Real-World Reproduction of Evolved Robot Morphologies: Automated Categorization and Evaluation

This paper describes the real-world reproduction of a handful of robots selected from a larger sample of simulated models previously generated by an evolutionary algorithm. The five robots, which are selected by automatic clustering to be representative of different morphological niches present in the sample, are constructed in the real world using off-the-shelf motor components, combined with 3D printed structural parts that were automatically generated based on the simulator models. A lab setup, involving evolution of turning gaits for each robot, is used to automate the experiments. The forward walking speeds of the constructed robots are measured, and compared with the simulated speeds. While some of the robots achieve near-identical results, some show a large performance loss compared to their simulated prototypes, underlining the reality gap issue seen in similar previous works.

[1]  Kyrre Glette,et al.  Some distance measures for morphological diversification in generative evolutionary robotics , 2014, GECCO.

[2]  Kyrre Glette,et al.  A hox gene inspired generative approach to evolving robot morphology , 2013, GECCO '13.

[3]  John Bares,et al.  Automated synthesis and optimization of robot configurations: an evolutionary approach , 1999 .

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

[5]  Inman Harvey,et al.  Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics , 1995, ECAL.

[6]  Hod Lipson,et al.  Automatic Design and Manufacture of Soft Robots , 2012, IEEE Transactions on Robotics.

[7]  Phil Husbands,et al.  Crawling Out of the Simulation: Evolving Real Robot Morphologies Using Cheap, Reusable Modules , 2004 .

[8]  Stéphane Doncieux,et al.  The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics , 2013, IEEE Transactions on Evolutionary Computation.

[9]  Thomas Röfer,et al.  Evolutionary Gait-Optimization Using a Fitness Function Based on Proprioception , 2004, RoboCup.

[10]  Mark Yim,et al.  Structure synthesis on-the-fly in a modular robot , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[12]  Masahiro Fujita,et al.  Evolving robust gaits with AIBO , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

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

[14]  Maciej Komosinski,et al.  Comparison of Different Genotype Encodings for Simulated Three-Dimensional Agents , 2002, Artificial Life.

[15]  Joshua Evan Auerbach,et al.  Environmental Influence on the Evolution of Morphological Complexity in Machines , 2014, PLoS Comput. Biol..

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