Evolving robots able to self-localize in the environment: the importance of viewing cognition as the result of processes occurring at different time-scales

In this paper we address the problem of synthesizing mobile robots able to solve problems in which they cannot merely react to sensory input, but have to maintain an internal state as well. More precisely, we shall show how autonomous robots synthesized through an evolutionary process can solve problems that necessarily require an ability to integrate sensorimotor information over time. By presenting the result of a set of experiments in which evolving robots are asked to navigate and self-localize in the environment, we shall show that successful results can be achieved by providing evolving individuals with neural controllers with neurons that: (a) vary their activity at different rates to detect regularities at different time-scales in the sensorimotor flow; and (b) use thresholded activation functions to detect events extending over time.

[1]  H. Maturana,et al.  Autopoiesis and Cognition , 1980 .

[2]  Stefano Nolfi,et al.  Evolving robots able to integrate sensory-motor information over time , 2001, Theory in Biosciences.

[3]  Joel L. Davis,et al.  Adaptive Critics and the Basal Ganglia , 1995 .

[4]  Inman Harvey,et al.  Evolving integrated controllers for autonomous learning robots using dynamic neural networks , 2002 .

[5]  Tom Ziemke.  On 'Parts' and 'Wholes' of Adaptive Behavior: Functional Modularity and Diachronic Structure in Recurrent Neural Robot Controllers , 2000 .

[6]  Tracy Brown,et al.  The Embodied Mind: Cognitive Science and Human Experience , 2002, Cybern. Hum. Knowing.

[7]  Stewart W. Wilson,et al.  From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior , 1997 .

[8]  Stefano Nolfi,et al.  Power and the limits of reactive agents , 2002, Neurocomputing.

[9]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[10]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[11]  A. Clark.  Being There: Putting Brain, Body, and World Together Again , 1996 .

[12]  William Bialek,et al.  Spikes: Exploring the Neural Code , 1996 .

[13]  H. Maturana,et al.  Autopoiesis and Cognition : The Realization of the Living (Boston Studies in the Philosophy of Scie , 1980 .

[14]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[15]  Stanley J. Rosenschein,et al.  A dynamical systems perspective on agent-environment interaction , 1996 .

[16]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[17]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[18]  T. Gelder,et al.  It's about time: an overview of the dynamical approach to cognition , 1996 .

[19]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[20]  W. Schultz,et al.  Context-dependent activity in primate striatum reflecting past and future behavioral events. , 1995 .

[21]  F. Keijzer.  Representation and Behavior , 2001 .

[22]  H. Maturana,et al.  The Tree of Knowledge: The Biological Roots of Human Understanding , 2007 .

[23]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[24]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[25]  R. Miller.  Time and the brain , 2000 .

[26]  S. Nolfi.  Evorobot 1 . 1 User Manual , 2000 .