Onboard Evolution of Understandable Swarm Behaviors
Onboard Evolution of Understandable Swarm Behaviors
复制标题
可理解的群体行为的机载进化
DOI:
10.1002/aisy.201900031
复制
发表时间:
2019
影响因子:
7.4
通讯作者:
Jones S
中科院分区:
文献类型:
--
作者:
Jones S
Designing the individual robot rules that give rise to desired emergent swarm behaviors is difficult. The common method of running evolutionary algorithms off‐line to automatically discover controllers in simulation suffers from two disadvantages: the generation of controllers is not situated in the swarm and so cannot be performed in the wild, and the evolved controllers are often opaque and hard to understand. A swarm of robots with considerable on‐board processing power is used to move the evolutionary process into the swarm, providing a potential route to continuously generating swarm behaviors adapted to the environments and tasks at hand. By making the evolved controllers human‐understandable using behavior trees, the controllers can be queried, explained, and even improved by a human user. A swarm system capable of evolving and executing fit controllers entirely onboard physical robots in less than 15 min is demonstrated. One of the evolved controllers is then analyzed to explain its functionality. With the insights gained, a significant performance improvement in the evolved controller is engineered.
登录
查看更多内容
DOI:
--
发表时间:
2005
期刊:
European Conference on Artificial Life
影响因子:
--
作者:
F. Mondada;M. Bonani;A. Guignard;Stéphane Magnenat;Christian Studer;D. Floreano
通讯作者:
D. Floreano
DOI:
--
发表时间:
2009
期刊:
Encyclopedia of Complexity and Systems Science
影响因子:
--
作者:
A. Winfield
通讯作者:
A. Winfield
DOI:
10.1007/bfb0027170
发表时间:
1997-04
期刊:
--
影响因子:
--
作者:
L. D. Whitley;Soraya B. Rana;Robert B. Heckendorn
通讯作者:
L. D. Whitley;Soraya B. Rana;Robert B. Heckendorn
DOI:
10.2514/6.2014-0611
发表时间:
2014-01
期刊:
--
影响因子:
--
作者:
S. J. Gill;M. Lowenberg;L. Crespo;S. Neild;B. Krauskopf;G. Puyou
通讯作者:
S. J. Gill;M. Lowenberg;L. Crespo;S. Neild;B. Krauskopf;G. Puyou
影响因子:
2.6
作者:
V. Trianni;S. Nolfi
通讯作者:
S. Nolfi