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
Jones S
中科院分区:
计算机科学3区
文献类型:
--
作者:
Jones S

文献摘要

参考文献

被引文献

相似文献

设计个体机器人规则以产生期望的涌现群体行为是困难的。在仿真中离线运行进化算法来自动发现控制器的常见方法有两个缺点:控制器的生成不在群中,因此不能在野外执行,并且进化的控制器通常是不透明的,难以理解。具有相当大的机载处理能力的机器人群用于将进化过程转移到群中,为不断生成适应当前环境和任务的群行为提供了一条潜在途径。通过使用行为树使进化的控制器人类可理解,控制器可以由人类用户查询,解释甚至改进。一个群系统能够发展和执行适合控制器完全板载物理机器人在不到15分钟的演示。然后分析其中一个进化的控制器以解释其功能。随着获得的见解,一个显着的性能改进,在进化的控制器工程。
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.
SWARM-BOT 中的超线性物理性能
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
觅食机器人
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
群体机器人自组织行为进化的工程设计:案例研究
DOI: --
发表时间: 2011
期刊: Artificial Life
影响因子: 2.6
作者:
V. Trianni;S. Nolfi
通讯作者: S. Nolfi