Skip to Main content Skip to Navigation
Conference papers

Evolutionary Robotics, Anticipation and the Reality Gap

Cedric Hartland 1, 2 Nicolas Bredeche 1, 2
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : Evolutionary Robotics provide efficient tools and approach to address automatic design of controllers for automous mobile robots. However, the computational cost of the optimization process makes it difficult to evolve controllers directly into the real world. This paper addresses the key problem of tranferring into the real world a robotic controller that has been evolved in a robotic simulator. The approach presented here relies on the definition of an anticipation-enabled control architecture. The anticipation module is able to build a partial model of the simulated environment and, once in the real world, performs an error estimation of this model. This error can be reused so as to perform in-situ on-line adaptation of robot control. Experiments in simulation and real-world showed that an evolved robot is able to perform on-line recovery from several kind of locomotion perturbations
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/inria-00120116
Contributor : Cédric Hartland <>
Submitted on : Wednesday, December 13, 2006 - 12:44:16 PM
Last modification on : Thursday, March 18, 2021 - 12:16:03 PM
Long-term archiving on: : Thursday, September 20, 2012 - 3:55:44 PM

File

robios2006.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00120116, version 1

Collections

Citation

Cedric Hartland, Nicolas Bredeche. Evolutionary Robotics, Anticipation and the Reality Gap. ROBIO 2006, Dec 2006, Kunming/Chine, China. pp.1640-1645. ⟨inria-00120116⟩

Share

Metrics

Record views

483

Files downloads

384