一种2对2智能空战实时机动决策方法
By adopting a target allocation-situation advantage-nonlinear model predictive control architecture, the 2v2 air combat problem is reduced to a parallel 1v1 air combat subproblem, solving the problems of real-time performance, safety, and portability in 2v2 air combat, and achieving efficient maneuver decision-making and safety assurance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SICHUAN UNIV
- Filing Date
- 2025-12-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to balance real-time performance, security, and portability in 2v2 beyond-visual-range air combat, especially in highly dynamic, strongly coupled, and resource-constrained scenarios. There is a lack of a unified dynamics-tactical coupling model, and existing decision-making methods are insufficient in terms of real-time performance and scalability.
The target assignment-situation advantage-nonlinear model predictive control (NMPC) architecture is adopted to reduce the 2v2 air combat problem to two parallel 1v1 optimal control subproblems. Through adaptive weight rules and constraint transcription technology, the maneuver decision-making is ensured to meet the aircraft constraints in the dynamic battlefield environment and output the globally optimal command.
It significantly improves the real-time performance and solution efficiency of online decision-making, has good versatility and portability, ensures flight safety through inherent hard constraints, effectively solves the dimensionality curse problem in multi-aircraft collaboration, and enhances tactical adaptability to dynamic battlefield environments.
Smart Images
Figure CN121613744B_ABST