Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots
复制标题

模块化控制器促进软机器人形态和控制的协同优化

DOI:
10.1145/3583131.3590416
复制
发表时间:
2023
期刊:
Proceedings of the Genetic and Evolutionary Computation Conference
影响因子:
--
通讯作者:
Cheney, Nick
Cheney, Nick
中科院分区:
--
文献类型:
--
作者:
Mertan, Alican;Cheney, Nick

文献摘要

参考文献

被引文献

相似文献

软机器人是机器人研究的一个快速增长的领域,考虑到手动工程复杂,兼容和通常非直观的机器人身体计划和行为的挑战,它将从设计自动化中受益匪浅。有人认为,目前限制软机器人脑-体协同优化的一个主要障碍是机器人控制器与其控制的特定身体计划之间的脆弱专业化,导致过早收敛。在这里,我们认为模块化控制器对机器人身体计划的变化更鲁棒。我们证明了形态突变后的软机器人与模块化控制器的运动性能降低,相对于那些具有类似的全球控制器-导致更适合的后代。此外,我们表明,模块化控制器的可转移性增加,以类似的身体计划,使更有效的脑-体协同优化的软机器人,从而增加了积极的形态突变率和更高的整体性能的进化机器人。我们希望这项工作有助于提供具体的方法来提高软机器人设计自动化在这个特定的设置,同时也提供证据来支持我们更普遍地理解脑-体协同优化的挑战。
Soft robotics is a rapidly growing area of robotics research that would benefit greatly from design automation, given the challenges of manually engineering complex, compliant, and generally non-intuitive robot body plans and behaviors. It has been suggested that a major hurdle currently limiting soft robot brain-body co-optimization is the fragile specialization between a robot's controller and the particular body plan it controls, resulting in premature convergence. Here we posit that modular controllers are more robust to changes to a robot's body plan. We demonstrate a decreased reduction in locomotion performance after morphological mutations to soft robots with modular controllers, relative to those with similar global controllers - leading to fitter offspring. Moreover, we show that the increased transferability of modular controllers to similar body plans enables more effective brain-body co-optimization of soft robots, resulting in an increased rate of positive morphological mutations and higher overall performance of evolved robots. We hope that this work helps provide specific methods to improve soft robot design automation in this particular setting, while also providing evidence to support our understanding of the challenges of brain-body co-optimization more generally.1
不断进化的非晶机器人
DOI: --
发表时间: 2010
期刊: IEEE Symposium on Artificial Life
影响因子: --
作者:
J. Hiller;Hod Lipson
通讯作者: Hod Lipson
基于体素的软机器人传感控制器的进化综合
DOI: --
发表时间: 2019
期刊: Artificial Life Conference Proceedings
影响因子: --
作者:
Jacopo Talamini;Eric Medvet;Alberto Bartoli;A. D. Lorenzo
通讯作者: A. D. Lorenzo
身体材料特性对实体代理神经进化的影响:以基于体素的软机器人为例
DOI: --
发表时间: 2022
期刊: GECCO Companion
影响因子: --
作者:
Eric Medvet;Giorgia Nadizar;F. Pigozzi
通讯作者: F. Pigozzi
Voxcraft-sim,GPU 加速的基于体素的物理引擎
DOI: 10.5281/zenodo.3835152
发表时间: 2020
影响因子: 1.8
作者:
Sida Liu;David Matthews;Sam Kriegman;J. Bongard
通讯作者: J. Bongard
编码和质量多样性对不断进化的 2D 虚拟生物的影响
DOI: --
发表时间: 2022
期刊: GECCO Companion
影响因子: --
作者:
Frank Veenstra;Martin Herring Olsen;K. Glette
通讯作者: K. Glette