Improving Evolvability of Morphologies and Controllers of Developmental Soft-Bodied Robots with Novelty Search
Improving Evolvability of Morphologies and Controllers of Developmental Soft-Bodied Robots with Novelty Search
复制标题
DOI：
10.3389/frobt.2015.00033
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
M. Joachimczak;Reiji Suzuki;Takaya Arita
中科院分区：
文献类型：
--
作者：
M. Joachimczak;Reiji Suzuki;Takaya Arita
新颖的搜索是一种基于表面上矛盾的想法，即放弃目标集中的健身功能可以导致发现更高的健身解决方案。在我们的工作过程中，我们创建了一个具有生物学启发的人工发育系统，目的是自动设计复杂的形态和多细胞柔软的机器人的控制器。我们的目标是利用在硅硅进化中的创造潜力，以便为我们提供新颖有效的设计，这些设计不含人类设计师所拥有的任何先入为主的观念。为此，我们努力允许任意形态的演变。使用健身驱动的搜索算法，该系统已被证明能够不断发展复杂的多细胞溶液，包括数百个可以行走，运行和游泳的单元组成的细胞，但可能的较大设计空间使搜索量变得昂贵且容易被粘住在当地的minima中。在这项工作中，我们研究了机器人设计发展的发展方法如何受益于放弃客观健身功能。我们发现，新颖的搜索产生了更好的性能解决方案。然后，我们就新颖搜索的表型表示，共同设计的形态/大脑的欺骗性格局以及基于复杂的开发表型的编码来讨论成功的关键因素。
Novelty search is an evolutionary search algorithm based on the superficially contradictory idea that abandoning goal focused fitness function altogether can lead to the discovery of higher fitness solutions. In the course of our work, we have created a biologically inspired artificial development system with the purpose of automatically designing complex morphologies and controllers of multicellular, soft-bodied robots. Our goal is to harness the creative potential of in silico evolution so that it can provide us with novel and efficient designs that are free of any preconceived notions a human designer would have. In order to do so, we strive to allow for the evolution of arbitrary morphologies. Using a fitness-driven search algorithm, the system has been shown to be capable of evolving complex multicellular solutions consisting of hundreds of cells that can walk, run and swim, yet the large space of possible designs makes the search expensive and prone to getting stuck in local minima. In this work, we investigate how a developmental approach to the evolution of robotic designs benefits from abandoning objective fitness function. We discover that novelty search produced significantly better performing solutions. We then discuss the key factors of the success in terms of the phenotypic representation for the novelty search, the deceptive landscape for co-designing morphology/brain, and the complex development-based phenotypic encoding.