Analysis of Lamarckian evolution in morphologically evolving robots

Evolving robot morphologies implies the need for lifetime learning so that newborn robots can learn to manipulate their bodies. An individual’s morphology will obviously combine traits of all its parents; it must adapt its own controller to suit its morphology, and cannot rely on the controller of any one parent to perform well without adaptation. This paper investigates the practicability and benefits of Lamarckian evolution in this setting. Implementing lifetime learning by means of on-line evolution, we first establish the suitability of an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers. We then analyze a Lamarckian set-up and the effect of the parental genetic material on the early convergence to good locomotion performance.

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

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

[3]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[4]  Fumiya Iida,et al.  Embodied Artificial Intelligence: Trends and Challenges , 2003, Embodied Artificial Intelligence.

[5]  Jordan B. Pollack,et al.  TITLE : Generative Representations for the Automated Design of Modular Physical Robots , 2003 .

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

[7]  Auke Jan Ijspeert,et al.  Learning to Move in Modular Robots using Central Pattern Generators and Online Optimization , 2008, Int. J. Robotics Res..

[8]  Jan Peters,et al.  Learning motor primitives for robotics , 2009, 2009 IEEE International Conference on Robotics and Automation.

[9]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[10]  Wenguo Liu,et al.  Autonomous Morphogenesis in Self-assembling Robots Using IR-Based Sensing and Local Communications , 2010, ANTS Conference.

[11]  A. E. Eiben,et al.  HyperNEAT for Locomotion Control in Modular Robots , 2010, ICES.

[12]  Kenneth O. Stanley,et al.  Evolving a diversity of virtual creatures through novelty search and local competition , 2011, GECCO '11.

[13]  Kenneth O. Stanley,et al.  On the Performance of Indirect Encoding Across the Continuum of Regularity , 2011, IEEE Transactions on Evolutionary Computation.

[14]  A. E. Eiben,et al.  Exploratory analysis of an on-line evolutionary algorithm in simulated robots , 2012, Evol. Intell..

[15]  Darwin G. Caldwell,et al.  Learning Fast Quadruped Robot Gaits with the RL PoWER Spline Parameterization , 2012 .

[16]  A. E. Eiben,et al.  Online Gait Learning for Modular Robots with Arbitrary Shapes and Sizes , 2013, TPNC.

[17]  Hod Lipson,et al.  Unshackling evolution , 2014 .

[18]  Dario Floreano,et al.  RoboGen: Robot Generation through Artificial Evolution , 2014, ALIFE.

[19]  B. Dias,et al.  Parental olfactory experience influences behavior and neural structure in subsequent generations , 2013, Nature Neuroscience.

[20]  A. E. Eiben,et al.  From evolutionary computation to the evolution of things , 2015, Nature.

[21]  A. E. Eiben,et al.  Improving RL power for on-line evolution of gaits in modular robots , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[22]  Hod Lipson,et al.  On the Difficulty of Co-Optimizing Morphology and Control in Evolved Virtual Creatures , 2016, ALIFE.

[23]  A. E. Eiben,et al.  Benefits of lamarckian evolution for morphologically evolving robots , 2017, GECCO.