A view-based neurocomputational system for relational map-making and navigation in visual environments

Abstract Artificial navigation systems stand to benefit greatly from learning maps of visual environments, but traditional map-making techniques are inadequate in several respects. This paper describes an adaptive, view-based, relational map-making system for navigating within a 3D environment defined by a spatially distributed set of visual landmarks. Inspired by an analogy to learning aspect graphs of 3D objects, the system comprises two neurocomputational architectures that emulate cognitive mapping in the rat hippocampus. The first architecture performs unsupervised place learning by combining the “What” with the “Where”, namely through conjunctions of landmark identity, pose, and egocentric gaze direction within a local, restricted sensory view of the environment. The second associatively learns action consequences by incorporating the “When”, namely through conjunctions of learned places and coarsely coded robot motions. Together, these networks form a map reminiscent of a partially observable Markov decision process, and consequently provide an ideal neural substrate for prediction, environment recognition, route planning, and exploration. Preliminary results from real-time implementations on a mobile robot called MAVIN (the Mobile Adaptive VIsual Navigator) demonstrate the potential for these capabilities.

[1]  Charles R. McLean,et al.  Hierarchical Control for Robots and Teleoperators , 1985 .

[2]  Allen M. Waxman,et al.  Mobile robot visual mapping and localization: A view-based neurocomputational architecture that emulates hippocampal place learning , 1994, Neural Networks.

[3]  Y. Miyashita.  Neuronal correlate of visual associative long-term memory in the primate temporal cortex , 1988, Nature.

[4]  Leslie G. Ungerleider,et al.  Object vision and spatial vision: two cortical pathways , 1983, Trends in Neurosciences.

[5]  Gary L. Drescher,et al.  A Mechanism for Early Piagetian Learning , 1987, AAAI.

[6]  B L McNaughton,et al.  Dynamics of the hippocampal ensemble code for space. , 1993, Science.

[7]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[8]  Mitsuo Sato,et al.  Learning control of finite Markov chains with unknown transition probabilities , 1982 .

[9]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[10]  Jeffrey L. Elman,et al.  Distributed Representations, Simple Recurrent Networks, and Grammatical Structure , 1991, Mach. Learn..

[11]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[12]  Tod S. Levitt,et al.  Qualitative Navigation for Mobile Robots , 1990, Artif. Intell..

[13]  E. Tolman.  Cognitive maps in rats and men. , 1948, Psychological review.

[14]  H T Blair,et al.  Maps, routes, and the hippocampus: A neural network approach , 1993, Hippocampus.

[15]  Alberto Del Bimbo,et al.  Recurrent neural networks can be trained to be maximum a posteriori probability classifiers , 1995, Neural Networks.

[16]  J. Paillard.  Brain and space , 1991 .

[17]  Wei-Min Shen,et al.  Autonomous learning from the environment , 1994 .

[18]  Benjamin Kuipers,et al.  A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations , 1991, Robotics Auton. Syst..

[19]  M. Shapiro,et al.  A simple network model simulates hippocampal place fields: II. Computing goal-directed trajectories and memory fields. , 1993, Behavioral neuroscience.

[20]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[21]  Drew McDermott,et al.  Image signatures for place recognition and map construction , 1992, Other Conferences.

[22]  Stephen P. Brooks,et al.  Markov Decision Processes. , 1995 .

[23]  Jacek M. Zurada,et al.  Computational Intelligence: Imitating Life , 1994 .

[24]  David I. Perrett,et al.  Neurophysiology of shape processing , 1993, Image Vis. Comput..

[25]  Ernest Davis,et al.  Representing and Acquiring Geographic Knowledge , 1986 .

[26]  L. Nadel,et al.  The Hippocampus as a Cognitive Map , 1978 .

[27]  A. Waxman,et al.  A neural system for qualitative mapping and navigation in visual environments , 1994, Proceedings of PerAc '94. From Perception to Action.

[28]  P. Culicover,et al.  Neural connections, mental computation , 1988 .

[29]  K Tanaka,et al.  Neuronal mechanisms of object recognition. , 1993, Science.

[30]  Allen M. Waxman,et al.  Adaptive 3-D Object Recognition from Multiple Views , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Alan N. Gove,et al.  Neural processing of targets in visible, multispectral IR and SAR imagery , 1995, Neural Networks.

[32]  Richard S. Sutton,et al.  Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming , 1990, ML.

[33]  Robert E. Schapire,et al.  A new approach to unsupervised learning in deterministic environments , 1990 .

[34]  Narendra Ahuja,et al.  Gross motion planning—a survey , 1992, CSUR.

[35]  Benjamin Kuipers,et al.  Navigation and Mapping in Large Scale Space , 1988, AI Mag..

[36]  Jian Wu,et al.  Models for map building and navigation , 1993, IEEE Trans. Syst. Man Cybern..

[37]  A. W. Smith,et al.  Encoding sequential structure: experience with the real-time recurrent learning algorithm , 1989, International 1989 Joint Conference on Neural Networks.

[38]  Michael Recce,et al.  A model of hippocampal function , 1994, Neural Networks.

[39]  Maja J. Mataric,et al.  Integration of representation into goal-driven behavior-based robots , 1992, IEEE Trans. Robotics Autom..

[40]  Michael C. Mozer,et al.  SLUG: A Connectionist Architecture for Inferring the Structure of Finite-State Environments , 1991, Mach. Learn..

[41]  Ren C. Luo,et al.  Multisensor integration and fusion in intelligent systems , 1989, IEEE Trans. Syst. Man Cybern..

[42]  Drew McDermott,et al.  Robot Planning , 1991, AI Mag..

[43]  B. McNaughton,et al.  Dead Reckoning, Landmark Learning, and the Sense of Direction: A Neurophysiological and Computational Hypothesis , 1991, Journal of Cognitive Neuroscience.

[44]  Bernhard Schölkopf,et al.  View-Based Cognitive Mapping and Path Planning , 1995, Adapt. Behav..