Title:

GS6-5 Lessons on the Reality-Gap: Iterations between Virtual and Real Robots

Publication: ICAROB2018
Volume: 23
Pages: 153-156
ISSN: 2188-7829
DOI: 10.5954/ICAROB.2018.GS6-5
Author(s): Andre Rosendo, Charlie Houseago, Fumiya Iida
Publication Date: February 2, 2018
Keywords: Reality gap, evolutionary robotics, virtual robots, design optimization, body-mind co-optimization
Abstract: Due to approximations between the virtual and real world, the knowledge transfer from simulations to robots is problematic. As physical conditions are prone to unknown and stochastic noise sources, the predictability reduces. We use data experiments from 100 real robots to tune the parameters of a simulation, and later used this tuned simulator to improve the design of the previous robots and find the optimum robot. We compare the simulated and observed behavior of this robot, and discuss our results.
PDF File: https://alife-robotics.co.jp/members2018/icarob/data/html/data/GS_pdf/GS6/GS6-5.pdf
Copyright: © The authors.
This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
See for details: https://creativecommons.org/licenses/by-nc/4.0/

ALife Robotics Corporation Ltd.

HOME

 

 

(c)2008 Copyright The Regents of ALife Robotics Corporation Ltd. All Rights Reserved.