The trade-off between morphology and control in the co-optimized design of robots

doi:10.1371/journal.pone.0186107

	The trade-off between morphology and control in the co-optimized design of robots
	Rosendo, Andre1,2 ; von Atzigen, Marco 3; Iida, Fumiya 1,3
	2017-10-12
发表期刊	PLOS ONE
ISSN	1932-6203
卷号	12 期号:10
发表状态	已发表
DOI	10.1371/journal.pone.0186107
摘要	Conventionally, robot morphologies are developed through simulations and calculations, and different control methods are applied afterwards. Assuming that simulations and predictions are simplified representations of our reality, how sure can roboticists be that the chosen morphology is the most adequate for the possible control choices in the real-world? Here we study the influence of the design parameters in the creation of a robot with a Bayesian morphology-control (MC) co-optimization process. A robot autonomously creates child robots from a set of possible design parameters and uses Bayesian Optimization (BO) to infer the best locomotion behavior from real world experiments. Then, we systematically change from an MC co-optimization to a control-only (C) optimization, which better represents the traditional way that robots are developed, to explore the trade-off between these two methods. We show that although C processes can greatly improve the behavior of poor morphologies, such agents are still outperformed by MC co-optimization results with as few as 25 iterations. Our findings, on one hand, suggest that BO should be used in the design process of robots for both morphological and control parameters to reach optimal performance, and on the other hand, point to the downfall of current design methods in face of new search techniques.
收录类别	SCI
语种	英语
资助项目	RoboSoft Coordination Action project (FP7-ICT-C project)[619319]
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000412845100064
出版者	PUBLIC LIBRARY SCIENCE
原始文献类型	Article
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/9904
专题	信息科学与技术学院信息科学与技术学院_PI研究组_ANDRE LUIS MACEDO ROSENDO SILVA组
通讯作者	Rosendo, Andre
作者单位	1.Univ Cambridge, Dept Engn, Cambridge, England 2.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 3.ETH, Inst Robot & Intelligent Syst, Zurich, Switzerland
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Rosendo, Andre,von Atzigen, Marco,Iida, Fumiya. The trade-off between morphology and control in the co-optimized design of robots[J]. PLOS ONE,2017,12(10).
APA	Rosendo, Andre,von Atzigen, Marco,&Iida, Fumiya.(2017).The trade-off between morphology and control in the co-optimized design of robots.PLOS ONE,12(10).
MLA	Rosendo, Andre,et al."The trade-off between morphology and control in the co-optimized design of robots".PLOS ONE 12.10(2017).