Minghu Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Minghu Tan has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Ke Zhang
School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China
4 shared publications - Jingyu Wang
School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China
3 shared publications Ke Zhang
School of Astronautics NUP, Northwestern Polytechnical University, Xi’an, China
3 shared publications- Haoyu Li
School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China
2 shared publications - Hong Shen
Northwestern Polytechnical University, xian, China
2 shared publications Jingyu Wang
School of Astronautics, Northwestern Polytechnical University, Xi’an, People’s Republic of China
2 shared publications
Latest Publications
- 21 October 2025
- Published by Springer Nature in Astrodynamics
- Vol. 9 (6) , 953-968
Analysis of the optimal transfer time under uncertainty of regular structure asteroids
- 21 October 2025
- Published by Springer Nature in Astrodynamics
- Vol. 9 (6) , 953-968
Analysis of the optimal transfer time under uncertainty of regular structure asteroids
- Open Access
A Deep Reinforcement Learning-Based Cooperative Guidance Strategy Under Uncontrollable Velocity Conditions
We present a novel approach to generating a cooperative guidance strategy using deep reinforcement learning to address the challenge of cooperative multi-missile strikes under uncontrollable velocity conditions. This method employs the multi-agent proximal policy optimization (MAPPO) algorithm to construct a continuous action space framework for intelligent cooperative guidance. A heuristically reshaped reward function is designed to enhance cooperative guidance among agents, enabling effective target engagement while mitigating the low learning efficiency caused by sparse reward signals in the guidance environment. Additionally, a multi-stage curriculum learning approach is introduced to smooth agent actions, effectively reducing action oscillations arising from independent sampling in reinforcement learning. Simulation results demonstrate that the proposed deep reinforcement learning-based guidance law can successfully achieve cooperative attacks across a range of randomized initial conditions.
Open AccessA Deep Reinforcement Learning-Based Cooperative Guidance Strategy Under Uncontrollable Velocity Conditions
We present a novel approach to generating a cooperative guidance strategy using deep reinforcement learning to address the challenge of cooperative multi-missile strikes under uncontrollable velocity conditions. This method employs the multi-agent proximal policy optimization (MAPPO) algorithm to construct a continuous action space framework for intelligent cooperative guidance. A heuristically reshaped reward function is designed to enhance cooperative guidance among agents, enabling effective target engagement while mitigating the low learning efficiency caused by sparse reward signals in the guidance environment. Additionally, a multi-stage curriculum learning approach is introduced to smooth agent actions, effectively reducing action oscillations arising from independent sampling in reinforcement learning. Simulation results demonstrate that the proposed deep reinforcement learning-based guidance law can successfully achieve cooperative attacks across a range of randomized initial conditions.
- 7 May 2024
- Published by Springer Nature in International Journal of Aeronautical and Space Sciences
- Vol. 25 (4) , 1507-1523
The Continuous Thrust Long-Orbit Satellite Pursuit-Evasion Game Control Using Feedback Genetic Shooting Method
- 7 May 2024
- Published by Springer Nature in International Journal of Aeronautical and Space Sciences
- Vol. 25 (4) , 1507-1523
The Continuous Thrust Long-Orbit Satellite Pursuit-Evasion Game Control Using Feedback Genetic Shooting Method
- 18 January 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (3) , 1050-1065
An Optimal Robust Trajectory Tracking Control Strategy for the Wheeled Mobile Robot
- 18 January 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (3) , 1050-1065
An Optimal Robust Trajectory Tracking Control Strategy for the Wheeled Mobile Robot
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (1) , 405-420
Three-Dimensional Cooperative Game Guidance Law for a Leader–Follower System With Impact Angles Constraint
Cooperative guidance issues with desired impact angles against a target are studied in a leader–follower system in this article. Different from the existing achievements, the attackers and the target are modeled as the participants of a pursuit-evasion game in the cooperative guidance scenario. Specifically, the leader's differential game guidance law is first formulated by using optimal control theory, while the cooperative guidance law of the follower is designed to ensure the simultaneous attack on the target with the desired impact angles by using model predictive control and robust sliding mode control. Compared to methods using time-to-go as the consensus variable, the proposed guidance law has the potential to achieve higher performance. Simulation validation shows that simultaneous attacks can be accomplished at the desired impact angles for different targets with stationary, classical maneuvers, and game maneuvers.
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (1) , 405-420
Three-Dimensional Cooperative Game Guidance Law for a Leader–Follower System With Impact Angles Constraint
Cooperative guidance issues with desired impact angles against a target are studied in a leader–follower system in this article. Different from the existing achievements, the attackers and the target are modeled as the participants of a pursuit-evasion game in the cooperative guidance scenario. Specifically, the leader's differential game guidance law is first formulated by using optimal control theory, while the cooperative guidance law of the follower is designed to ensure the simultaneous attack on the target with the desired impact angles by using model predictive control and robust sliding mode control. Compared to methods using time-to-go as the consensus variable, the proposed guidance law has the potential to achieve higher performance. Simulation validation shows that simultaneous attacks can be accomplished at the desired impact angles for different targets with stationary, classical maneuvers, and game maneuvers.
- 9 March 2023
- Published by Springer Nature in The Journal of the Astronautical Sciences
- Vol. 70 (2) , 1-23
A Sun–Earth Stable Manifold-Based Method for Planar Two-Impulse Earth–Moon Transfer Design
- 9 March 2023
- Published by Springer Nature in The Journal of the Astronautical Sciences
- Vol. 70 (2) , 1-23
A Sun–Earth Stable Manifold-Based Method for Planar Two-Impulse Earth–Moon Transfer Design
- 31 January 2023
- Published by Springer Nature
- p. 1924-1932
The Differential Game Cooperative Guidance Law for the Single Target
- 31 January 2023
- Published by Springer Nature
- p. 1924-1932
The Differential Game Cooperative Guidance Law for the Single Target
- 23 January 2023
- Published by Taylor & Francis in International Journal of Computer Mathematics
- Vol. 100 (5) , 1094-1109
Prescribed time convergence and robust zeroing neural network for solving time-varying linear matrix equation
To overcome the inefficiency, weak robustness and even the failure due to increasing dimensionality of traditional numerical algorithms in solving time-varying linear matrix equation, zeroing neural network, with parallel computational features and simple structure, offers a new solution method. As an important component, the activation function directly affects the performance of zeroing neural network in solving time-varying linear matrix equation. Focusing on the unification of prescribed time convergence and strong robustness without changing the basic structure of zeroing neural network, a novel activation function is proposed for the first time in this paper. Compared with commonly used activation functions in previous work, the novel activation function has superior performance for zeroing neural network to solve the time-varying linear matrix equation. The first item is global asymptotic convergence, capable of converging from random initial states to the theoretical solution. The second item is the prescribed time convergence, i.e., the upper bound of convergence time is only related to the parameters of the novel activation function and zeroing neural network, which facilitates the prediction of the convergence process. The third item is strong robustness, which ensures that the solution converges in various noisy environments. Theoretical analysis and comparative simulation experiments verify that zeroing neural network with the novel activation function has these performances for both low- or high-dimensional time-varying linear matrix equation.
- 23 January 2023
- Published by Taylor & Francis in International Journal of Computer Mathematics
- Vol. 100 (5) , 1094-1109
Prescribed time convergence and robust zeroing neural network for solving time-varying linear matrix equation
To overcome the inefficiency, weak robustness and even the failure due to increasing dimensionality of traditional numerical algorithms in solving time-varying linear matrix equation, zeroing neural network, with parallel computational features and simple structure, offers a new solution method. As an important component, the activation function directly affects the performance of zeroing neural network in solving time-varying linear matrix equation. Focusing on the unification of prescribed time convergence and strong robustness without changing the basic structure of zeroing neural network, a novel activation function is proposed for the first time in this paper. Compared with commonly used activation functions in previous work, the novel activation function has superior performance for zeroing neural network to solve the time-varying linear matrix equation. The first item is global asymptotic convergence, capable of converging from random initial states to the theoretical solution. The second item is the prescribed time convergence, i.e., the upper bound of convergence time is only related to the parameters of the novel activation function and zeroing neural network, which facilitates the prediction of the convergence process. The third item is strong robustness, which ensures that the solution converges in various noisy environments. Theoretical analysis and comparative simulation experiments verify that zeroing neural network with the novel activation function has these performances for both low- or high-dimensional time-varying linear matrix equation.
- 28 October 2022
- Published by Elsevier in Information Sciences
- Vol. 616, 348-366
A novel system identification algorithm for nonlinear Markov jump system
- 28 October 2022
- Published by Elsevier in Information Sciences
- Vol. 616, 348-366
A novel system identification algorithm for nonlinear Markov jump system
- 4 October 2022
- Published by Springer Nature in Astrophysics and Space Science
- Vol. 367 (10) , 1-13
A multi-step method to calculate long-term quasi-periodic orbits around the Sun-Earth $L_{1}$/$L_{2}$- 4 October 2022
- Published by Springer Nature in Astrophysics and Space Science
- Vol. 367 (10) , 1-13
A multi-step method to calculate long-term quasi-periodic orbits around the Sun-Earth $L_{1}$/$L_{2}$