Real world morphological evolution is feasible

Evolutionary algorithms offer great promise for the automatic design of robot bodies, tailoring them to specific environments or tasks. Most research is done on simplified models or virtual robots in physics simulators, which do not capture the natural noise and richness of the real world. Very few of these virtual robots are built as physical robots, and the few that are will rarely be further improved in the actual environment they operate in, limiting the effectiveness of the automatic design process. We utilize our shape-shifting quadruped robot, which allows us to optimize the design in its real-world environment. The robot is able to change the length of its legs during operation, and is robust enough for complex experiments and tasks. We have co-evolved control and morphology in several different scenarios, and have seen that the algorithm is able to exploit the dynamic morphology solely through real-world experiments.

[1]  Kyrre Glette,et al.  Real-world evolution adapts robot morphology and control to hardware limitations , 2018, GECCO.

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

[3]  Kyrre Glette,et al.  Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds , 2019, EvoApplications.

[4]  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).

[5]  Frédéric Maire,et al.  Towards the targeted environment-specific evolution of robot components , 2018, GECCO.

[6]  Kyrre Glette,et al.  Environmental Adaptation of Robot Morphology and Control through Real-world Evolution , 2020, ArXiv.

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

[8]  Kyrre Glette,et al.  Experiences from Real-World Evolution with DyRET: Dynamic Robot for Embodied Testing , 2019 .

[9]  Kyrre Glette,et al.  Exploring Mechanically Self-Reconfiguring Robots for Autonomous Design , 2018, ArXiv.

[10]  A. E. Eiben,et al.  Grand Challenges for Evolutionary Robotics , 2014, Front. Robot. AI.

[11]  F. Iida,et al.  Morphological Evolution of Physical Robots through Model-Free Phenotype Development , 2015, PloS one.

[12]  Kyrre Glette,et al.  Self-Modifying Morphology Experiments with DyRET: Dynamic Robot for Embodied Testing , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[13]  Matthew Garratt,et al.  Towards crossing the reality gap with evolved plastic neurocontrollers , 2020, GECCO.

[14]  Jean-Baptiste Mouret,et al.  20 years of reality gap: a few thoughts about simulators in evolutionary robotics , 2017, GECCO.

[15]  Javaan Chahl,et al.  Sim2real gap is non-monotonic with robot complexity for morphology-in-the-loop flapping wing design , 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Navinda Kottege,et al.  A testbed that evolves hexapod controllers in hardware , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

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

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

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

[20]  Kyrre Glette,et al.  Evolved embodied phase coordination enables robust quadruped robot locomotion , 2019, GECCO.