Lamarckian Evolution of Simulated Modular Robots.
Lamarckian Evolution of Simulated Modular Robots.
复制标题
DOI:
10.3389/frobt.2019.00009
复制
发表时间:
2019
影响因子:
3.4
通讯作者:
Eiben AE
中科院分区:
文献类型:
--
作者:
Jelisavcic M;Glette K;Haasdijk E;Eiben AE
We study evolutionary robot systems where not only the robot brains but also the robot bodies are evolvable. Such systems need to include a learning period right after ‘birth' to acquire a controller that fits the newly created body. In this paper we investigate the possibility of bootstrapping infant robot learning through employing Lamarckian inheritance of parental controllers. In our system controllers are encoded by a combination of a morphology dependent component, a Central Pattern Generator (CPG), and a morphology independent part, a Compositional Pattern Producing Network (CPPN). This makes it possible to transfer the CPPN part of controllers between different morphologies and to create a Lamarckian system. We conduct experiments with simulated modular robots whose fitness is determined by the speed of locomotion, establish the benefits of inheriting optimized parental controllers, shed light on the conditions that influence these benefits, and observe that changing the way controllers are evolved also impacts the evolved morphologies.
登录
查看更多内容
影响因子:
2.6
作者:
Eiben, A E;Kernbach, S;Haasdijk, Evert
通讯作者:
Haasdijk, Evert
影响因子:
14.3
作者:
Clune, Jeff;Stanley, Kenneth O.;Ofria, Charles
通讯作者:
Ofria, Charles
影响因子:
25
作者:
Dias, Brian G.;Ressier, Kerry J.
通讯作者:
Ressier, Kerry J.
影响因子:
3.7
作者:
Brodbeck L;Hauser S;Iida F
通讯作者:
Iida F
DOI:
10.1016/j.engappai.2013.09.009
发表时间:
2013-11-01
影响因子:
8
作者:
Faina, Andres;Bellas, Francisco;Duro, Richard J.
通讯作者:
Duro, Richard J.