Adaptive CGFs Based on Grammatical Evolution

Adaptive CGFs Based on Grammatical Evolution
复制标题

基于语法进化的自适应 CGF

DOI:
10.1155/2015/197306
复制
发表时间:
2015-12
影响因子:
--
通讯作者:
Wang, Weiping
Wang, Weiping
中科院分区:
工程技术4区
文献类型:
--
作者:
Yao, Jian;Huang, Qiwang;Wang, Weiping

文献摘要

参考文献

相似文献

计算机生成部队(CGF)在军事模拟中扮演蓝色或红色单位,以进行人员培训和武器系统评估。传统上,CGF 是通过基于规则的脚本进行控制的,尽管 CGF 的理论驱动行为是严格且可预测的。此外,CGF经常被学员欺骗或无法适应新情况(例如战场变化或武器系统更新),并且在大多数情况下,主题专家(SME)针对新场景或训练任务审查和重新设计大量CGF脚本,这既具有挑战性又耗时。为了克服这些限制并走向更真实的场景,我们进行了一项使用语法进化 (GE) 来生成用于空战模拟的自适应 CGF 的研究。专家知识采用模块化行为树 (BT) 进行编码,以便与遗传算法 (GA) 中的运算符兼容。 GE 将用 BT 表示的 CGF 映射为二进制字符串,并使用 GA 通过模拟的性能反馈来演化 CGF。为了观察和研究这一进化过程,人们在自适应 CGF 和非自适应基线 CGF 之间进行了超视距空战实验。实验结果表明,GE 是一种以 BT 形式主义生成 CGF 并通过 GA 演化 CGF 的有效框架。
Computer generated forces (CGFs) play blue or red units in military simulations for personnel training and weapon systems evaluation. Traditionally, CGFs are controlled through rule-based scripts, despite the doctrine-driven behavior of CGFs being rigid and predictable. Furthermore, CGFs are often tricked by trainees or fail to adapt to new situations (e.g., changes in battle field or update in weapon systems), and, in most cases, the subject matter experts (SMEs) review and redesign a large amount of CGF scripts for new scenarios or training tasks, which is both challenging and time-consuming. In an effort to overcome these limitations and move toward more true-to-life scenarios, a study using grammatical evolution (GE) to generate adaptive CGFs for air combat simulations has been conducted. Expert knowledge is encoded with modular behavior trees (BTs) for compatibility with the operators in genetic algorithm (GA). GE maps CGFs, represented with BTs to binary strings, and uses GA to evolve CGFs with performance feedback from the simulation. Beyond-visual-range air combat experiments between adaptive CGFs and nonadaptive baseline CGFs have been conducted to observe and study this evolutionary process. The experimental results show that the GE is an efficient framework to generate CGFs in BTs formalism and evolve CGFs via GA.
DOI: 10.2514/1.17168
发表时间: 2006-09
影响因子: 2.6
作者:
Kai Virtanen;Janne Karelahti;T. Raivio
通讯作者: Kai Virtanen;Janne Karelahti;T. Raivio
DOI: --
发表时间: 2014
期刊: The 2012 International Joint Conference on Neural Networks (IJCNN)
影响因子: --
作者:
A. Toubman;J. Roessingh;P. Spronck;A. Plaat;H. J. Herik
通讯作者: A. Toubman;J. Roessingh;P. Spronck;A. Plaat;H. J. Herik
DOI: 10.1162/artl.1997.3.1.63
发表时间: 1997
期刊: Artificial Life
影响因子: 2.6
作者:
D. Heiss-Czedik
通讯作者: D. Heiss-Czedik
DOI: 10.1109/syscon.2013.6549953
发表时间: 2013-04
期刊: 2013 IEEE International Systems Conference (SysCon)
影响因子: --
作者:
S. Mittal;Margery J. Doyle;Eric Watz
通讯作者: S. Mittal;Margery J. Doyle;Eric Watz
DOI: --
发表时间: 2013-04
期刊: --
影响因子: --
作者:
Simon J. E. Taylor;Azam Khan;K. L. Morse;A. Tolk;L. Yilmaz;Justyna Zander
通讯作者: Simon J. E. Taylor;Azam Khan;K. L. Morse;A. Tolk;L. Yilmaz;Justyna Zander