Liang Jiang

Liang Jiang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 August 2022 in Aerospace
Verified
Journal Article
Open access
PDF file
LJLiang Jiang
Liang Jiang
YNYing Nan
Ying Nan
YZYu Zhang
Yu Zhang
ZLZhihan Li
Zhihan Li
Anti-interception guidance can enhance a hypersonic glide vehicle (HGV) compard to multiple interceptors. In general, anti-interception guidance for aircraft can be divided into procedural guidance, fly-around guidance and active evading guidance. However, these guidance methods cannot be applied to an HGV’s unknown real-time process due to limited intelligence information or on-board computing abilities. In this paper, an anti-interception guidance approach based on deep reinforcement learning (DRL) is proposed. First, the penetration process is conceptualized as a generalized three-body adversarial optimal (GTAO) problem. The problem is then modelled as a Markov decision process (MDP), and a DRL scheme consisting of an actor-critic architecture is designed to solve this. Reusing the same sample batch during training results in fewer serious estimation errors in the critic network (CN), which provides better gradients to the immature actor network (AN). We propose a new mechanismcalled repetitive batch training (RBT). In addition, the training data and test results confirm that the RBT can improve the traditional DDPG-based-methodes.

22 June 2021 in IEEE Access
Verified
Journal Article
Open access
LJLiang Jiang
Liang Jiang
YNYing Nan
Ying Nan
ZLZhi-Han Li
Zhi-Han Li
A midcourse maneuver controller is obtained using deep reinforcement learning to maintain the survivability of a ballistic missile. First, the midcourse is abstracted as a Markov decision process (MDP) with an unknown system state equation. Then, a controller formed by the Dueling Double Deep Q (D3Q) neural network is used to approximate the state-action value function of the MDP. In order to make the controller’s intelligence improved by deep reinforcement learning, the state space, action space, and instant reward function of the MDP are customized. The controller uses a real-time situation as input and outputs the ignition states of pulse motors. Offline training shows that deep reinforcement learning can achieve the optimal strategy’s convergence after approximately 65 hours. Online tests demonstrate the controller’s ability to avoid an interceptor intelligently and to account for an entry error. In scenarios with multiple random factors, the controller achieved a penetration probability of 100% and a mean re-entry error of less than 5000 m.