基于群体OODA的无人集群系统智能评价模型及方法
收稿日期: 2022-09-14
修回日期: 2022-09-28
录用日期: 2022-11-21
网络出版日期: 2022-12-06
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
Received date: 2022-09-14
Revised date: 2022-09-28
Accepted date: 2022-11-21
Online published: 2022-12-06
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)
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。
沈博 , 武文亮 , 杨刚 , 周兴社 . 基于群体OODA的无人集群系统智能评价模型及方法[J]. 航空学报, 2023 , 44(14) : 328003 -328003 . DOI: 10.7527/S1000-6893.2022.28003
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).
1 | BENI G, WANG J. Swarm intelligence in cellular robotic systems[M]∥In: DARIO P, SANDINI G, AEBISCHER P, editors. Robots and Biological Systems: Towards a New Bionics? Berlin: Springer, 1993: 703-712. |
2 | ZOMAYA A Y. Handbook of nature-inspired and innovative computing[M]. Berlin: Springer, 2006: 187-219. |
3 | PAN Y H. Heading toward artificial intelligence 2.0[J]. Engineering, 2016, 2(4): 409-413. |
4 | 郭斌, 於志文. 人机物融合群智计算[J]. 中国计算机学会通迅, 2021, 17:35-40. |
GUO B, YU Z. Crowd intelligence with the deep fusion of human, machine and IoT[J]. Communication of The Chinese Computer Society, 2021, 17:35-40 (in Chinese). | |
5 | 国务院. 新一代人工智能发展规划[EB/OL]. (2017-07-20) [2022-07-25]. . |
Department State. Development plan of new generation AI[EB/OL]. (2017-07-20). [2022-07-25]. . | |
6 | WU C, ZHANG T. Intelligent unmanned systems: Important achievements and applications of new generation artificial intelligence[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(5): 649-651. |
7 | 樊邦奎, 张瑞雨. 无人机系统与人工智能[J]. 武汉大学学报(信息科学版), 2017, 42(11): 1523-1529. |
FAN B K, ZHANG R Y. Unmanned aircraft system and artificial intelligence[J]. Geomatics and Information Science of Wuhan University, 2017, 42(11): 1523-1529 (in Chinese). | |
8 | SCHRANZ M, DI CARO G A, SCHMICKL T, et al. Swarm Intelligence and cyber-physical systems: Concepts, challenges and future trends[J]. Swarm and Evolutionary Computation, 2021, 60(2): 100762. |
9 | DORIGO M, THERAULAZ G, TRIANNI V. Swarm robotics: Past, present, and future[J]. Proceedings of the IEEE, 2021, 109(7): 1152-1165. |
10 | CHEN J, SUN J, WANG G. From unmanned systems to autonomous intelligent systems[J]. Engineering, 2022, 12: 16-19. |
11 | CHUNG S J, PARANJAPE A A, DAMES P, et al. A survey on aerial swarm robotics[J]. IEEE Transactions on Robotics, 2018, 34(4): 837-855. |
12 | DORIGO M, THERAULAZ G, TRIANNI V. Reflections on the future of swarm robotics[J]. Science Robotics, 2020, 5(49): eabe4385. |
13 | HAMANN H. Swarm robotics: A formal approach[M]. Berlin: Springer, 2018:6-8. |
14 | 武文亮, 周兴社, 沈博, 等. 集群机器人系统特性评价研究综述[J]. 自动化学报, 2022, 48(5): 1153-1172. |
WU W L, ZHOU X S, SHEN B, et al. A review of swarm robotic systems property evaluation research[J]. Acta Automatica Sinica, 2022, 48(5): 1153-1172 (in Chinese). | |
15 | ZHANG K, YANG Z, BASAR T. Multi-agent reinforcement learning: A selective overview of theories and algorithms[M]. Hanadbook of Reinforcement Learning and Control. Berlin: Springer, 2021:321-384. |
16 | KAELBLING L P. The foundation of efficient robot learning[J]. Science, 2020, 369(6506): 915-916. |
17 | TURING A M I Computing machinery and intelligence[J]. Mind, 1950, LIX(236): 433-460. |
18 | LI L, ZHENG N N, WANG F Y. A theoretical foundation of intelligence testing and its application for intelligent vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(10): 6297-6306. |
19 | 国家自然科学基金委员会. 人工智能挑战性科学难题及颠覆性技术[EB/OL]. (2019-01-04) [2022-07-25]. . |
National Natural Science Foundation. Challenging scientific problems and disruptive technologies of AI [EB/OL]. (2019-01-04) [2022-07-25]. (in Chinese). | |
20 | 国家标准化管理委员会, 中央网信办, 国家发展改革委, 等. 国家新一代人工智能标准体系建设指南[EB/OL]. (2020-07-27) [2022-07-25]. . |
National Standardization Management Committee, Central Network Information Office, National Development and Reform Commission, et al. Construction guidelines of national new generation AI standard system[EB/OL]. (2020-07-27)[2022-07-25]. (in Chinese). | |
21 | DEFENSE O. Unmanned aircraft systems roadmap 2000-2025[R]. Washington DC: Department of Defense, 2000. |
22 | DEFENSE O. Unmanned aerial vehicles roadmap 2002-2027[R]. Washington DC: Department of Defense, 2002. |
23 | DEFENSE O. Unmanned aircraft system roadmap 2005-2030[R]. Washington DC: Department of Defense, 2005. |
24 | CLOUGH B. Metrics, schmetrics! How do You track a UAV’s autonomy?: AIAA-2002-3499[R]. Reston: AIAA,2002. |
25 | SHOLES E. Evolution of a UAV autonomy classification taxonomy[C]∥ 2007 IEEE Aerospace Conference. Piscataway: IEEE Press, 2007: 1-16. |
26 | SHERIDAN T B. Automation, authority and angst—revisited[C]∥1991 Proceedings of the Human Factors Society Annual Meeting. San Francisco: Human Factors & Ergonomics Society Press, 1991: 2-6. |
27 | HUANG H M, PAVEK K, ALBUS J, et al. Autonomy levels for unmanned systems (ALFUS) framework: An update[C]∥ Defense and Security. San Francisco: SPIE, 2005: 439-448. |
28 | YOUNG L, YETTER J, GUYNN M. System analysis applied to autonomy: Application to high-altitude long-endurance remotely operated aircraft: AIAA-2005-7103[R]. Reston: AIAA, 2005. |
29 | 陈宗基, 魏金钟, 王英勋, 等. 无人机自主控制等级及其系统结构研究[J]. 航空学报, 2011, 32(6): 1075-1083. |
CHEN Z J, WEI J Z, WANG Y X, et al. UAV autonomous control levels and system structure[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(6): 1075-1083 (in Chinese). | |
30 | 王越超, 刘金国. 无人系统的自主性评价方法[J]. 科学通报, 2012, 57(15): 1290-1299. |
WANG Y C, LIU J G. Autonomy evaluation method of unmanned system[J]. Chinese Science Bulletin, 2012, 57(15): 1290-1299 (in Chinese). | |
31 | ZHANG T, LI Q, ZHANG C S, et al. Current trends in the development of intelligent unmanned autonomous systems[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 68-85. |
32 | 段海滨, 范彦铭, 魏晨, 等. 群体熵: 一种群体智能行为的量化分析工具[J]. 中国科学(信息科学), 2020, 50(3): 335-346. |
DUAN H B, FAN Y M, WEI C, et al. Swarm entropy: A quantitative analysis tool for swarm intelligence behaviors[J]. Scientia Sinica (Informationis), 2020, 50(3): 335-346 (in Chinese). | |
33 | CHAITIN G J. Algorithmic information theory[M]. Cambridge: Cambridge University Press, 2004:179-196. |
34 | CHAITIN G J. G?del’s theorem and information[J]. International Journal of Theoretical Physics, 1982, 21(12): 941-954. |
35 | LEGG S, HUTTER M. Universal intelligence: A definition of machine intelligence[J]. Minds and Machines, 2007, 17(4): 391-444. |
36 | CHOLLET F. On the measure of intelligence[DB/OL]. arXiv preprint: 1911.01547, 2019. |
37 | 郑志明, 吕金虎, 韦卫, 等. 精准智能理论: 面向复杂动态对象的人工智能[J]. 中国科学: 信息科学, 2021, 51(4): 678-690. |
ZHENG Z M, LYU J H, WEI W, et al. Refined intelligence theory: Artificial intelligence regarding complex dynamic objects[J]. Scientia Sinica (Informationis), 2021, 51(4): 678-690 (in Chinese). | |
38 | 罗杰, 姜鑫, 郭炳晖, 等. 群体智能系统的动力学模型与群体熵度量[J]. 中国科学: 信息科学, 2022, 52(1): 99-110. |
LUO J, JIANG X, GUO B H, et al. Dynamic model and crowd entropy measurement of crowd intelligence system[J]. Scientia Sinica (Informationis), 2022, 52(1): 99-110 (in Chinese). | |
39 | IANTOVICS L B, EMMERT-STREIB F, ARIK S. MetrIntMeas a novel metric for measuring the intelligence of a swarm of cooperating agents[J]. Cognitive Systems Research, 2017, 45: 17-29. |
40 | WANG X H, ZHANG Y, WANG L Z, et al. Robustness evaluation method for unmanned aerial vehicle swarms based on complex network theory[J]. Chinese Journal of Aeronautics, 2020, 33(1): 352-364. |
41 | HECKER J P, MOSES M E. Beyond pheromones: Evolving error-tolerant, flexible, and scalable ant-inspired robot swarms[J]. Swarm Intelligence, 2015, 9(1): 43-70. |
42 | 杨伟. 关于未来战斗机发展的若干讨论[J]. 航空学报, 2020, 41(6): 524377. |
YANG W. Development of future fighters[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(6): 524377 (in Chinese). | |
43 | CHEN T Q, GUESTRIN C. XGBoost: A scalable tree boosting system[C]∥ Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785-794. |
44 | ZHENG L M, YANG J C, CAI H, et al. MAgent: A many-agent reinforcement learning platform for artificial collective intelligence[DB/OL]. arXiv preprint: 1712.00600, 2017. |
/
〈 |
|
〉 |