Crossing the Reality Gap in Evolutionary Robotics by Promoting Transferable Controllers

Abstract : The reality gap, that often makes controllers evolved in simulation inefficient once transferred onto the real system, remains a critical issue in Evolutionary Robotics (ER); it prevents ER application to real-world problems. We hypothesize that this gap mainly stems from a conflict between the efficiency of the solutions in simulation and their transferability from simulation to reality: best solutions in simulation often rely on bad simulated phenomena (e.g. the most dynamic ones). This hypothesis leads to a multi-objective formulation of ER in which two main objectives are optimized via a Pareto-based Multi-Objective Evolutionary Algorithm: (1) the fitness and (2) the transferability. To evaluate this second objective, a simulation-to-reality disparity value is approximated for each controller. The proposed method is applied to the evolution of walking controllers for a real 8-DOF quadrupedal robot. It successfully finds effi- cient and well-transferable controllers with only a few experiments in reality.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download
Contributor : Sylvain Koos <>
Submitted on : Wednesday, October 19, 2011 - 6:28:53 PM
Last modification on : Thursday, March 21, 2019 - 2:42:23 PM
Long-term archiving on : Friday, January 20, 2012 - 10:28:03 AM


Files produced by the author(s)


  • HAL Id : hal-00633927, version 1


Sylvain Koos, Jean-Baptiste Mouret, Stéphane Doncieux. Crossing the Reality Gap in Evolutionary Robotics by Promoting Transferable Controllers. Conference on Genetic and Evolutionary Computation, Jul 2010, United States. pp.119-126. ⟨hal-00633927⟩



Record views


Files downloads