According to the autonomous characteristics of the unmanned combat system in the context of military application, the level division of the autonomy of the unmanned combat system is proposed and its conceptual model is established. The paper analyzes the autonomy of unmanned combat systems, establishes relevant hierarchical models and assessment methods. A task-oriented optimal assignment model for autonomy level of unmanned combat system is proposed. First of all, the operational task planning model of unmanned combat system is established, and takes minimality of the consumption of task resources and the total time of task completion as the goals. In addition, the autonomous level modulation model of the unmanned combat system is established. The decision rules are formulated to maximize the task completion rate of the unmanned combat system in the execution of combat activities while minimizing the resource consumption and the risk of executing tasks. Finally, a landing battle case is designed to verify the correctness and effectiveness of the hierarchical optimization distribution model proposed in this paper.
无人作战系统自主性等级的划分是无人作战系统对于所分配任务做出判断和决策的能力的评价。2012年,美国国防部发布《武器系统自主性》,将自主武器系统的自主性等级划分为三级[16]:“人在回路外的控制”(human out of the loop control)“人在回路上的控制”(human on the loop control)“人在回路中的控制”(human in the loop control),如图1所示。本文参考自主武器系统划分,结合无人作战系统特性,根据无人作战系统对于自身智能的认知结果以及人机交互程度属性,提出无人作战系统自主性等级划分。根据现有参考文献,结合军事应用背景,把无人作战系统自主性等级定义为5个级别,分别为全自主、半自主、人类监督、用户协作和全手动,如表1所示,各等级描述如表2所示。
United States Department of Defense. Unmanned Systems Integrated Roadmap: FY2017-2042[R]. Department of Defense, Washington DC, 2018.
[2]
ParasuramanR, SheridanT B, WickensC D. A Model for Types and Levels of Human Interaction with Automation[J]. IEEE Transactions on Systems Man and Cybernetics-Part A Systems and Humans, 2000, 30(3):286-297.
SheridanT B. Human Supervisory Control[M]. Hoboken: John Wiley & Sons, Inc, 2012.
[4]
RyanW P, JeremyJ H, RichardB M. Methods for Determining the Level of Autonomy to Design into a Human Spacefight Vehicle: A Function Specific Approach[C]. Proceedings of NIST Workshop on Performance Metrics for Intelligent Systems, Gaitherbug, MD, 2003.
HuangH M, MessinaE, MadhavanR, et al. Autonomy Levels for Unmanned Systems (ALFUS) Framework: Safety and Application Issues[C]. Performance Metrics for Intelligent Systems Workshop. Washington DC, USA. ACM New York: NY USA Press, 2007: 48-53.
MorrowD, ChangD, WickensC, et al. Designing External Aids that Support Older Pilot Performance[J]. Human Factors & Ergonomics Society Annual Meeting Proceedings, 2005, 49(2):186-189.
[9]
Shuai Z, LiX R, PengZ, et al. UAV Autonomy Evaluation Based on Multi-factors Fuzzy Evaluation[C]// 2016 7th International Conference on Mechanical and Aerospace Engineering (ICMAE). IEEE, Cambridge, UK, 2016:487-491.
[10]
HuangH M, PavekK, NovakB, et al. A Framework for Autonomy Levels for Unmanned Systems (ALFUS)[C]. AUVSI’s Unmanned System North America Conference. Baltimore: Arlington Va Press, 2005:849-863.
RussellS J, NorvigP N. Artificial Intelligence: A Modern Approach. Prentice Hall[J]. Applied Mechanics & Materials, 2010, 263(5):2829-2833.
[14]
Clark, Matthew, Alley Jim. Autonomy Community of Interest (COI) Test and Evaluation, Verification and Validation (TEVV) Working Group: Technology Investment Strategy 2015-2018[R]. TEVV Working Group, May 2015.
[15]
Office of the Secretary of Defense. Unmanned Systems Integrated Roadmap: FY2013-2038[R]. Department of Defense, Washington DC, 2015.
[16]
United States Department of Defense. Autonomy in Weapon Systems[R]. US: United States Department of Defense, 2012.
[17]
Defense Science Board. Autonomy[R]. US: Office of the Secretary of Denfense, 2016.
[18]
Endsley, Mica. Autonomous Horizons: System Autonomy in the Air Force-A Path to the Future. Volume I: Human-Autonomy Teaming[R]. United States Air Force Office of the Chief Scientist, 2015.
[19]
R.Parasuraman, T.B.Sheridan, C.D.Wickens. A Model for Types and Levels of Human Interaction with Automation[J]. IEEE Transactions on Systems and Cybernetics Part A: Systems and Humans, 2000, 30(3): 286-297.