Yue-He Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yue-He Zhu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Ya-Zhong Luo
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
7 shared publications Jia-Cheng Zhang
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
2 shared publications- Yu Zhang
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
2 shared publications - Bo-Yong He
State Key Laboratory of Astronautic Dynamics (ADL), Xi’an Satellite Control Center, Xi’an, China
1 shared publication Hanwei Wang
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
1 shared publicationHua Wang
1 shared publication
Latest Publications
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 11679-11694
Nash Equilibria for Asynchronous Impulsive Orbital Pursuit–Evasion Games Under J2 Perturbation
Impulsive orbital pursuit–evasion (PE) games are critical for space security. The impulse timing relationship directly influences the control strategies and results. However, most existing studies assume simultaneous or sequential maneuvers, whereas real impulsive orbital games involve asynchronous maneuvers. Additionally, orbital perturbations affect game precision, particularly in low Earth orbits and long-duration scenarios. This study investigates asynchronous impulsive orbital PE games under J2 perturbation and introduces a solution method for asynchronous multi-impulse Nash equilibrium. The necessary conditions for Nash equilibrium are derived using an extended Pontryagin principle, which transforms the necessary condition into a special multipoint boundary value problem (MPBVP). A solution method combining iterative best response and segmented shooting is proposed. The first impulses of both players are modeled as a single-impulse Stackelberg game to generate an approximate Stackelberg equilibrium as the initial guess, providing physical meaning to initial guesses and avoiding the blindness of random guesses. For uneven time segments, the asynchronous Nash equilibrium is obtained through segmented shooting and interior point constraint handling. Simulations show that the proposed initial guess improvement ensures 100% convergence success, validating the algorithm's effectiveness and Nash equilibrium optimality. Comparative simulations demonstrate superior computational efficiency and broader applicability.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 11679-11694
Nash Equilibria for Asynchronous Impulsive Orbital Pursuit–Evasion Games Under J2 Perturbation
Impulsive orbital pursuit–evasion (PE) games are critical for space security. The impulse timing relationship directly influences the control strategies and results. However, most existing studies assume simultaneous or sequential maneuvers, whereas real impulsive orbital games involve asynchronous maneuvers. Additionally, orbital perturbations affect game precision, particularly in low Earth orbits and long-duration scenarios. This study investigates asynchronous impulsive orbital PE games under J2 perturbation and introduces a solution method for asynchronous multi-impulse Nash equilibrium. The necessary conditions for Nash equilibrium are derived using an extended Pontryagin principle, which transforms the necessary condition into a special multipoint boundary value problem (MPBVP). A solution method combining iterative best response and segmented shooting is proposed. The first impulses of both players are modeled as a single-impulse Stackelberg game to generate an approximate Stackelberg equilibrium as the initial guess, providing physical meaning to initial guesses and avoiding the blindness of random guesses. For uneven time segments, the asynchronous Nash equilibrium is obtained through segmented shooting and interior point constraint handling. Simulations show that the proposed initial guess improvement ensures 100% convergence success, validating the algorithm's effectiveness and Nash equilibrium optimality. Comparative simulations demonstrate superior computational efficiency and broader applicability.
- Open Access
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
Learning-based Framework for Impulsive Optical Imaging Orbital Games with Awareness Delay
The spacecraft optical imaging orbital game is a challenging decision-making problem that involves awareness delay, nonlinear orbital dynamics, impulsive maneuvering, and coupled terminal imaging con-straints. To address this problem, this paper formulates the confrontation as a Markov decision process and develops a deep reinforcement learning framework based on the soft actor–critic (SAC) algorithm trained against an optimization-based receding horizon opponent. Unlike conventional orbital pursuit-evasion formulations, the proposed model incorporates optical imaging requirements, including relative distance, sunlight angle, minimum sustained imaging duration, single-impulse magnitude, minimum impulse inter-val, and total impulse budget. In the proposed framework, the optimization-based opponent serves as a competitive training counterpart under the same awareness delay and maneuvering constraints, thereby providing structured interaction samples for learning. Simulation results show that the trained policy achieves high reliability in the nominal setting and consistently outperforms the optimization-based oppo-nent. Its advantage comes mainly from more effective coordination of maneuver timing and direction ra-ther than greater instantaneous control effort. Additional Monte Carlo tests further demonstrate the useful generalization capability for untrained initial orbital geometries, different opponent preference settings, and a bounded range of awareness delay.
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessLearning-based Framework for Impulsive Optical Imaging Orbital Games with Awareness Delay
The spacecraft optical imaging orbital game is a challenging decision-making problem that involves awareness delay, nonlinear orbital dynamics, impulsive maneuvering, and coupled terminal imaging con-straints. To address this problem, this paper formulates the confrontation as a Markov decision process and develops a deep reinforcement learning framework based on the soft actor–critic (SAC) algorithm trained against an optimization-based receding horizon opponent. Unlike conventional orbital pursuit-evasion formulations, the proposed model incorporates optical imaging requirements, including relative distance, sunlight angle, minimum sustained imaging duration, single-impulse magnitude, minimum impulse inter-val, and total impulse budget. In the proposed framework, the optimization-based opponent serves as a competitive training counterpart under the same awareness delay and maneuvering constraints, thereby providing structured interaction samples for learning. Simulation results show that the trained policy achieves high reliability in the nominal setting and consistently outperforms the optimization-based oppo-nent. Its advantage comes mainly from more effective coordination of maneuver timing and direction ra-ther than greater instantaneous control effort. Additional Monte Carlo tests further demonstrate the useful generalization capability for untrained initial orbital geometries, different opponent preference settings, and a bounded range of awareness delay.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 17653-17665
Attention Network for the Fast Generation of a Multitarget Rendezvous Sequence
Global trajectory optimization of multitarget successive rendezvous missions is studied. A learning-based method is proposed to train a neural network offline, which can directly generate the near-optimal rendezvous sequence online. A neural network structure based on the attention mechanism is developed to extract combinatorial features among multiple on-orbit bodies. Physical equations and neural networks are integrated to generate solutions in a recurrent manner. The sequence generator can be trained and applied in cases with diverse values and sizes. A local refinement approach is applied to the generator to enhance the final solution quality. A reinforcement parallel learning algorithm is specifically designed for efficient model training. Numerical simulations are conducted on general random cases and global trajectory optimization competition (GTOC) problems. The well-trained solver can efficiently produce a sequence that is equivalent to the solution obtained via traditional advanced heuristics. When the trained sequence generator is applied to multispacecraft rendezvous sequence planning, the target assignment optimization process clearly accelerates due to fast sequence generation. The sequence and time of the GTOC winner's solution is reoptimized and better results were obtained, indicating that the proposed model performs significantly well in terms of solution quality.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 17653-17665
Attention Network for the Fast Generation of a Multitarget Rendezvous Sequence
Global trajectory optimization of multitarget successive rendezvous missions is studied. A learning-based method is proposed to train a neural network offline, which can directly generate the near-optimal rendezvous sequence online. A neural network structure based on the attention mechanism is developed to extract combinatorial features among multiple on-orbit bodies. Physical equations and neural networks are integrated to generate solutions in a recurrent manner. The sequence generator can be trained and applied in cases with diverse values and sizes. A local refinement approach is applied to the generator to enhance the final solution quality. A reinforcement parallel learning algorithm is specifically designed for efficient model training. Numerical simulations are conducted on general random cases and global trajectory optimization competition (GTOC) problems. The well-trained solver can efficiently produce a sequence that is equivalent to the solution obtained via traditional advanced heuristics. When the trained sequence generator is applied to multispacecraft rendezvous sequence planning, the target assignment optimization process clearly accelerates due to fast sequence generation. The sequence and time of the GTOC winner's solution is reoptimized and better results were obtained, indicating that the proposed model performs significantly well in terms of solution quality.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1506-1514
Sequence Optimization of Multispacecraft Multitarget Rendezvous Missions with a Coevolutionary Algorithm
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1506-1514
Open AccessSequence Optimization of Multispacecraft Multitarget Rendezvous Missions with a Coevolutionary Algorithm
- 1 February 2025
- Published by Springer Nature in Astrodynamics
- Vol. 9 (1) , 129-141
GTOC12: Methods and results from the National University of Defense Technology
- 1 February 2025
- Published by Springer Nature in Astrodynamics
- Vol. 9 (1) , 129-141
GTOC12: Methods and results from the National University of Defense Technology
- 1 July 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Guidance, Control, and Dynamics
- Vol. 47 (7) , 1447-1456
Intelligence-Based Multistage Optimization Framework for Multiple Debris Removal Mission
- 1 July 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Guidance, Control, and Dynamics
- Vol. 47 (7) , 1447-1456
Intelligence-Based Multistage Optimization Framework for Multiple Debris Removal Mission
- 20 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 59 (6) , 9390-9403
A Fast Approach to Satellite Range Rescheduling Using Deep Reinforcement Learning
Real-time emergency event processing for mega-constellation management requires an approach that can quickly obtain a satisfactory satellite range rescheduling scheme. In this paper, a deep reinforcement learning (DRL) approach is proposed for rapid rescheduling on the basis of established satellite range scheduling schemes. Three rescheduling principles with different impacts on established scheduling schemes are first analyzed. A mathematical model for both maximizing the completion profits of dynamic missions and minimizing their impacts on scheduled missions is formulated. An efficient DRL-based approach to satellite range rescheduling is then developed. A mask processing mechanism is integrated into the reinforcement learning framework to effectively eliminate the conflicts accurately expressed by the conflict space, and a modified pointer network (Ptr-Net) based on the mask processing mechanism is employed to approximate the action-value function for optimal decision-making. Experimental results show that the proposed approach significantly outperforms the rule-based heuristic and another DRL-based method in terms of computational efficiency and optimization performance, and the total time spent during the training and testing phases of the proposed approach is approximately 13% of the total running time required by the search-based methods.
- 20 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 59 (6) , 9390-9403
A Fast Approach to Satellite Range Rescheduling Using Deep Reinforcement Learning
Real-time emergency event processing for mega-constellation management requires an approach that can quickly obtain a satisfactory satellite range rescheduling scheme. In this paper, a deep reinforcement learning (DRL) approach is proposed for rapid rescheduling on the basis of established satellite range scheduling schemes. Three rescheduling principles with different impacts on established scheduling schemes are first analyzed. A mathematical model for both maximizing the completion profits of dynamic missions and minimizing their impacts on scheduled missions is formulated. An efficient DRL-based approach to satellite range rescheduling is then developed. A mask processing mechanism is integrated into the reinforcement learning framework to effectively eliminate the conflicts accurately expressed by the conflict space, and a modified pointer network (Ptr-Net) based on the mask processing mechanism is employed to approximate the action-value function for optimal decision-making. Experimental results show that the proposed approach significantly outperforms the rule-based heuristic and another DRL-based method in terms of computational efficiency and optimization performance, and the total time spent during the training and testing phases of the proposed approach is approximately 13% of the total running time required by the search-based methods.
- Open Access
- 15 March 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (6) , 1419
Active Debris Removal Mission Planning Method Based on Machine Learning
To prevent the proliferation of space debris and stabilize the space environment, active debris removal (ADR) has increasingly gained public concern. Considering the complexity of space operations and the viability of ADR missions, it would be necessary to schedule the ADR process in order to remove as much debris as possible. This paper presents an active debris removal mission planning problem, devoted to generate an optimal debris removal plan to guide the mission process. According to the problem characteristics, a two-layer time-dependent traveling salesman problem(TSP) mathematical model is established, involving the debris removal sequence planning and the transfer trajectory planning. Subsequently, two main novel methods based on machine learning are proposed for the ADR mission planning problem, including a deep neural networks(DNN)-based estimation method for approximating the optimal velocity increments of perturbed multiple-impulse rendezvous and an reinforcement learning(RL)-based method for optimizing the sequence of debris removal and rendezvous time. Experimental results of different simulation scenarios have verified the effectiveness and superiority of the proposed method, indicating the good performance for solving the active debris removal mission planning problem.
- 15 March 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (6) , 1419
Open AccessActive Debris Removal Mission Planning Method Based on Machine Learning
To prevent the proliferation of space debris and stabilize the space environment, active debris removal (ADR) has increasingly gained public concern. Considering the complexity of space operations and the viability of ADR missions, it would be necessary to schedule the ADR process in order to remove as much debris as possible. This paper presents an active debris removal mission planning problem, devoted to generate an optimal debris removal plan to guide the mission process. According to the problem characteristics, a two-layer time-dependent traveling salesman problem(TSP) mathematical model is established, involving the debris removal sequence planning and the transfer trajectory planning. Subsequently, two main novel methods based on machine learning are proposed for the ADR mission planning problem, including a deep neural networks(DNN)-based estimation method for approximating the optimal velocity increments of perturbed multiple-impulse rendezvous and an reinforcement learning(RL)-based method for optimizing the sequence of debris removal and rendezvous time. Experimental results of different simulation scenarios have verified the effectiveness and superiority of the proposed method, indicating the good performance for solving the active debris removal mission planning problem.
- 31 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 57 (2) , 1123-1138
Fast Approximation of Optimal Perturbed Long-Duration Impulsive Transfers via Artificial Neural Networks
The design of multitarget rendezvous missions requires a method to quickly and accurately approximate the optimal transfer between any two rendezvous targets. In this paper, an artificial neural network-based method is proposed for the rapid approximation of optimal perturbed long-duration impulsive transfers. The relationship between the optimal transfer velocity increments and the initial right ascension of the ascending node difference between the departure body and the rendezvous target is analyzed, and the result suggests that the perturbed long-duration impulsive transfers should be divided into three types. An efficient database generation method is developed. Three regression multilayer perceptrons are trained individually and applied to approximate the corresponding types of transfers. The simulation results show that the well-trained multilayer perceptrons are capable of quickly estimating the optimal velocity increments with a relative error of less than 3% for all three types of transfers. Additional tests of the debris chains with total velocity increments of several thousand m/s show that the estimation results are very close to the optimized results, with a final estimation error of less than 10 m/s.
- 31 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 57 (2) , 1123-1138
Fast Approximation of Optimal Perturbed Long-Duration Impulsive Transfers via Artificial Neural Networks
The design of multitarget rendezvous missions requires a method to quickly and accurately approximate the optimal transfer between any two rendezvous targets. In this paper, an artificial neural network-based method is proposed for the rapid approximation of optimal perturbed long-duration impulsive transfers. The relationship between the optimal transfer velocity increments and the initial right ascension of the ascending node difference between the departure body and the rendezvous target is analyzed, and the result suggests that the perturbed long-duration impulsive transfers should be divided into three types. An efficient database generation method is developed. Three regression multilayer perceptrons are trained individually and applied to approximate the corresponding types of transfers. The simulation results show that the well-trained multilayer perceptrons are capable of quickly estimating the optimal velocity increments with a relative error of less than 3% for all three types of transfers. Additional tests of the debris chains with total velocity increments of several thousand m/s show that the estimation results are very close to the optimized results, with a final estimation error of less than 10 m/s.
- Open Access
Fast Approximation of Optimal Perturbed Long-Duration Impulsive Transfers via Deep Neural Networks
The design of multitarget rendezvous missions requires a method to quickly and accurately approximate the optimal transfer between any two rendezvous targets. In this paper, a deep neural network (DNN)-based method is proposed for quickly approximating optimal perturbed long-duration impulsive transfers. This kind of transfer is divided into three types according to the variation trend of the right ascension of the ascending node (RAAN) difference between the departure body and the rendezvous target. An efficient database generation method combined with a reliable optimization approach is developed. Three regression DNNs are trained individually and applied to approximate the corresponding types of transfers. The simulation results show that the well-trained DNNs are capable of quickly estimating the optimal velocity increments with a relative error of less than 3% for all the three types of transfers. The tests on the debris chains with the total velocity increments of several thousand m/s show that the estimated results can be very close to the optimized ones with a final estimation error of less than 10 m/s.
Open AccessFast Approximation of Optimal Perturbed Long-Duration Impulsive Transfers via Deep Neural Networks
The design of multitarget rendezvous missions requires a method to quickly and accurately approximate the optimal transfer between any two rendezvous targets. In this paper, a deep neural network (DNN)-based method is proposed for quickly approximating optimal perturbed long-duration impulsive transfers. This kind of transfer is divided into three types according to the variation trend of the right ascension of the ascending node (RAAN) difference between the departure body and the rendezvous target. An efficient database generation method combined with a reliable optimization approach is developed. Three regression DNNs are trained individually and applied to approximate the corresponding types of transfers. The simulation results show that the well-trained DNNs are capable of quickly estimating the optimal velocity increments with a relative error of less than 3% for all the three types of transfers. The tests on the debris chains with the total velocity increments of several thousand m/s show that the estimated results can be very close to the optimized ones with a final estimation error of less than 10 m/s.