Chiba Naoaki, Suzuki Reiji, Arita Takaya
Graduate School of Information Science, Nagoya University, Nagoya, Japan.
Graduate School of Informatics, Nagoya University, Nagoya, Japan.
Front Robot AI. 2020 Apr 9;7:45. doi: 10.3389/frobt.2020.00045. eCollection 2020.
Niche construction is a process in which organisms modify the selection pressures on themselves and others through their ecological activities, and ecological inheritance is the consequence of niche construction inherited through generations. However, it is still unclear how such mutual interactions between robots or embodied agents and their physical environments can yield complex and divergent evolutionary processes or an open-ended evolution. Our purpose is to clarify what kind of complex and various niche-constructing behaviors evolve in a physically grounded environment under various conditions of ecological inheritance of constructed structures and spatial relationships. We focus on a predator-prey relationship, and constructed an evolutionary model in which a prey creature has to avoid predation through the construction of a structure composed of objects in a 2D physically simulated environment supported by a physics engine. We used a deep auto-encoder to extract the defining feature of adaptive structures automatically. The results in the case of no ecological inheritance revealed that the number of available resources can affect the diversity of emerging adaptive structures. Also, in the case with ecological inheritance, it was found that combinations of two types of ecological inheritance, which are the inheritance of adaptive structures and birthplace, can have strong effects on the diversity of emerging structures and the adaptivity of the population. We expect that findings in evolutionary simulations of niche-constructing behavior might contribute to evolutionary design of robotic builders or robot fabrication, especially when we assume physically simulated environments.
生态位构建是生物体通过其生态活动改变自身及其他生物体所面临的选择压力的过程,而生态遗传则是生态位构建经多代传承的结果。然而,机器人或具身智能体与其物理环境之间的这种相互作用如何能够产生复杂多样的进化过程或开放式进化,目前仍不清楚。我们的目的是阐明在构建结构和空间关系的各种生态遗传条件下,在物理环境中会进化出何种复杂多样的生态位构建行为。我们聚焦于捕食者 - 猎物关系,并构建了一个进化模型,在该模型中,猎物生物必须在由物理引擎支持的二维物理模拟环境中通过构建由物体组成的结构来避免被捕食。我们使用深度自动编码器自动提取适应性结构的定义特征。无生态遗传情况下的结果表明,可用资源的数量会影响新出现的适应性结构的多样性。此外,在有生态遗传的情况下,发现适应性结构的遗传和出生地这两种生态遗传类型的组合,会对新出现结构的多样性和种群的适应性产生强烈影响。我们期望生态位构建行为进化模拟的研究结果可能有助于机器人建造者的进化设计或机器人制造,特别是当我们假设物理模拟环境时。