Abstract
With the development of unmanned combat air vehicles (UCAVs) and artificial intelligence (AI), within visual range (WVR) air combat confrontations utilizing intelligent UCAVs are expected to be widely used in future air combats. As controlling highly dynamic and uncertain WVR air combats from the ground stations of the UCAV is not feasible, it is necessary to develop an algorithm that can generate highly intelligent air combat strategies in order to enable UCAV to independently complete air combat missions. In this paper, a 1-vs.-1 WVR air combat strategy generation algorithm is proposed using the multi-agent deep deterministic policy gradient (MADDPG). A 1-vs.-1 WVR air combat is modeled as a two-player zero-sum Markov game (ZSMG). A method for predicting the position of the target is introduced into the model in order to enable the UCAV to predict the target’s actions and position. Moreover, to ensure that the UCAV is not limited by the constraints of the basic fighter maneuver (BFM) library, the action space is considered to be a continuous one. At the same time, a potential-based reward shaping method is proposed in order to improve the efficiency of the air combat strategy generation algorithm. Finally, the efficiency of the air combat strategy generation algorithm and the intelligence level of the resulting strategy is verified through simulation experiments. The results show that an air combat strategy using target position prediction is superior to the one that does not use target position prediction.
Highlights
With the development of unmanned combat air vehicles (UCAVs), the role of UCAVs is becoming increasingly significant in the field of combat [1]
We propose a UCAV 1-vs.-1 within visual range (WVR) air combat strategy generation algorithm based on multi-agent deep deterministic policy gradient (MADDPG)
The intercept time is measured from the beginning of the air combat simulation until a UCAV has established a position of advantage
Summary
With the development of unmanned combat air vehicles (UCAVs), the role of UCAVs is becoming increasingly significant in the field of combat [1]. In the vast majority of articles, the author only uses the current UCAV motion state as the state space for reinforcement learning, which makes it difficult for a trained UCAV air combat strategy to learn predicted target maneuvering and intentional air combat decisions. This means that an air combat strategy will not consist of the intelligent behavior necessary to be in the dominant position in advance. In order to solve the above mentioned problems, we propose a UCAV 1-vs.-1 WVR air combat strategy generation method that is based on a multi-agent reinforcement learning method with the inclusion of a target maneuver prediction in this article. Introducing potential-based reward shaping method to improve the efficiency of maneuver strategy generation algorithm of UCAV
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
