. & Blank, D. (1993). Emergent Control and Planning in an Autonomous Vehicle. Proceedings of the Fifteenth Annual Meeting of the Cognitive Science Society.
Millan, J. & Del R. (1994). Learning Efficient Reactive Behavioural Sequences from Basic Reflexes.
Nehmzow, U. (1995). Flexible Control of Mobile Robots Through Autonomous Competence Acquisition. Measurement and Control 28: 48–54.
Nehmzow, U., Hallam, J. & Smithers, T. (1989). Really Useful Robots. In Kanade, T., Groen, F. C. A. & Hertzberger, L. O. (eds.) Intelligent Autonomous Systems 2. Elsevier: Amsterdam.
Nehmzow, U. & McGonigle, B. (1994). Achieving Rapid Adaptations in Robots by Means of External Tuition. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 301–308. MIT Press.
Nehmzow, U., Smithers, T & McGonigle, B. (1993). Increasing Behavioural Repertoire in a Mobile Robot. In Meyer, J. A., Roitblat, H. & Wilson, S. (eds). From Animals to Animats 2, Proceedings of the Second International Conference on the Simulation of Adaptive Behaviour, 291–297. MIT Press.
Pfeifer, R. & Scheier C. (1994). From Perception to Action: The Right Direction? In: Gaussier, P. & Nicoud, J. D. (eds.) From Perception to Action, 1–11. IEEE Computer Society Press.
Raphael, B. (1976). The Robot ‘Shakey’ and ‘His’ Successors. Computers and People 25(10): 7.
Rutkowska, J. C. (1994). Emergent Functionality in Human Infants. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 178–188. MIT Press.
Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning Internal Representations by Error Propagation. In Rumelhart, D. E. & McLelland, J. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Bradford Books/MIT Press: Cambridge, MA.
Rylatt, R. M., Czarnecki, C. A. & Routen, T. W. (1995). A Perspective on the Future of Behaviour-Based Robotics. Mobile Robots Workshop Notes, Tenth Biennial Conference on Artificial Intelligence and Simulated Behaviour. Sheffield, England.
Saunders, G. M., Kolen, J. F. & Pollack, J. B. (1994). The Importance of Leaky Levels for Behaviour-Based AI. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 275–281. MIT Press.
Scutt, T. (1994). The Five Neuron Trick. From Animals to Animats 3: Proceedings of the Third International Conference on the Simulation of Adaptive Behaviour, 365–369. MIT Press.
Sutton, R. S. (1988). Learning to Predict by the Methods of Temporal Differences. Machine Learning 3: 9–44.
Tani, J. & Fukumura, N. (1994). Learning Goal-Directed Sensory-Based Navigation of a Mobile Robot. Neural Networks 7(3): 553–563.
Thrun, S. (1994). A Lifelong Learning Perspective for Mobile Robot Control. Proceedings of the IEEE Conference on Intelligent Robots and Systems, 12–16.
Verschure, P. F. M. J. & Pfeifer, R. (1993). Categorisation, Representations and the Dynamics of System-Environment Interaction: A Case Study in Autonomous Systems. From Animals to Animats 2: Proceedings of the Second International Conference on the Simulation of Adaptive Behaviour, 210–217. MIT Press.
Van de Velde, W. (ed.) (1993). Toward Learning Robots. Bradford Books: MIT Press, Cambridge, MA.
Verschure, P. F. M. J. (1992). Taking Connectionism Seriously: The Vague Promise of Subsymbolism and an Alternative. Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society. Erlbaum: N. Y.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Rylatt, M., Czarnecki, C. & Routen, T. Connectionist Learning in Behaviour-Based Mobile Robots: A Survey. Artificial Intelligence Review 12, 445–468 (1998). https://doi.org/10.1023/A:1006567623867
Issue Date:
DOI: https://doi.org/10.1023/A:1006567623867