Echo state networks for embodied evolution in robotic swarms
Echo state networks for embodied evolution in robotic swarms
复制标题
用于机器人群中体现进化的回声状态网络
DOI:
10.1007/s10015-022-00828-w
复制
发表时间:
2022
影响因子:
0.9
通讯作者:
Kazuhiro Ohkura
中科院分区:
文献类型:
--
作者:
Motoaki Hiraga;Yoshiaki Katada;Kazuhiro Ohkura
Embodied evolution is an evolutionary robotics approach that implements an evolutionary algorithm over a population of robots and evolves while the robots perform their tasks. So far, most studies on embodied evolution utilize relatively simple neural networks as robot controllers. However, a simple structured controller might restrict robot behavior and lead to lower performance. This paper proposes an embodied evolution approach that uses echo state networks as robot controllers. The experiments are conducted using computer simulations, and the controllers are evolved in a two-target navigation task. The results show that the echo state network controllers outperform the conventional controllers.
登录
查看更多内容
影响因子:
0.9
作者:
Wei Yufei;Hiraga Motoaki;Ohkura Kazuhiro;Car Zlatan
通讯作者:
Car Zlatan
影响因子:
3.9
作者:
Heiko Hamann
通讯作者:
Heiko Hamann
DOI:
--
发表时间:
2010
期刊:
--
影响因子:
--
作者:
A. Eiben;E. Haasdijk;Nicolas Bredèche
通讯作者:
Nicolas Bredèche
影响因子:
3.7
作者:
Haasdijk E;Bredeche N;Eiben AE
通讯作者:
Eiben AE
影响因子:
2.6
作者:
Alkilabi, Muhanad H. Mohammed;Narayan, Aparajit;Tuci, Elio
通讯作者:
Tuci, Elio