A unified intelligent control strategy synthesizing multi-constrained guidance and avoidance penetration  

作　　者：Sibo ZHAO Jianwen ZHU Weimin BAO Xiaoping LI 

机构地区：[1]School of Aerospace Science and Technology,Xidian University,Xi’an 710126,China [2]College of Missile Engineering,Rocket Force University of Engineering,Xi’an 710025,China [3]China Aerospace Science and Technology Corporation,Beijing 100048,China

出　　处：《Science China(Information Sciences)》2024年第7期325-326,共2页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant No.92371203).

摘　　要：Satisfying various terminal constraints and achieving evasive flight in no-flying-zones(NFZs)are two important flight missions undertaken by high velocity vehicles.We studied an intelligent maneuvering guidance strategy using deep reinforcement learning(DRL)methods to achieve the coordination and unification of evasive flight and multi-constrained guidance with minimal energy loss.

关 键 词：CONSTRAINED UNIFIED CONSTRAINTS 

分 类 号：V249.1[航空宇航科学与技术—飞行器设计] V448[自动化与计算机技术—检测技术与自动化装置] TP273[自动化与计算机技术—控制科学与工程]