智能化装备体系的“学习性”：从鲁棒自主到认知演化的跃迁逻辑

张龙; 黄文博; 雷震; 冯轩铭; 王莹

doi:10.11959/j.issn.2096-6652.202607

Chinese

您当前的位置：

首页 >

文章列表页 >

智能化装备体系的“学习性”：从鲁棒自主到认知演化的跃迁逻辑

学术论文 | 更新时间：2026-04-27

- 智能化装备体系的“学习性”：从鲁棒自主到认知演化的跃迁逻辑
- “Iearnability” of intelligent weapon systems: a transition logic from robust autonomy to cognitive evolution
- 智能科学与技术学报 2026年8卷第1期页码：61-71
- 作者机构：
  
  1.军事科学院系统工程研究院，北京 100101
  2.海军航空大学，山东烟台 264000
  3.陆军研究院，北京 100012
- 作者简介：
  
  [ "张龙（1990- ），男，军事科学院系统工程研究院博士生，主要研究方向为智能化装备体系设计与评估。" ]
  [ "黄文博（1983- ），男，博士，军事科学院系统工程研究院助理研究员，主要研究方向为装备论证与智能评估。" ]
  [ "雷震（1985- ），男，军事科学院系统工程研究院博士生，主要研究方向为装备论证。" ]
  [ "王莹（1988- ），女，军事科学院系统工程研究院助理研究员，主要研究方向为装备论证与智能评估。" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.202607
  中图分类号： E919;TP18
- 收稿：2025-10-21，
  
  修回：2026-03-18，
  
  录用：2026-03-20，
  
  纸质出版：2026-03-15
- 稿件说明：
移动端阅览
张龙,黄文博,雷震等.智能化装备体系的“学习性”：从鲁棒自主到认知演化的跃迁逻辑[J].智能科学与技术学报,2026,08(01):61-71.

Zhang Long,Huang Wenbo,Lei Zhen,et al.“Iearnability” of intelligent weapon systems: a transition logic from robust autonomy to cognitive evolution[J].Chinese Journal of Intelligent Science and Technology,2026,08(01):61-71.
张龙,黄文博,雷震等.智能化装备体系的“学习性”：从鲁棒自主到认知演化的跃迁逻辑[J].智能科学与技术学报,2026,08(01):61-71. DOI： 10.11959/j.issn.2096-6652.202607.

Zhang Long,Huang Wenbo,Lei Zhen,et al.“Iearnability” of intelligent weapon systems: a transition logic from robust autonomy to cognitive evolution[J].Chinese Journal of Intelligent Science and Technology,2026,08(01):61-71. DOI： 10.11959/j.issn.2096-6652.202607.

摘要

智能化装备体系是作战形态向认知主导、自主适应转型的实体承载。为在高度不确定性与强对抗性战场环境中维持功能连续性，体系必须具备内生性的“学习性”。将学习性界定为智能化装备体系应对不确定性、维持功能连续性的存在论能力，并构建了一个贯通本体论、作用机理与实现路径的三层理论框架。首先，从历史必然性、技术重塑与复杂性临界3个维度，论证了学习性成为体系存续刚性需求的内在逻辑。其次，逐层剖析了学习性的三重层级内涵：智能节点层以“鲁棒自主”为存在基线，智能系统层以“涌现协同”为结构增益，智能体系层以“认知演化”实现规则主导。进而，提出了与之对应的三层结构化实现路径，详细阐述了从个体表征推演、系统结构自组织到体系规则演化的耦合机理与闭环反馈机制。所提框架旨在为智能化装备体系的顶层设计、效能评估与能力生成提供一套系统性的理论框架，为理解并构建未来战场的“认知生命体”提供理论探索。

Abstract

The intelligent equipment system serves as the physical carrier for the transformation of operational forms toward cognitive adaptation. To maintain functional continuity within highly uncertain and strongly adversarial battlefield environments

the system must possess an endogenous "learnability". Learnability as the ontological capability of an intelligent equipment system was defined to cope with uncertainty and sustain functional continuity

constructing a three-layer theoretical framework that integrates ontology

operational mechanisms

and implementation paths. Firstly

the intrinsic logic of learnability becoming a rigid requirement for system survival was demonstrated in three dimensions

such as historical inevitability

technological reshaping

and complexity criticality. Secondly

the connotations of learnability at three hierarchical levels were analyzed

such as the intelligent node level established "robust autonomy" as the existence baseline

the intelligent system level achieved "emergent collaboration" as structural gain

and the intelligent system-of-systems level realized "cognitive evolution" for rule dominance. Furthermore

corresponding three-layer structured implementation paths were proposed

elaborating on the coupling mechanisms and closed-loop feedback mechanisms ranging from individual representation deduction and system structure self-organization to system-of-systems rule evolution. This framework aims to provide a systematic theoretical framework for the top-level design

effectiveness evaluation

and capability generation of intelligent equipment systems

offering theoretical exploration for understanding and constructing the "cognitive life forms" of the future battlefield.

关键词

Keywords

references

Li X D, Dunkin F, Dezert J. Multi-source information fusion: Progress and future[J]. Chinese Journal of Aeronautics, 2024, 37(7): 24-58.

Zhou Z H, Wei P J, Wang Z Y, et al. Towards human-centered interaction with UAV swarms: Framework, system design, and user study[J]. Design and Artificial Intelligence, 2025, 1(3): 100029.

Zabala-López A, Linares-Vásquez M, Haiduc S, et al. A survey of data-centric technologies supporting decision-making before deploying military assets[J]. Defence Technology, 2024, 42: 226-246.

Chen X, Li L X, Zhang W, et al. Command and control system in intelligentized warfare[C]//Proceedings of the 2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS). Piscataway: IEEE Press, 2021: 951-954.

Liu C, Li J, Wang Y, et al. A time-driven dynamic weapon target assignment method[J]. IEEE Access, 2023, 11: 129623-129639.

León-Pamplona J C, Guerrero-Sierra H F, Wilches-Tinjacá J A. Lethal autonomous weapons systems (LAWS)[J]. Revista Científica General José María Córdova, 2025, 23(52): 761-784.

Grosvenor A, Zemlyansky A, Wahab A, et al. Hybrid intelligence systems for reliable automation: advancing knowledge work and autonomous operations with scalable AI architectures[J]. Frontiers in Robotics and AI, 2025, 12: 1566623.

王飞跃. 未来的智能生态≌AIR 2 IST+LaSEE 2 CiSEE+SEE 2 H 3 O[J ] . 智能科学与技术学报, 2025, 7(2): 139-142.

Wang F Y. The future ecology of in telligence: AIR 2 IST+LaSEE 2 CiSEE+SEE 2 H 3 O[J ] . Chinese Journal of Intelligent Science and Technology, 2025, 7(2): 139-142.

Gibney E, Witze A, Ahart J. Trump's AI 'genesis mission': what are the risks and opportunities?[J]. Nature, 2025, 648(8093): 253-255.

Kaber D. From automation to autonomy through AI: enabling and retaining human controllability[M]//Xu W. Handbook of human-centered artificial intelligence. Singapore: Springer Nature Singapore, 2025: 1-45.

马琼敏, 唐小静, 肖刚, 等. 装备学习能力评估方法研究[J]. 军事运筹与评估, 2024, 39(2): 9-14.

Ma Q M, Tang X J, Xiao G, et al. A study on assessment methods of equipments learning capability[J]. Military Operations Research and Assessments, 2024, 39(2): 9-14.

王建红, 严俊琦. 世界模型赋能未来产业发展: 演化图景与推进策略[J]. 改革与战略, 2025, 41(3): 169-176.

Wang J H, Yan J Q. World model empowers future industrial development: evolution prospect and promotion strategy[J]. Reformation & Strategy, 2025, 41(3): 169-176.

张龙, 王数, 雷震, 等. AIGC军事大模型评估体系框架研究[J]. 战术导弹技术, 2025(1): 42-52.

Zhang L, Wang S, Lei Z, et al. Research on the framework of AIGC military large model evaluation system[J]. Tactical Missile Technology, 2025(1): 42-52.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统