分布式MAS在飞行冲突解脱中的应用研究  

Application of Distributed MAS in Flight Conflict Avoidance

作　　者：周建[1] Ahmed RAHMANI 刘昕[1] 王莉莉[1] 

机构地区：[1]中国民航大学空中交通管理学院,天津300300 [2]里尔中央理工学院自动化信息技术工程和信号实验室,法国里尔59650

出　　处：《交通运输系统工程与信息》2015年第5期231-238,共8页Journal of Transportation Systems Engineering and Information Technology

基　　金：国家自然科学基金资助(U1333116);国家空管科研课题(GKG201405002);中央高校基本科研业务费中国民航大学专项基金资助(ZXH2013D013)

摘　　要：在自由飞行的环境下,为解决飞行冲突探测与解脱(conflict detection and resolution,CDR)问题,提出一种基于高度层、航向和速度调配的综合解脱方法,并将多agent系统(multi-agent system,MAS)的分布式技术与启发式算法相结合,进行问题求解.首先设计了分布式MAS框架结构,然后建立了飞行冲突探测模型,高度层调配模型及航向、速度调配模型,最后,综合运用了基于合同网协议的分布式算法和自适应遗传算法进行问题求解.仿真实验表明,所设计的MAS框架是可行的,同时分布式算法和自适应遗传算法的综合应用能很快找到基于高度层、航向和速度分配的近似最优解,为CDR问题提供了新的解决思路.In order to solve the problem of flight conflict detection and resolution（CDR） in the background of free flight, an integrated CDR method based on assignment of flight level, heading and velocity is proposed, and distributed technology of MAS（multi- agent system） and a heuristic algorithm are combined for the algorithm implementation. Firstly, a framework of distributed MAS is designed. Secondly, a conflict detection model, a flight level allocation model and a heading velocity assignment model are established.Finally, a distributed algorithm based on contract net protocol and an adaptive genetic algorithm are designed to solve the problem. Simulation results show that the MAS framework is feasible, and the combination of the designed distributed algorithm and adaptive genetic algorithm can search the approximate optimal solution rapidly, based on the allocation of flight level, heading and velocity, which provides a new solution to the CDR problem.

关 键 词：航空运输 冲突解脱 合同网协议 多AGENT系统 空中交通管理 

分 类 号：V355.1[航空宇航科学与技术—人机与环境工程] V328.3