Evolving a nervous system of spiking neurons for a behaving robot

We describe the artificial evolution of 'nervous systems' for the ARBIB robot, which control the way it interacts with its environment. The present work differs from earlier attempts to evolve robot controllers by use of a biologically-inspired heterogeneous network of spiking neurons. An obstacle-avoidance task is defined so as to provide an appropriate fitness function for the evolutionary process, and ten separate runs were undertaken in a simulated environment. Evolved nervous systems from 7 of the 10 runs led to an 'emergent' wall-following behaviour. Two of the seven, both having just 7 neurons, are examined and described. They are considerably simpler than our earlier, manually-designed solutions which had some 30-50 neurons, although the latter were additionally capable of ontogenetic (during lifetime) learning. One of the two example nervous system promotes photo-taxis as well as wall-following. These two evolved systems are tested on a real Khepera robot, and behave entirely as expected from the simulations.

[1]  Inman Harvey,et al.  Evolutionary robotics: the Sussex approach , 1997, Robotics Auton. Syst..

[2]  René J. V. Bertin,et al.  Phototaxic Foraging of the Archaepaddler, a Hypothetical Deep-Sea Species , 1998, Artificial Life.

[3]  Robert I. Damper,et al.  Computational modelling of learning and behaviour in small neuronal systems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[4]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[5]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[6]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..

[7]  M. Dawkins,et al.  Darwin and the Emergence of Evolutionary Theories of Mind and Behavior , 1988 .

[8]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

[9]  J. Baldwin.  A New Factor in Evolution , 1896, The American Naturalist.

[10]  Stewart W. Wilson,et al.  Not) Evolving Collective Behaviours in Synthetic Fish , 1996 .

[11]  Prabhas Chongstitvatana,et al.  Using Perturbation to Improve Robustness of Solutions Generated by Genetic Programming for Robot Learning , 1999, J. Circuits Syst. Comput..

[12]  James E. Baker,et al.  Reducing Bias and Inefficienry in the Selection Algorithm , 1987, ICGA.

[13]  Jordan B. Pollack,et al.  Evolutionary Body Building: Adaptive Physical Designs for Robots , 1998, Artificial Life.

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

[15]  Robert I. Damper,et al.  ARBIB: An autonomous robot based on inspirations from biology , 2000, Robotics Auton. Syst..

[16]  Stefano Nolfi,et al.  Learning and Evolution , 1999, Auton. Robots.

[17]  Robert E. Smith,et al.  Combined biological paradigms: A neural, genetics-based autonomous systems strategy , 1997, Robotics Auton. Syst..

[18]  Allen I. Selverston,et al.  A consideration of invertebrate central pattern generators as computational data bases , 1988, Neural Networks.

[19]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[20]  Jari Ojala.  Adaptive behavior with protozoa-inspired dynamics , 1998, Biological Cybernetics.

[21]  Luc Steels,et al.  The artificial life roots of artificial intelligence , 1993 .

[22]  Friedrich Krebs,et al.  Emergent value orientation in self-organization of an animat , 1997 .

[23]  Andreas C. Nearchou,et al.  A Genetic Navigation Algorithm for Autonomous Mobile Robots , 1999, Cybern. Syst..

[24]  Jordan B. Pollack,et al.  Automatic design and manufacture of robotic lifeforms , 2000, Nature.

[25]  Leonard K. Kaczmarek,et al.  The Neuron: Cell and Molecular Biology , 1991 .

[26]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[27]  Moshe Sipper,et al.  Design, Observation, Surprise! A Test of Emergence , 1999, Artificial Life.

[28]  Robert I. Damper,et al.  The Hi-NOON neural simulator and its applications , 2001, Microelectron. Reliab..

[29]  Marco Dorigo,et al.  Alecsys and the AutonoMouse: Learning to control a real robot by distributed classifier systems , 2004, Machine Learning.

[30]  Geoffrey E. Hinton,et al.  How Learning Can Guide Evolution , 1996, Complex Syst..

[31]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.