Abstract
In this paper we define the task of place learning and describe one approach to this problem. Our framework represents distinct places as evidence grids, a probabilistic description of occupancy. Place recognition relies on nearest neighbor classification, augmented by a registration process to correct for translational differences between the two grids. The learning mechanism is lazy in that it involves the simple storage of inferred evidence grids. Experimental studies with physical and simulated robots suggest that this approach improves place recognition with experience, that it can handle significant sensor noise, that it benefits from improved quality in stored cases, and that it scales well to environments with many distinct places. Additional studies suggest that using historical information about the robot's path through the environment can actually reduce recognition accuracy. Previous researchers have studied evidence grids and place learning, but they have not combined these two powerful concepts, nor have they used systematic experimentation to evaluate their methods' abilities.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aamodt, A. & Plaza, E. (1994). Case-based reasoning: Foundational issues, methodological variations, and system approaches. AI Communications 7: 39–59.
Aha, D. W. (1990). A study of instance-based algorithms for supervised learning tasks: Mathematical, empirical, and psychological evaluations. Doctoral dissertation, Department of Information & Computer Science, University of California, Irvine.
Anderson, J. R. & Matessa, M. (1992). Explorations of an incremental, Bayesian algorithm for categorization. Machine Learning 9: 275–308.
Atkeson, C. (1989). Using local models to control movement. In Touretzky, D. S. (ed.), Advances in Neural Information Processing Systems (Vol. 2). San Francisco: Morgan Kaufmann.
Elfes, A. (1989). Using occupancy grids for mobile robot perception and navigation. IEEE Computer Magazine, June, 46–58.
Kibler, D. & Langley, P. (1988). Machine learning as an experimental science. Proceedings of the Third European Working Session on Learning (pp. 81–92). Glasgow: Pittman.
Kolodner, J. L. (1993). Case-based reasoning. San Francisco: Morgan Kaufmann.
Kortencamp, D. & Weymouth, T. (1994). Topological mapping for mobile robots using a combination of sonar and vision sensing. Proceedings of the Twelfth National Conference on Artificial Intelligence (pp. 979–984). Seattle, WA: AAAI Press.
Kuipers, B. & Byun, Y. T. (1988). A robust, qualitative method for robot spatial learning. Proceedings of the Eighth National Conference on Artificial Intelligence (pp. 774–779). St. Paul, MN.
Langley, P. & Pfleger, K. (1995). Case-based acquisition of place knowledge. Proceedings of the Twelfth International Conference on Machine Learning (pp. 244–352). Lake Tahoe, CA: Morgan Kaufmann.
Langley, P. & Sage, S. (in press). Scaling to domains with irrelevant features. In Greiner, R., Petsche, T. & Hanson, S. J. (eds.), Computational learning theory and natural learning systems (Vol. 4). Cambridge, MA: MIT Press.
Lavrac, N. & Dzeroski, S. (1993). Inductive logic programming: Techniques and applications. New York: Ellis Horwood.
Leake, D. B. (1994). Case-based reasoning. Knowledge Engineering Review 9: 61–64.
Levitt, T. S, Lawton, D. T., Chelberg, D. M. & Nelson, P.C. (1987). Qualitative landmark-based path planning and following. Proceedings of the Sixth National Conference on Artificial Intelligence (pp. 689–694). Seattle, WA: AAAI Press.
Lin, L., Hanson, S. J. & Judd, J. S. (1994). On-line learning for landmark-based navigation (Technical Report No. SCR-94-TR-472). Princeton, NJ: Siemens Corporate Research, Learning Systems Department.
Mahadevan, S. (1992). Enhancing transfer in reinforcement learning by building stochastic models of robot actions. Proceedings of the Ninth International Conference on Machine Learning (pp. 290–299). Aberdeen: Morgan Kaufmann.
Mataric, M. J. (1991). Behavioral synergy without explicit integration. Sigart Bulletin 2: 130–133.
Moore, A. W. (1990). Acquisition of dynamic control knowledge for a robotic manipulator. Proceedings of the Seventh International Conference on Machine Learning (pp. 244–252). Austin, TX: Morgan Kaufmann.
Moravec, H. & Blackwell, M. (1992). Learning sensor models for evidence grids. Robotics Institute Research Review. Pittsburgh, PA: Carnegie Mellon University.
Schiele, B. & Crowley, J. L. (1994). A comparison of position estimation techniques using occupancy grids. Robotics and Autonomous Systems 12: 163–171.
Thrun, S. B. (1993). Exploration and model building in mobile robot domains. Proceedings of the IEEE International Conference on Neural Networks. San Francisco: IEEE.
Yamauchi, B. & Beer, R. (1994). Spatial learning for navigation in dynamic environments. IEEE Transactions on Systems, Man, and Cybernetics — Part B 26: 496–505.
Yeap, Y. K. (1988). Towards a computational theory of cognitive maps. Artificial Intelligence 34: 297–360.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Langley, P., Pfleger, K. & Sahami, M. Lazy Acquisition of Place Knowledge. Artificial Intelligence Review 11, 315–342 (1997). https://doi.org/10.1023/A:1006545731094
Issue Date:
DOI: https://doi.org/10.1023/A:1006545731094