Towards real-world capable spatial memory in the LIDA cognitive architecture

Abstract The ability to represent and utilize spatial information relevant to their goals is vital for intelligent agents. Doing so in the real world presents significant challenges, which have so far mostly been addressed by robotics approaches neglecting cognitive plausibility; whereas existing cognitive models mostly implement spatial abilities in simplistic environments, neglecting uncertainty and complexity. Here, we take a step towards computational software agents capable of forming spatial memories in realistic environments, based on the biologically inspired LIDA cognitive architecture. We identify and address challenges faced by agents operating with noisy sensors and actuators in a complex physical world, including near-optimal integration of spatial cues from different modalities for localization and mapping, correcting cognitive maps when revisiting locations, the structuring of complex maps for computational efficiency, and multi-goal route planning on hierarchical cognitive maps. We also describe computational mechanisms addressing these challenges based on LIDA, and demonstrate their functionality by replicating several psychological experiments.

[1]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[2]  Sebastian Thrun,et al.  FastSLAM: A Scalable Method for the Simultaneous Localization and Mapping Problem in Robotics , 2007 .

[3]  Michael E Hasselmo,et al.  Head direction cells in the postsubiculum do not show replay of prior waking sequences during sleep , 2012, Hippocampus.

[4]  N. Fortin,et al.  1.21 – Navigation and Episodic-Like Memory in Mammals , 2008 .

[5]  Robert Trappl,et al.  Bayesian Integration of Information in Hippocampal Place Cells , 2014, PloS one.

[6]  James F. Cremer,et al.  Distance perception in real and virtual environments , 2004 .

[7]  J. O’Keefe,et al.  Geometric determinants of the place fields of hippocampal neurons , 1996, Nature.

[8]  Janet Wiles,et al.  Solving Navigational Uncertainty Using Grid Cells on Robots , 2010, PLoS Comput. Biol..

[9]  Margaret F. Carr,et al.  Hippocampal replay in the awake state: a potential substrate for memory consolidation and retrieval , 2011, Nature Neuroscience.

[10]  Rosamund F Langston,et al.  Lateral Entorhinal Cortex is Critical for Novel Object-Context Recognition , 2013, Hippocampus.

[11]  Bernard J. Baars,et al.  CONSCIOUSNESS IS COMPUTATIONAL: THE LIDA MODEL OF GLOBAL WORKSPACE THEORY , 2009 .

[12]  Ha Hong,et al.  Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream , 2013, NIPS.

[13]  David Waller,et al.  Factors Affecting the Perception of Interobject Distances in Virtual Environments , 1999, Presence.

[14]  D. G. Stork,et al.  Is backpropagation biologically plausible? , 1989, International 1989 Joint Conference on Neural Networks.

[15]  Ke Chen,et al.  Spatial Working Memory in the LIDA Cognitive Architecture , 2013, ICCM 2013.

[16]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[17]  Ke Chen,et al.  Computational cognitive models of spatial memory in navigation space: A review , 2015, Neural Networks.

[18]  A S Etienne,et al.  Path integration in mammals and its interaction with visual landmarks. , 1996, The Journal of experimental biology.

[19]  Punit Shah.  Toward a Neurobiology of Unrealistic Optimism , 2012, Front. Psychology.

[20]  Ben Goertzel,et al.  A world survey of artificial brain projects, Part I: Large-scale brain simulations , 2010, Neurocomputing.

[21]  K. Jeffery,et al.  The Boundary Vector Cell Model of Place Cell Firing and Spatial Memory , 2006, Reviews in the neurosciences.

[22]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[23]  E. Moser,et al.  A manifold of spatial maps in the brain , 2010, Trends in Cognitive Sciences.

[24]  Dwight J. Kravitz,et al.  A new neural framework for visuospatial processing , 2011, Nature Reviews Neuroscience.

[25]  N. Burgess,et al.  The hippocampus and memory: insights from spatial processing , 2008, Nature Reviews Neuroscience.

[26]  Joaquin M. Fuster,et al.  Physiology of executive functions: The perception-action cycle. , 2002 .

[27]  Tamas Madl,et al.  LIDA: A Systems-level Architecture for Cognition, Emotion, and Learning , 2014, IEEE Transactions on Autonomous Mental Development.

[28]  T. Hafting,et al.  Microstructure of a spatial map in the entorhinal cortex , 2005, Nature.

[29]  Gordon Wyeth,et al.  FAB-MAP + RatSLAM: Appearance-based SLAM for multiple times of day , 2010, 2010 IEEE International Conference on Robotics and Automation.

[30]  Thomas L. Griffiths,et al.  A more rational model of categorization , 2006 .

[31]  Adam N. Sanborn,et al.  Unifying rational models of categorization via the hierarchical Dirichlet process , 2019 .

[32]  Fred W. Mast,et al.  The neural basis of the egocentric and allocentric spatial frame of reference , 2007, Brain Research.

[33]  Pete R. Jones,et al.  Development of Cue Integration in Human Navigation , 2008, Current Biology.

[34]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Michael E. Hasselmo,et al.  Coincidence Detection of Place and Temporal Context in a Network Model of Spiking Hippocampal Neurons , 2007, PLoS Comput. Biol..

[36]  K. Zilles,et al.  Neural Correlates of First-Person Perspective as One Constituent of Human Self-Consciousness , 2004, Journal of Cognitive Neuroscience.

[37]  Neil Burgess,et al.  Predictions derived from modelling the hippocampal role in navigation , 2000, Biological Cybernetics.

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

[39]  Paul Sharkey,et al.  Estimation of Distances in Virtual Environments Using Size Constancy , 2009, Int. J. Virtual Real..

[40]  Emilio Kropff,et al.  Place cells, grid cells, and the brain's spatial representation system. , 2008, Annual review of neuroscience.

[41]  G. Buzsáki,et al.  Forward and reverse hippocampal place-cell sequences during ripples , 2007, Nature Neuroscience.

[42]  Alexei V. Samsonovich,et al.  Toward a Unified Catalog of Implemented Cognitive Architectures , 2010, BICA.

[43]  N. Spruston,et al.  Conditional dendritic spike propagation following distal synaptic activation of hippocampal CA1 pyramidal neurons , 2005, Nature Neuroscience.

[44]  Russell A. Epstein.  Parahippocampal and retrosplenial contributions to human spatial navigation , 2008, Trends in Cognitive Sciences.

[45]  J. Magee,et al.  Pathway Interactions and Synaptic Plasticity in the Dendritic Tuft Regions of CA1 Pyramidal Neurons , 2009, Neuron.

[46]  B. Baars.  The conscious access hypothesis: origins and recent evidence , 2002, Trends in Cognitive Sciences.

[47]  Yoshua Bengio,et al.  An objective function for STDP , 2015, ArXiv.

[48]  T. Hafting,et al.  Finite Scale of Spatial Representation in the Hippocampus , 2008, Science.

[49]  C. Gallistel,et al.  The precision of locomotor odometry in humans , 2009, Experimental Brain Research.

[50]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[51]  Nikolaus Kriegeskorte,et al.  Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation , 2014, PLoS Comput. Biol..

[52]  Gordon Wyeth,et al.  Outdoor Simultaneous Localisation and Mapping Using RatSLAM , 2005, FSR.

[53]  Michael Beetz,et al.  Extending Player/Stage/Gazebo towards Cognitive Robots Acting in Ubiquitous Sensor-equipped Environments , 2007 .

[54]  J. Gower.  Generalized procrustes analysis , 1975 .

[55]  Javier Snaider,et al.  Modular Composite Representation , 2014, Cognitive Computation.

[56]  P. Berkes,et al.  Statistically Optimal Perception and Learning: from Behavior to Neural Representations , 2022 .

[57]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[58]  N. Burgess.  Spatial Cognition and the Brain , 2008, Annals of the New York Academy of Sciences.

[59]  David Ball,et al.  Maintaining a Cognitive Map in Darkness: The Need to Fuse Boundary Knowledge with Path Integration , 2012, PLoS Comput. Biol..

[60]  M. Quirk,et al.  Experience-Dependent Asymmetric Shape of Hippocampal Receptive Fields , 2000, Neuron.

[61]  Stan Franklin,et al.  Cortical Learning Algorithms with Predictive Coding for a Systems-Level Cognitive Architecture , 2013 .

[62]  Ian D. Reid,et al.  Article in Press Robotics and Autonomous Systems ( ) – Robotics and Autonomous Systems a Comparison of Loop Closing Techniques in Monocular Slam , 2022 .

[63]  J. Jonides,et al.  Evidence of hierarchies in cognitive maps , 1985, Memory & cognition.

[64]  Sebastian Thrun,et al.  Simultaneous Localization and Mapping , 2008, Robotics and Cognitive Approaches to Spatial Mapping.

[65]  J. O’Keefe,et al.  Boundary Vector Cells in the Subiculum of the Hippocampal Formation , 2009, The Journal of Neuroscience.

[66]  E. Maguire,et al.  The Well-Worn Route and the Path Less Traveled Distinct Neural Bases of Route Following and Wayfinding in Humans , 2003, Neuron.

[67]  Stan Franklin,et al.  A New Action Execution Module for the Learning Intelligent Distribution Agent (LIDA): The Sensory Motor System , 2015, Cognitive Computation.

[68]  Alexei V. Samsonovich,et al.  On a roadmap for the BICA Challenge , 2012, BICA 2012.

[69]  Jason P. Mitchell,et al.  Multiple routes to memory: Distinct medial temporal lobe processes build item and source memories , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[70]  Yoshua Bengio,et al.  Towards Biologically Plausible Deep Learning , 2015, ArXiv.

[71]  Robert Trappl,et al.  Exploring the Structure of Spatial Representations , 2016, PloS one.

[72]  Tien Dat Nguyen,et al.  How does presentation method and measurement protocol affect distance estimation in real and virtual environments? , 2010, TAP.

[73]  M. Moser,et al.  Representation of Geometric Borders in the Entorhinal Cortex , 2008, Science.

[74]  Keiji Tanaka,et al.  Object category structure in response patterns of neuronal population in monkey inferior temporal cortex. , 2007, Journal of neurophysiology.

[75]  Gordon Wyeth,et al.  RatSLAM: a hippocampal model for simultaneous localization and mapping , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[76]  B L McNaughton,et al.  Path Integration and Cognitive Mapping in a Continuous Attractor Neural Network Model , 1997, The Journal of Neuroscience.

[77]  Bruce L. McNaughton,et al.  Path integration and the neural basis of the 'cognitive map' , 2006, Nature Reviews Neuroscience.

[78]  D. Knill,et al.  The Bayesian brain: the role of uncertainty in neural coding and computation , 2004, Trends in Neurosciences.

[79]  Alejandra Barrera,et al.  Comparative Experimental Studies on Spatial Memory and Learning in Rats and Robots , 2011, J. Intell. Robotic Syst..

[80]  J. Taube.  The head direction signal: origins and sensory-motor integration. , 2007, Annual review of neuroscience.

[81]  Wolfram Burgard,et al.  Probabilistic Robotics (Intelligent Robotics and Autonomous Agents) , 2005 .

[82]  Cyrill Stachniss,et al.  Simultaneous Localization and Mapping , 2016, Springer Handbook of Robotics, 2nd Ed..

[83]  John Mann.  The Frontiers of Psychology , 1935, Nature.

[84]  T. McNamara,et al.  Subjective hierarchies in spatial memory. , 1989, Journal of experimental psychology. Learning, memory, and cognition.

[85]  K. Jeffery.  Self-localization and the entorhinal–hippocampal system , 2007, Current Opinion in Neurobiology.

[86]  Ricardo Chavarriaga,et al.  Robust self-localisation and navigation based on hippocampal place cells , 2005, Neural Networks.

[87]  Javier Snaider,et al.  The LIDA Framework as a General Tool for AGI , 2011, AGI.

[88]  S. Franklin,et al.  Modeling sensorimotor learning in LIDA using a dynamic learning rate , 2015, BICA 2015.

[89]  H. Mittelstaedt,et al.  Homing by path integration in a mammal , 1980, Naturwissenschaften.

[90]  Stan Franklin,et al.  Multi-layer Cortical Learning Algorithms , 2014, 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB).

[91]  Ben Goertzel,et al.  A world survey of artificial brain projects, Part II: Biologically inspired cognitive architectures , 2010, Neurocomputing.

[92]  J. Rieser,et al.  Bayesian integration of spatial information. , 2007, Psychological bulletin.

[93]  Edwin Olson,et al.  Fast iterative alignment of pose graphs with poor initial estimates , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[94]  Gyorgy Csizmadia,et al.  Storage of the Distance between Place Cell Firing Fields in the Strength of Plastic Synapses with a Novel Learning Rule , 2008 .

[95]  Walter J. Freeman,et al.  The limbic action-perception cycle controlling goal-directed animal behavior , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[96]  W E Skaggs,et al.  Deciphering the hippocampal polyglot: the hippocampus as a path integration system. , 1996, The Journal of experimental biology.

[97]  Joachim Denzler,et al.  Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding , 2015, VISAPP.

[98]  Bernard J. Baars,et al.  Global Workspace Dynamics: Cortical “Binding and Propagation” Enables Conscious Contents , 2013, Front. Psychol..

[99]  T. Bussey,et al.  Transient Inactivation of Perirhinal Cortex Disrupts Encoding, Retrieval, and Consolidation of Object Recognition Memory , 2005, The Journal of Neuroscience.

[100]  Howard Eichenbaum,et al.  A cognitive map for object memory in the hippocampus. , 2009, Learning & memory.

[101]  Usef Faghihi,et al.  Global Workspace Theory, its LIDA model and the underlying neuroscience , 2012, BICA 2012.

[102]  Inah Lee,et al.  Neural Correlates of Object-in-Place Learning in Hippocampus and Prefrontal Cortex , 2011, The Journal of Neuroscience.