航空学报 > 2023, Vol. 44 Issue (14): 328003-328003   doi: 10.7527/S1000-6893.2022.28003

基于群体OODA的无人集群系统智能评价模型及方法

沈博(), 武文亮, 杨刚, 周兴社   

  1. 西北工业大学 计算机学院,西安 710129
  • 收稿日期:2022-09-14 修回日期:2022-09-28 接受日期:2022-11-21 出版日期:2022-12-08 发布日期:2022-12-06
  • 通讯作者: 沈博 E-mail:shen@nwpu.edu.cn
  • 基金资助:
    国家自然科学基金(61902295);国防科技创新区(18-163-11-ZT-003-010-01);国家重点研发计划(2017YFB1001900);中央高校基本科研业务费专项资金(D5000210108)

Evaluation models and methods for intelligence of unmanned swarm systems based on collective OODA loop

Bo SHEN(), Wenliang WU, Gang YANG, Xingshe ZHOU   

  1. School of Computer and Engineering,Northwestern Polytechnical University,Xi’an 710129,China
  • Received:2022-09-14 Revised:2022-09-28 Accepted:2022-11-21 Online:2022-12-08 Published:2022-12-06
  • Contact: Bo SHEN E-mail:shen@nwpu.edu.cn
  • Supported by:
    National Natural Science Foundation of China(61902295);National Defence Science and Technology Innovation Zone(18-163-11-ZT-003-010-01);National key Research and Development Project(2017YFB1001900);Basic Scientific Research Funds of the Central Universities(D5000210108)

摘要:

随着无人系统、智能技术的发展以及应用日趋复杂,由若干无人系统在一定时间与空间内自主协同完成任务的智能无人集群系统得以快速涌现,其可有效提高完成复杂任务的能力,在国防装备与国民经济等领域具有重要且广泛的应用前景。无人集群系统的智能评价具有场景多样、指标多维、方法多类等特征,是极具挑战性的研究问题。本文在分析无人集群系统智能评价已有相关研究基础上,结合国家科研项目,基于群体观察-判断-决策-执行(OODA)行为模型提出了评价协同演化模型及适应群体OODA的等级评价标准,进而提出场景驱动的评价过程与适应性评价方法,设计开发自主评价工具集,并结合无人集群系统(USS)及其典型应用场景进行了初步验证。

关键词: 无人集群, 智能评价, 评价指标, 场景驱动, 评价模型

Abstract:

With the rapid development of unmanned systems and intelligent techniques, as well as the increasing complexity of the applications, intelligent unmanned swarm systems have developed rapidly. Unmanned swarms can effectively complete complex tasks via networking cooperation, and have demonstrated their potentials in the fields of defense equipment and national economy. At the same time, intelligence evaluation of unmanned swarms involves diverse scenarios, multidimensional indexes, and multi-class methods. It is quite a challenging research field. Supported by national research projects, this paper proposes the co-evolution model and the level-evaluation model based on collective Observe-Orient-Decide-Act (OODA) loop. Then. the scenario-driven evaluation process, evaluation methods and evaluation platform are proposed. A preliminary validation of the results is also conducted with Unmanned Swarm System (USS).

Key words: unmanned swarm, intelligence evaluation, evaluation metric, scenario driven, evaluation model

中图分类号: