Maneuvering penetration strategies of ballistic missiles based on deep reinforcement learning
- 27 April 2022
- journal article
- research article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
- Vol. 236 (16), 3494-3504
- https://doi.org/10.1177/09544100221088361
Abstract
In this paper, a ballistic missile terminal penetration scenario is studied, which contains three participants: target, missile, and defender. The ballistic missile attempts to hit the target while evading the defender. A maneuvering penetration guidance strategy that balances both the guidance accuracy and penetration capability is proposed through deep reinforcement learning. Reward shaping and random initialization are applied to improve training speed and generalization, respectively. The proposed strategy is developed based on the twin delayed deep deterministic policy gradient algorithm. It directly maps observations to actions and is an end-to-end guidance scheme that does not require an accurate model. The simulation results show that the proposed strategy has higher penetration probabilities than conventional strategies for different initial heading errors and even for defenders with different guidance laws, which indicates its good robustness and generalization. For different initial heading errors, it has learned different maneuvering modes and has certain intelligence. In addition, it is computationally small, does not consume much memory, and can be easily applied on modern flight computers.Keywords
Funding Information
- National Natural Science Foundation of China (12072090)
This publication has 24 references indexed in Scilit:
- Consensus of leader-follower multi-warhead networked cooperative attack with stochastic multi-step time-varying delayPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Research on the evasive strategy of missile based on the theory of differential gamePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Maneuver Control Strategies to Maximize Prediction Errors in Ballistic Middle PhaseJournal of Guidance, Control, and Dynamics, 2013
- Missile Avoidance Maneuvres with Simultaneous Decoy DeploymentPublished by American Institute of Aeronautics and Astronautics (AIAA) ,2009
- Analysis of Optimal Weaving Frequency of Maneuvering TargetsJournal of Spacecraft and Rockets, 2004
- Optimal planar evasive aircraft maneuvers against proportional navigation missilesJournal of Guidance, Control, and Dynamics, 1996
- Proportional navigation and weaving targetsJournal of Guidance, Control, and Dynamics, 1995
- Reinforcement learning is direct adaptive optimal controlIEEE Control Systems, 1992
- Analysis of Three-Dimensional Optimal Evasion with Linearized KinematicsJournal of Guidance and Control, 1979
- Analysis of Optimal Evasive Maneuvers Based on a Linearized Two-Dimensional Kinematic ModelJournal of Aircraft, 1977