Cognitive map plasticity and imitation strategies to improve individual and social behaviors of autonomous agents

Starting from neurobiological hypotheses on the existence of place cells (PC) in the brain, the aim of this article is to show how little assumptions at both individual and social levels can lead to the emergence of non-trivial global behaviors in a multi-agent system (MAS). In particular, we show that adding a simple, hebbian learning mechanism on a cognitive map allows autonomous, situated agents to adapt themselves in a dynamically changing environment, and that even using simple agent-following strategies (driven either by similarities in the agent movement, or by individual marks — “signatures” — in agents) can dramatically improve the global performance of the MAS, in terms of survival rate of the agents. Moreover, we show that analogies can be made between such a MAS and the emergence of certain social behaviors.

[1]  Guy Theraulaz,et al.  Swarm made architectures , 1992 .

[2]  C. Freksa,et al.  Spatial Cognition, An Interdisciplinary Approach to Representing and Processing Spatial Knowledge , 1998 .

[3]  L. Matthews.  Cognitive science perspectives on personality and emotion , 1997 .

[4]  H. Simon,et al.  A Behavioral Model of Rational Choice , 1955 .

[5]  Philippe Gaussier,et al.  Neurobiologically Inspired Mobile Robot Navigation and Planning , 2007, Frontiers in neurorobotics.

[6]  P. Gaussier,et al.  Impact of imitation on the dynamics of animat populations in a spatial cognition task , 2004 .

[7]  Alice Alvernhe,et al.  Different CA1 and CA3 Representations of Novel Routes in a Shortcut Situation , 2008, The Journal of Neuroscience.

[8]  R. Axtell.  The Complexity of Exchange , 1999 .

[9]  Guillaume Damiand,et al.  Topological Map: An Efficient Tool to Compute Incrementally Topological Features on 3D Images , 2006, IWCIA.

[10]  Jean-Arcady Meyer,et al.  Animat navigation using a cognitive graph , 1998, Biological Cybernetics.

[11]  Michael Batty,et al.  Cities and Complexity: Understanding Cities Through Cellular Automata, Agent-Based Models and Fractals , 2005 .

[12]  Philippe Gaussier,et al.  From Visuo-Motor Development to Low-level Imitation , 2002 .

[13]  Nestor A. Schmajuk,et al.  Escape, Avoidance, and Imitation: A Neural Network Approach , 1997, Adapt. Behav..

[14]  Joshua M. Epstein,et al.  Growing Artificial Societies: Social Science from the Bottom Up , 1996 .

[15]  Geography, environment and cognition: an introduction , 1992 .

[16]  Aude Billard,et al.  From Animals to Animats , 2004 .

[17]  Philippe Gaussier,et al.  Learning Invariant Sensorimotor Behaviors: A Developmental Approach to Imitation Mechanisms , 2004, Adapt. Behav..

[18]  Philippe Gaussier,et al.  Transition Cells and Neural Fields for Navigation and Planning , 2005, IWINAC.

[19]  Philippe Gaussier,et al.  Robustness of Visual Place Cells in Dynamic Indoor and Outdoor Environment , 2006 .

[20]  D. Spencer.  Cities and Complexity: Understanding Cities with Cellular Automata, Agent-Based Models, and Fractals , 2009 .

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

[22]  J. Banquet,et al.  Chapter 4 Space-time, order, and hierarchy in fronto-hippocampal system: A neural basis of personality , 1997 .

[23]  Kevin Lynch,et al.  The Image of the City , 1960 .

[24]  Sorin Moga,et al.  From Perception-Action Loops to Imitation Processes: A Bottom-Up Approach of Learning by Imitation , 1998, Appl. Artif. Intell..

[25]  Philippe Gaussier,et al.  From Navigation to Active Object Recognition , 2000 .

[26]  M. Batty.  Polynucleated Urban Landscapes , 2001 .

[27]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[28]  Philippe Gaussier,et al.  Learning and motivational couplings promote smarter behaviors of an animat in an unknown world , 2002, Robotics Auton. Syst..

[29]  Philippe Gaussier,et al.  A Hierarchy of Associations in Hippocampo-Cortical Systems: Cognitive Maps and Navigation Strategies , 2005, Neural Computation.

[30]  C. Giovannangeli,et al.  Robots as Tool to Study the Robustness of Visual Place Cells , 2022 .

[31]  T. Lindvall.  ON A ROUTING PROBLEM , 2004, Probability in the Engineering and Informational Sciences.

[32]  Joshua M. Epstein,et al.  Growing Artificial Societies: Social Science from the Bottom Up , 1996 .

[33]  Joachim Hoffmann,et al.  Exploiting redundancy for flexible behavior: unsupervised learning in a modular sensorimotor control architecture. , 2007, Psychological review.

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

[35]  Mark Stefik,et al.  V. Braitenberg, Vehicles: Experiments in Synthetic Psychology , 1985, Artificial Intelligence.

[36]  Anthony G. Pipe,et al.  An Architecture for Learning "Potential Field" Cognitive Maps with an Application to Mobile Robotics , 2000, Adapt. Behav..

[37]  Marc Toussaint,et al.  A Sensorimotor Map: Modulating Lateral Interactions for Anticipation and Planning , 2006, Neural Computation.

[38]  Evgueniy V. Lubenov,et al.  Hippocampal theta oscillations are travelling waves , 2009, Nature.

[39]  John O'Keefe,et al.  The hippocampal cognitive map and navigational strategies. , 1991 .

[40]  Joshua M. Epstein,et al.  Growing artificial societies , 1996 .

[41]  R. Palmer,et al.  Asset Pricing Under Endogenous Expectations in an Artificial Stock Market , 1996 .

[42]  Wilfried Brauer,et al.  Spatial Cognition III , 2003, Lecture Notes in Computer Science.

[43]  W. Arthur,et al.  The Economy as an Evolving Complex System II , 1988 .

[44]  Hélène Mathian,et al.  SIMPOP: A Multiagent System for the Study of Urbanism , 1997 .

[45]  R. Passingham.  The hippocampus as a cognitive map J. O'Keefe & L. Nadel, Oxford University Press, Oxford (1978). 570 pp., £25.00 , 1979, Neuroscience.

[46]  Toby Tyrrell,et al.  Computational mechanisms for action selection , 1993 .

[47]  Angelo Arleo,et al.  Modelling the Cortical Columnar Organisation for Topological State-Space Representation, and Action Planning , 2008, SAB.

[48]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[49]  Joana Barros,et al.  Simulating urban dynamics in Latin American cities , 2004 .

[50]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[51]  N. Gilbert,et al.  Artificial Societies: The Computer Simulation of Social Life , 1995 .

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

[53]  Philippe Gaussier,et al.  Cognitive map plasticity and imitation strategies to extend the performance of a MAS , 2006, IAS.

[54]  D. Cliff.  From animals to animats , 1994, Nature.

[55]  Philippe Gaussier,et al.  Autonomous learning and reproduction of complexsequences: a multimodal architecture forbootstraping imitation games , 2005 .

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

[57]  Jie Chen,et al.  Towards Energy Optimization: Emergent Task Allocation in a Swarm of Foraging Robots , 2007, Adapt. Behav..

[58]  Philippe Gaussier,et al.  From view cells and place cells to cognitive map learning: processing stages of the hippocampal system , 2002, Biological Cybernetics.

[59]  Richard Szabo.  Topological Navigation of Simulated Robots using Occupancy Grid , 2004, ArXiv.

[60]  I. Benenson,et al.  Entity-Based Modeling of Urban Residential Dynamics: The Case of Yaffo, Tel Aviv , 2002 .

[61]  T. Schelling.  Models of Segregation , 1969 .