Morphological change in machines accelerates the evolution of robust behavior

Most animals exhibit significant neurological and morphological change throughout their lifetime. No robots to date, however, grow new morphological structure while behaving. This is due to technological limitations but also because it is unclear that morphological change provides a benefit to the acquisition of robust behavior in machines. Here I show that in evolving populations of simulated robots, if robots grow from anguilliform into legged robots during their lifetime in the early stages of evolution, and the anguilliform body plan is gradually lost during later stages of evolution, gaits are evolved for the final, legged form of the robot more rapidly—and the evolved gaits are more robust—compared to evolving populations of legged robots that do not transition through the anguilliform body plan. This suggests that morphological change, as well as the evolution of development, are two important processes that improve the automatic generation of robust behaviors for machines. It also provides an experimental platform for investigating the relationship between the evolution of development and robust behavior in biological organisms.

[1]  N. A. Bernshteĭn The co-ordination and regulation of movements , 1967 .

[2]  J. Bruner,et al.  The role of tutoring in problem solving. , 1976, Journal of child psychology and psychiatry, and allied disciplines.

[3]  P. Dorato,et al.  Survey of robust control for rigid robots , 1991, IEEE Control Systems.

[4]  D. Tesar,et al.  Control of a six-degree-of-freedom flexible industrial manipulator , 1991, IEEE Control Systems.

[5]  Marco Colombetti,et al.  Robot shaping: developing situated agents through learning , 1992 .

[6]  G. Edelman,et al.  Solving Bernstein's problem: a proposal for the development of coordinated movement by selection. , 1993, Child development.

[7]  Frank L. Lewis,et al.  Neural Network Control of Robot Manipulators , 1996, IEEE Expert.

[8]  L. Altenberg,et al.  PERSPECTIVE: COMPLEX ADAPTATIONS AND THE EVOLUTION OF EVOLVABILITY , 1996, Evolution; international journal of organic evolution.

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

[10]  Jeffrey Ventrella,et al.  Designing Emergence in Animated Artificial Life Worlds , 1998, Virtual Worlds.

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

[12]  A. Clark An embodied cognitive science? , 1999, Trends in Cognitive Sciences.

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

[14]  E. A. Dipaolo,et al.  Homeostatic adaptation to inversion of the visual field and other sensorimotor disruptions , 2000 .

[15]  W. Fontana,et al.  Plasticity, evolvability, and modularity in RNA. , 2000, The Journal of experimental zoology.

[16]  Di Paolo,et al.  Homeostatic adaptation to inversion of the visual field and other sensorimotor disruptions , 2000 .

[17]  Daniel E. Koditschek,et al.  RHex: A Simple and Highly Mobile Hexapod Robot , 2001, Int. J. Robotics Res..

[18]  Jordan B. Pollack,et al.  Creating High-Level Components with a Generative Representation for Body-Brain Evolution , 2002, Artificial Life.

[19]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[20]  Josh Bongard,et al.  Evolving modular genetic regulatory networks , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[21]  Hod Lipson,et al.  ON THE ORIGIN OF MODULAR VARIATION , 2002, Evolution; international journal of organic evolution.

[22]  Maciej Komosin´ski,et al.  The Framsticks system: versatile simulator of 3D agents and their evolution , 2003 .

[23]  P. Husbands,et al.  Local evolvability of statistically neutral GasNet robot controllers. , 2003, Bio Systems.

[24]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[25]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[26]  Hod Lipson,et al.  Three Dimensional Stochastic Reconfiguration of Modular Robots , 2005, Robotics: Science and Systems.

[27]  Inman Harvey,et al.  Evolutionary Robotics: A New Scientific Tool for Studying Cognition , 2005, Artificial Life.

[28]  U. Alon,et al.  Spontaneous evolution of modularity and network motifs. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[29]  Günter P. Wagner,et al.  Complex Adaptations and the Evolution of Evolvability , 2005 .

[30]  Russ Tedrake,et al.  Efficient Bipedal Robots Based on Passive-Dynamic Walkers , 2005, Science.

[31]  E. Borenstein,et al.  Direct evolution of genetic robustness in microRNA. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[32]  C. Ruff,et al.  Who's afraid of the big bad Wolff?: "Wolff's law" and bone functional adaptation. , 2006, American journal of physical anthropology.

[33]  Randall D. Beer,et al.  Parameter Space Structure of Continuous-Time Recurrent Neural Networks , 2006, Neural Computation.

[34]  Hod Lipson,et al.  Resilient Machines Through Continuous Self-Modeling , 2006, Science.

[35]  Marc H. Raibert,et al.  Walking BigDog: Insights and challenges from legged robotics , 2006 .

[36]  R. Pfeifer,et al.  Self-Organization, Embodiment, and Biologically Inspired Robotics , 2007, Science.

[37]  A. Ijspeert,et al.  From Swimming to Walking with a Salamander Robot Driven by a Spinal Cord Model , 2007, Science.

[38]  J. Coyne,et al.  THE LOCUS OF EVOLUTION: EVO DEVO AND THE GENETICS OF ADAPTATION , 2007, Evolution; international journal of organic evolution.

[39]  Guglielmo Tamburrini,et al.  Biorobotic Experiments for the Discovery of Biological Mechanisms* , 2007, Philosophy of Science.

[40]  Gregory S. Chirikjian,et al.  Modular Self-Reconfigurable Robot Systems , 2007 .

[41]  Jun Tani,et al.  Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment , 2008, PLoS Comput. Biol..

[42]  John R. Koza,et al.  Automated ab initio synthesis of complete designs of four patented optical lens systems by means of genetic programming , 2008, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[43]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[44]  Jason D. Lohn,et al.  Human-competitive evolved antennas , 2008, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[45]  Andreas Wagner,et al.  Specialization Can Drive the Evolution of Modularity , 2010, PLoS Comput. Biol..

[46]  N. Tinbergen On aims and methods of Ethology , 2010 .