Advertisement

Autonomous Robots

, Volume 5, Issue 3–4, pp 297–316 | Cite as

Hierarchical Learning of Navigational Behaviors in an Autonomous Robot using a Predictive Sparse Distributed Memory

  • Rajesh P.N. Rao
  • Olac Fuentes
Article

Abstract

We describe a general framework for learning perception-based navigational behaviors in autonomous mobile robots. A hierarchical behavior-based decomposition of the control architecture is used to facilitate efficient modular learning. Lower level reactive behaviors such as collision detection and obstacle avoidance are learned using a stochastic hill-climbing method while higher level goal-directed navigation is achieved using a self-organizing sparse distributed memory. The memory is initially trained by teleoperating the robot on a small number of paths within a given domain of interest. During training, the vectors in the sensory space as well as the motor space are continually adapted using a form of competitive learning to yield basis vectors that efficiently span the sensorimotor space. After training, the robot navigates from arbitrary locations to a desired goal location using motor output vectors computed by a saliency-based weighted averaging scheme. The pervasive problem of perceptual aliasing in finite-order Markovian environments is handled by allowing both current as well as the set of immediately preceding perceptual inputs to predict the motor output vector for the current time instant. We describe experimental and simulation results obtained using a mobile robot equipped with bump sensors, photosensors and infrared receivers, navigating within an enclosed obstacle-ridden arena. The results indicate that the method performs successfully in a number of navigational tasks exhibiting varying degrees of perceptual aliasing.

sensorimotor learning autonomous navigation stochastic hill-climbing predictive sparse distributed memory teleoperation competitive learning basis vectors perceptual aliasing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Albus, J. 1971. A theory of cerebellar functions. Math. Bio., 10:25- 61.Google Scholar
  2. Asada, M., Uchibe, E., Noda, S., Tawaratsumida, S., and Hosoda, K. 1994. Coordination of multiple behaviors acquired by a vision-based reinforcement learning. In Proceedings of the 1994 IEEE/RSJ International Conference on Intelligent Robots an Systems, Munich, Germany, pp. 917-924.Google Scholar
  3. Beer, R. and Gallagher, J. 1992. Evolving dynamical neural networks for adaptive behavior. Adaptive Behavior, 1:91-122.Google Scholar
  4. Brooks, R.A. 1986. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, 2(1):14-22.Google Scholar
  5. Broomhead, D.S. and Lowe, D. 1988. Multivariable functional interpolation and adaptive networks. Complex Systems, 2:321-355.Google Scholar
  6. Chrisman, L. 1992. Reinforcement learning with perceptual aliasing. In Proceedings of the Eleventh National Conference on Artificial Intelligence.Google Scholar
  7. Cliff, D., Husbands, P., and Harvey, I. 1992. Evolving visually guided robots. In From Animals to Animats 2: Proceedings of the Second International Conference on the Simulation of Adaptive Behavior, J.A. Meyer, H. Roitblat, and S. Wilson (Eds.), MIT Press: Cambridge, MA, pp. 374-383.Google Scholar
  8. Connell, J.H. 1990. Minimalist Mobile Robotics: A Colony-Style Architecture for an Artificial Creature, Academic Press: Boston, MA.Google Scholar
  9. Dayan, P. and Hinton, G. 1993. Feudal reinforcement learning. In Advances in Neural Information Processing Systems 5, S. Hanson, J. Cowan, and C. Giles (Eds.), Morgan Kaufmann: San Mateo, CA, pp. 271-278.Google Scholar
  10. de Bourcier, P. 1993. Animate navigation using visual landmarks. Cognitive Science Research Papers 277, University of Sussex at Brighton.Google Scholar
  11. Elfes, A. 1987. Sonar-based real-world mapping and navigation. IEEE Journal of Robotics and Automation, 3:249-265.Google Scholar
  12. Fuentes, O., Rao, R.P.N., and Wie, M.V. 1995. Hierarchical learning of reactive behaviors in an autonomous mobile robot. In Proceedings of the IEEE International Conf. on Systems, Man, and Cybernetics.Google Scholar
  13. Fuentes, O. and Nelson, R.C. 1997. Learning dextrous manipulation skills using the evolution strategy. In Proceedings of the 1997 IEEE International Conference on Robotics and Automation, Albuquerque, New Mexico.Google Scholar
  14. Hackbusch, W. 1985. Multi-grid Methods and Applications, Springer-Verlag: Berlin.Google Scholar
  15. Hertz, J., Krogh, A., and Palmer, R. 1991. Introduction to the Theory of Neural Computation, Addison-Wesley Publishing Company: Redwood City, CA.Google Scholar
  16. Hinton, G., McClelland, J., and Rumelhart, D. 1986. Distributed representations. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1. MIT Press: Cambridge, MA.Google Scholar
  17. Joglekar, U.D. 1989. Learning to read aloud: A neural network approach using sparse distributed memory. Technical Report 89.27, Research Institute for Advanced Computer Science, NASA Ames Research Center.Google Scholar
  18. Jordan, M. 1986. Attractor dynamics and parallelism in a connectionist sequential machine. In Proceedings of the 1986 Cognitive Science Conference.Google Scholar
  19. Kaelbling, L. 1993a. Hierarchical reinforcement learning: Preliminary results. In Proceedings of the Tenth International Conference on Machine Learning, Morgan Kaufmann: San Mateo, CA, pp. 167-173.Google Scholar
  20. Kaelbling, L.P. 1993b. Learning in Embedded Systems, MIT Press: Cambridge, MA.Google Scholar
  21. Kaelbling, L.P., Littman, M.L., and Moore, A.W. 1996. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237-285.Google Scholar
  22. Kanerva, P. 1988. Sparse Distributed Memory, Bradford Books: Cambridge, MA.Google Scholar
  23. Kanerva, P. 1993. Sparse distributed memory and related models. In Associative Neural Memories, M.H. Hassoun (Ed.), Oxford University Press: New York, pp. 50-76.Google Scholar
  24. Krose, B.J.A. and Eecen, M. 1994. A self-organizing representation of sensor space for mobile robot navigation. In IEEE/RSJ/GI International Conference on Intelligent Robots an Systems, pp. 9-14.Google Scholar
  25. Kuipers, B.J. and Byun, Y.-T. 1988. A robust, qualitiative approach to a spatial learning mobile robot. In SPIE Cambridge Symposium on Optical and Optoelectronic Engineering: Advances in Intelligent Robotics Systems.Google Scholar
  26. Lewis, M.A., Fagg, A.H., and Solidum, A. 1992. Genetic programming approach to the construction of a neural network for control of a walking robot. In Proceedings of the 1992 IEEE International Conference on Robotics and Automation, Nice, France.Google Scholar
  27. Maes, P. and Brooks, R.A. 1990. Learning to coordinate behaviors. In Proceedings of AAAI-90, pp. 796-802.Google Scholar
  28. Mahadevan, S. and Connell, J. 1991. Scaling reinforcement learning to robotics by exploiting the subsumption architecture. In Proceedings of the Eighth International Workshop on Machine Learning.Google Scholar
  29. Marr, D. 1969. A theory of cerebellar cortex. J. Physiol. (London), 202:437-470.Google Scholar
  30. Mataric, M. 1992. Integration of representation into goal-driven behavior-based robot. IEEE Transactions on Robotics and Automation, 8(3):304-312.Google Scholar
  31. McCallum, R.A. 1996. Hidden state and reinforcement learning with instance-based state identification. IEEE Trans. on Systems, Man and Cybernetics, 26(3):464-473.Google Scholar
  32. McIlwain, J.T. 1991. Distributed spatial coding in the superior colliculus: A review. Visual Neuroscience, 6:3-13.Google Scholar
  33. Nehmzow, U. and Smithers, T. 1991. Mapbuilding using self-organizing networks in “Really Useful Robots”. In From Animals to Animats 1: Proceedings of the First International Conference on Simulation of Adaptive Behavior, J.-A. Meyer and S.W. Wilson (Eds.), MIT Press: Cambridge, MA, pp. 152-159.Google Scholar
  34. Nelson, R.C. 1991. Visual homing using an associative memory. Biological Cybernetics, 65:281-291.Google Scholar
  35. Nolfi, S. 1997. Using emergent modularity to develop control systems for mobile robots. Adaptive Behavior, 5:343-363.Google Scholar
  36. Nowlan, S. 1990. Maximum likelihood competitive learning. In Advances in Neural Information Processing Systems 2, D. Touretzky (Ed.), Morgan Kaufmann: San Mateo, CA, pp. 574-582.Google Scholar
  37. Pierce, D. and Kuipers, B. 1991. Learning hill-climbing functions as a strategy for generating behaviors in a mobile robot. In From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, pp. 327-336.Google Scholar
  38. Poggio, T. and Girosi, F. 1990. Networks for approximation and learning. In Proc. IEEE, vol. 78, pp. 1481-1497.Google Scholar
  39. Pomerleau, D. 1989. ALVINN:Anautonomous land vehicle in a neural network. In Advances in Neural Information Processing Systems, D. Touretzky (Ed.), vol. 1, Morgan Kaufmann: San Mateo, pp. 305-313.Google Scholar
  40. Pomerleau, D. 1991. Efficient training of artificial neural networks for autonomous navigation. Neural Computation, 3(1):88-97.Google Scholar
  41. Prager, R.W. and Fallside, F. 1989. The modified Kanerva model for automatic speech recognition. Computer Speech and Language, 3(1):61-81.Google Scholar
  42. Rao, R.P.N. and Ballard, D.H. 1995a. An active vision architecture based on iconic representations. Artificial Intelligence (Special Issue on Vision), 78:461-505.Google Scholar
  43. Rao, R.P.N. and Ballard, D.H. 1995b. Learning saccadic eye movements using multiscale spatial filters. In Advances in Neural Information Processing Systems 7, G. Tesauro, D.S. Touretzky, and T.K. Leen (Eds.), MIT Press: Cambridge, MA, pp. 893-900.Google Scholar
  44. Rao, R.P.N. and Ballard, D.H. 1995c. Natural basis functions and topographic memory for face recognition. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 10-17.Google Scholar
  45. Rao, R.P.N. and Ballard, D.H. 1995d. Object indexing using an iconic sparse distributed memory. In Proceedings of the International Conference on Computer Vision (ICCV), pp. 24-31.Google Scholar
  46. Rao, R.P.N. and Fuentes, O. 1995. Perceptual homing by an autonomous mobile robot using sparse self-organizing sensory-motor maps. In Proceedings of World Congress on Neural Networks (WCNN), pp. II380-II383.Google Scholar
  47. Rao, R.P.N. and Fuentes, O. 1996. Learning navigational behaviors using a predictive sparse distributed memory. In From Animals to Animats 4: Proceedings of the Fourth Int. Conf. on Simulation of Adaptive Behavior (SAB), pp. 382-390.Google Scholar
  48. Rao, R.P.N. and Ballard, D.H. 1997. Dynamic model of visual recognition predicts neural response properties in the visual cortex. Neural Computation, 9(4):721-763.Google Scholar
  49. Rogers, D. 1990. Predicting weather using a genetic memory: A combination of Kanerva's sparse distributed memory and Holland's genetic algorithms. In Advances in Neural Information Processing Systems 2, D.S. Touretzky (Ed.), Morgan Kaufmann, pp. 455-464.Google Scholar
  50. Singh, S. 1992. Transfer of learning by composing solutions of elemental sequential tasks. Machine Learning, 8:323-339.Google Scholar
  51. Tani, J. and Fukumura, N. 1994. Learning goal-directed sensory-based navigation of a mobile robot. Neural Networks, 7(3):553-563.Google Scholar
  52. Whitehead, S. and Ballard, D. 1991. Learning to perceive and act by trial and error. Machine Learning, 7(1):45-83.Google Scholar
  53. Wixson, L. 1991. Scaling reinforcement learning techniques via modularity. In Proceedings of the Eighth International Workshop on Machine Learning, Morgan Kaufmann, pp. 368-372.Google Scholar
  54. Yair, E., Zeger, K., and Gersho, A. 1992. Competitive learning and soft competition for vector quantizer design. IEEE Trans. Signal Processing, 40(2):294-309.Google Scholar

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • Rajesh P.N. Rao
    • 1
  • Olac Fuentes
    • 2
  1. 1.Computational Neurobiology LaboratoryThe Salk Institute, Sloan Center for Theoretical Neurobiology andLa JollaUSA
  2. 2.Centro de Investigación en ComputaciónInstituto Politecnico Nacional, MexicoMexico

Personalised recommendations