Skip to Main content Skip to Navigation

L'approche par transférabilité : une réponse aux problèmes de passage à la réalité, de généralisation et d'adaptation

Abstract : The design of controllers for robots that have to deal with unknown or poorly controlled environments is a difficult engineering problem. Evolutionary robotics tackles this challenge by developing automatic methods to design controllers that are based on black-box optimization processes using evolutionary algorithms. In this context, the performance values are estimated for each controller either directly on the robot or with a simulation. Assessing performance with the real robot and in all the possible situations is usually not consistent with the evaluation budgets required by these optimization methods. We here propose a general approach, which combines a multi-objective optimization process in a fixed simulation model, a surrogate model and a few experiments on the robot. This transferability approach can be applied to any optimization process conducted in a simplified environment (simulation) for a targeted full environment (robot). It looks for controllers that maximize two objectives: the performance in simulation and a transferability objective, which reflects how well the behavior observed in simulation matches the behavior on the robot. The second objective is estimated by a surrogate model built by performing a few transfer experiments on the robot while optimizing controllers. The approach is applied on three open problems from evolutionary robotics: the reality gap problem, the optimization of controllers with generalization abilities and the adaptation of a robot to its environment.
Document type :
Complete list of metadata
Contributor : Sylvain Koos Connect in order to contact the contributor
Submitted on : Wednesday, July 4, 2012 - 1:15:02 PM
Last modification on : Monday, July 4, 2022 - 11:54:54 AM
Long-term archiving on: : Thursday, December 15, 2016 - 9:07:41 PM


  • HAL Id : tel-00714385, version 1


Sylvain Koos. L'approche par transférabilité : une réponse aux problèmes de passage à la réalité, de généralisation et d'adaptation. Robotique [cs.RO]. Université Pierre et Marie Curie - Paris VI, 2011. Français. ⟨tel-00714385⟩



Record views


Files downloads