A method for isolating morphological effects on evolved behaviour

As the field of embodied cognitive science begins to mature, it is imperative to develop methods for identifying and quantifying the constraints and opportunities an agent's body places on its possible behaviours. In this paper we present results from a set of experiments conducted on 10 different legged agents, in which we evolve neural controllers for locomotion. The genetic algorithm and neural network architecture were kept constant across the agent set, but the agents had different sizes, masses and body plans. It was found that increased mass has a negative effect on the evolution of locomotion, but that this does not hold for all of the agents tested. Also, the number of legs has an effect on evolved behaviours, with hexapedal agents being the easiest for which to evolve locomotion, and wormlike agents being the most difficult. Moreover, it was found that repeating the experiments with a larger neural network increased the evolutionary potential of some of the agents, but not for all of them. The results suggest that by employing this methodology we can test hypotheses about the behavioural effect of specific morphological features, which has to date eluded precise quantitative analysis.

[1]  Tucker R. Balch,et al.  Hierarchic Social Entropy: An Information Theoretic Measure of Robot Group Diversity , 2000, Auton. Robots.

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

[3]  Lynne E. Parker,et al.  ALLIANCE: an architecture for fault tolerant, cooperative control of heterogeneous mobile robots , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[4]  Kohki Kikuchi,et al.  Evolutionary design of morphology and intelligence in robotic system using genetic programming , 1998 .

[5]  Chandana Paul,et al.  Making Evolution an Offer It Can't Refuse: Morphology and the Extradimensional Bypass , 2001, ECAL.

[6]  Frédéric Gruau,et al.  Cellular Encoding for interactive evolutionary robotics , 1996 .

[7]  A. Ijspeert,et al.  Visual tracking in simulated salamander locomotion , 2000 .

[8]  R A Brooks,et al.  New Approaches to Robotics , 1991, Science.

[9]  Demetri Terzopoulos,et al.  Artificial fishes: Autonomous locomotion, perception, behavior, and learning in a simulated physical world , 1994 .

[10]  Francesco Mondada,et al.  Evolutionary neurocontrollers for autonomous mobile robots , 1998, Neural Networks.

[11]  Demetri Terzopoulos,et al.  Artificial Fishes: Autonomous Locomotion, Perception, Behavior, and Learning in a Simulated Physical World , 1994, Artificial Life.

[12]  Holk Cruse.  Coordination of leg movement in walking animals , 1991 .

[13]  Karl Sims,et al.  Evolving 3D Morphology and Behavior by Competition , 1994, Artificial Life.

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

[15]  Stefano Nolfi,et al.  Evolving Mobile Robots in Simulated and Real Environments , 1995, Artificial Life.

[16]  R. Pfeifer,et al.  Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny , 2001 .

[17]  Maciej Komosinski,et al.  The World of Framsticks: Simulation, Evolution, Interaction , 2000, Virtual Worlds.

[18]  Colm Massey,et al.  Recent Developments in the Evolution of Morphologies and Controllers for Physically Simulated Creatures , 2000, Artificial Life.

[19]  Domenico Parisi,et al.  Evolving organisms that can reach for objects , 1991 .

[20]  Nick Jakobi,et al.  Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis , 1997, Adapt. Behav..

[21]  John Hallam,et al.  Evolving robot morphology , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[22]  Jeffrey J. Ventrella,et al.  Explorations in the emergence of morphology a~d locomotion behavior in animated characters , 1994 .

[23]  Torsten Reil,et al.  Biologically inspired control of physically simulated bipeds , 2001, Theory in Biosciences.

[24]  Chandana Paul,et al.  The road less travelled: morphology in the optimization of biped robot locomotion , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[25]  Akio Ishiguro,et al.  The Effect of Neuromodulations on the Adaptability of Evolved Neurocontrollers , 2001, ECAL.