Guanjie Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guanjie Hu has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Jianguo Guo
Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xi’an 710072, China
9 shared publications - Zongyi Guo
Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xi’an 710072, China
8 shared publications - David Henry
University of Bordeaux, IMS Laboratory, F-33400 Talence, France
2 shared publications Jianguo Guo
Northwestern Polytechnical University
2 shared publications- Jérôme Cieslak
IMS-Lab, University of Bordeaux, Talence, France
2 shared publications Min Zhou
Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xian, China
2 shared publications
Latest Publications
- Open Access
A Review of Intelligent Trajectory Planning and Optimization for Aerospace Vehicles
Aerospace vehicles operate across a wide flight envelope, traversing dense atmospheric layers from near-space to low Earth orbit. Trajectory planning and optimization in a large spatial domain and wide speed range present severe challenges to traditional methods, including computational efficiency, model accuracy, and constraint adaptability. Artificial intelligence provides an effective pathway to overcome these limitations and has become a key driver for advancing trajectory planning and optimization of aerospace vehicles. This paper presents a systematic review of the core characteristics of aerospace trajectory planning, including environment coupling, multi-constraint compliance, propulsion integration, and aerodynamic nonlinearity, as well as the limitations of traditional methods. The study focuses on the application of intelligent algorithms in both the ascent and reentry phases. For the ascent phase, three key issues are addressed: multistage hybrid optimization with continuous and discrete variables, propulsion multimodal–trajectory coupling, and trajectory reconfiguration under engine failure. For the reentry phase, discussions are focused on such technical difficulties as multi-constraint trajectory generation, no-fly zone avoidance, and multi-mission requirement optimization. Finally, future research directions in intelligent trajectory planning and optimization are discussed, providing theoretical support and methodological guidance for the autonomous and intelligent development of aerospace vehicle trajectory planning.
Open AccessA Review of Intelligent Trajectory Planning and Optimization for Aerospace Vehicles
Aerospace vehicles operate across a wide flight envelope, traversing dense atmospheric layers from near-space to low Earth orbit. Trajectory planning and optimization in a large spatial domain and wide speed range present severe challenges to traditional methods, including computational efficiency, model accuracy, and constraint adaptability. Artificial intelligence provides an effective pathway to overcome these limitations and has become a key driver for advancing trajectory planning and optimization of aerospace vehicles. This paper presents a systematic review of the core characteristics of aerospace trajectory planning, including environment coupling, multi-constraint compliance, propulsion integration, and aerodynamic nonlinearity, as well as the limitations of traditional methods. The study focuses on the application of intelligent algorithms in both the ascent and reentry phases. For the ascent phase, three key issues are addressed: multistage hybrid optimization with continuous and discrete variables, propulsion multimodal–trajectory coupling, and trajectory reconfiguration under engine failure. For the reentry phase, discussions are focused on such technical difficulties as multi-constraint trajectory generation, no-fly zone avoidance, and multi-mission requirement optimization. Finally, future research directions in intelligent trajectory planning and optimization are discussed, providing theoretical support and methodological guidance for the autonomous and intelligent development of aerospace vehicle trajectory planning.
- 9 January 2026
- Published by Elsevier in Aerospace Science and Technology
- Vol. 171
Gradient-enhanced PINN-based hybrid attitude control for reentry vehicle under uncertainties
- 9 January 2026
- Published by Elsevier in Aerospace Science and Technology
- Vol. 171
Gradient-enhanced PINN-based hybrid attitude control for reentry vehicle under uncertainties
- 16 November 2025
- Published by Springer Nature
- p. 652-663
DRGA-Based Integrated Guidance Control Design with Field-of-View and Impact Angle Constraints
- 16 November 2025
- Published by Springer Nature
- p. 652-663
DRGA-Based Integrated Guidance Control Design with Field-of-View and Impact Angle Constraints
- 21 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 15857-15869
Ascent Trajectory and Parameter Collaborative Optimization for Aerospace Vehicles With Rocket-Based Combined Cycle Propulsion
The rocket-based combined cycle (RBCC) propulsion adopted by aerospace vehicles has multiple modes, and each mode operation and transition will directly affect the ascent trajectory design. This paper focuses on the ascent trajectory optimization research of aerospace vehicles with RBCC. Firstly, the trajectory optimization issue in ascent phase scenario is constructed considering the trajectory planning requirements for different propulsion modes. In order to balance the trajectory optimization and modal transition, an angle of attack-velocity profile design based on high-order polynomials is proposed. The number of constraints is significantly simplified through the profile design, and the collaborative optimization problem of ascent trajectory and modal parameters is constructed. Subsequently, three particle swarm optimization (PSO) improvement strategies are given oriented to convergence performance and constraint processing. Furthermore, a trajectory and parameter collaborative optimization method based on improved PSO and parallel search theory is proposed. At last, the effectiveness and superiority of the proposed method are illustrated through comparative simulations with existing methods.
- 21 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (6) , 15857-15869
Ascent Trajectory and Parameter Collaborative Optimization for Aerospace Vehicles With Rocket-Based Combined Cycle Propulsion
The rocket-based combined cycle (RBCC) propulsion adopted by aerospace vehicles has multiple modes, and each mode operation and transition will directly affect the ascent trajectory design. This paper focuses on the ascent trajectory optimization research of aerospace vehicles with RBCC. Firstly, the trajectory optimization issue in ascent phase scenario is constructed considering the trajectory planning requirements for different propulsion modes. In order to balance the trajectory optimization and modal transition, an angle of attack-velocity profile design based on high-order polynomials is proposed. The number of constraints is significantly simplified through the profile design, and the collaborative optimization problem of ascent trajectory and modal parameters is constructed. Subsequently, three particle swarm optimization (PSO) improvement strategies are given oriented to convergence performance and constraint processing. Furthermore, a trajectory and parameter collaborative optimization method based on improved PSO and parallel search theory is proposed. At last, the effectiveness and superiority of the proposed method are illustrated through comparative simulations with existing methods.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Intelligent tracking guidance adapted to the ascent phase of aerospace vehicles
Aiming at the tracking guidance problem in ascent phase of aerospace vehicles, an intelligent guidance method based on adaptive dynamic programming (ADP) is proposed. Firstly, decoupling transformation is carried out for the motion model of aerospace vehicle. Throttle opening and angle of attack are adopted to implement velocity tracking and altitude tracking, respectively. Secondly, multiple constraints under the complex flight environment in ascent phase are established and the observer is designed to deal with nonlinear uncertainties. Then, the cost function of ascent phase tracking guidance problem is constructed, and an ADP method is proposed to achieve the intelligent solution. Finally, it is proved that the tracking error and weight estimation errors of the tracking guidance system are uniformly ultimately bounded. And the proposed intelligent guidance method is verified by simulation.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Intelligent tracking guidance adapted to the ascent phase of aerospace vehicles
Aiming at the tracking guidance problem in ascent phase of aerospace vehicles, an intelligent guidance method based on adaptive dynamic programming (ADP) is proposed. Firstly, decoupling transformation is carried out for the motion model of aerospace vehicle. Throttle opening and angle of attack are adopted to implement velocity tracking and altitude tracking, respectively. Secondly, multiple constraints under the complex flight environment in ascent phase are established and the observer is designed to deal with nonlinear uncertainties. Then, the cost function of ascent phase tracking guidance problem is constructed, and an ADP method is proposed to achieve the intelligent solution. Finally, it is proved that the tracking error and weight estimation errors of the tracking guidance system are uniformly ultimately bounded. And the proposed intelligent guidance method is verified by simulation.
- 9 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (6) , 9342-9353
Reinforcement Learning-Based Integrated Decision-Making and Control for Morphing Flight Vehicles Under Aerodynamic Uncertainties
This paper presents an integrated decision-making and control framework of morphing flight vehicles with variable-span wings in the glide phase. The proposed framework comprehensively consists of morphing strategy, attitude control and online aerodynamic uncertainties estimate, thus outperforms existing works at its capacity of adequately considering the interaction between morphing mechanism and control design. Furthermore, the introduction of deep deterministic policy gradient (DDPG) algorithm has the effect of reducing the dependence on a precise model to some extent. By introducing aerodynamic uncertainties into the training environment and employing estimate, the framework enhances decision-making adaptability. Additionally, the decision-making method is designed to optimal a comprehensive performance index including lift-to-drag ratio and attitude tracking effect, thus ensuring the physical realisability. The effectiveness of decision-making and control is validated by simulation results.
- 9 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (6) , 9342-9353
Reinforcement Learning-Based Integrated Decision-Making and Control for Morphing Flight Vehicles Under Aerodynamic Uncertainties
This paper presents an integrated decision-making and control framework of morphing flight vehicles with variable-span wings in the glide phase. The proposed framework comprehensively consists of morphing strategy, attitude control and online aerodynamic uncertainties estimate, thus outperforms existing works at its capacity of adequately considering the interaction between morphing mechanism and control design. Furthermore, the introduction of deep deterministic policy gradient (DDPG) algorithm has the effect of reducing the dependence on a precise model to some extent. By introducing aerodynamic uncertainties into the training environment and employing estimate, the framework enhances decision-making adaptability. Additionally, the decision-making method is designed to optimal a comprehensive performance index including lift-to-drag ratio and attitude tracking effect, thus ensuring the physical realisability. The effectiveness of decision-making and control is validated by simulation results.
- 22 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (6) , 2436-2443
Koopman Operator-Based Integrated Guidance and Control for Strap-Down High-Speed Missiles
This work focuses on addressing the challenges of integrated guidance and control (IGC) for strap-down high-speed missiles with nonlinearities and field-of-view constraints. To achieve this, a data-driven prediction model using the Koopman operator is developed, which exhibits high accuracy in capturing the significant nonlinearities of the investigated high-speed missiles. Furthermore, the field-of-view restrictions imposed by the strap-down seeker are addressed by introducing a Lyapunov-based model predictive control (LMPC) scheme based on the linear Koopman prediction model. To enhance the robustness of the system, a disturbance observer is integrated into the Koopman-operator-based LMPC (KLMPC), enabling the estimation and compensation of disturbances. A KLMPC-based IGC (KLMPC-IGC) design framework is then developed to solve the constrained IGC problem, ensuring the stability and robustness of the closed-loop system. Numerical simulation results validate the higher prediction accuracy of the proposed linear prediction model compared with traditional local linearization prediction, as well as demonstrate the effectiveness of the presented approach.
- 22 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (6) , 2436-2443
Koopman Operator-Based Integrated Guidance and Control for Strap-Down High-Speed Missiles
This work focuses on addressing the challenges of integrated guidance and control (IGC) for strap-down high-speed missiles with nonlinearities and field-of-view constraints. To achieve this, a data-driven prediction model using the Koopman operator is developed, which exhibits high accuracy in capturing the significant nonlinearities of the investigated high-speed missiles. Furthermore, the field-of-view restrictions imposed by the strap-down seeker are addressed by introducing a Lyapunov-based model predictive control (LMPC) scheme based on the linear Koopman prediction model. To enhance the robustness of the system, a disturbance observer is integrated into the Koopman-operator-based LMPC (KLMPC), enabling the estimation and compensation of disturbances. A KLMPC-based IGC (KLMPC-IGC) design framework is then developed to solve the constrained IGC problem, ensuring the stability and robustness of the closed-loop system. Numerical simulation results validate the higher prediction accuracy of the proposed linear prediction model compared with traditional local linearization prediction, as well as demonstrate the effectiveness of the presented approach.
- 29 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (4) , 6047-6055
ADP-Based Intelligent Tracking Algorithm for Reentry Vehicles Subjected to Model and State Uncertainties
This article presents an adaptive dynamic programming-based intelligent control algorithm for the attitude tracking issue of reentry vehicles subject to model and state uncertainties simultaneously. The traditional control approaches struggle to achieve satisfactory tracking performance since the model and state are together influenced and deviated by the both uncertainties. Instead, the attitude tracking issue in this article is first transformed into an optimal regulation issue of the tracking error. Then, a novel cost function inspired by the idea of zero-sum game is introduced to eliminate the model uncertainties, and state uncertainties are handled dynamically by updating weights based on the optimality principle of the critic network. Consequently, the intelligent tracking control law is obtained by the optimal regulation. The stability of the system and the convergence of network weights are further analyzed using the Lyapunov stability theory. The effectiveness of the proposed control scheme is verified by simulations.
- 29 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 19 (4) , 6047-6055
ADP-Based Intelligent Tracking Algorithm for Reentry Vehicles Subjected to Model and State Uncertainties
This article presents an adaptive dynamic programming-based intelligent control algorithm for the attitude tracking issue of reentry vehicles subject to model and state uncertainties simultaneously. The traditional control approaches struggle to achieve satisfactory tracking performance since the model and state are together influenced and deviated by the both uncertainties. Instead, the attitude tracking issue in this article is first transformed into an optimal regulation issue of the tracking error. Then, a novel cost function inspired by the idea of zero-sum game is introduced to eliminate the model uncertainties, and state uncertainties are handled dynamically by updating weights based on the optimality principle of the critic network. Consequently, the intelligent tracking control law is obtained by the optimal regulation. The stability of the system and the convergence of network weights are further analyzed using the Lyapunov stability theory. The effectiveness of the proposed control scheme is verified by simulations.
- 25 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (4) , 3104-3115
Evaluation Model, Intelligent Assignment, and Cooperative Interception in Multimissile and Multitarget Engagement
A complete engagement framework, including evaluation model, intelligent assignment, and cooperative interception is proposed to address the issue of multimissile and multitarget engagement (MME). The concepts of targets threat degree and missiles interception effective degree are included in the evaluation model, which fully considers both the offensive and defensive sides. Then, the multitarget assignment is carried out based on the obtained evaluation model, and a reinforcement learning-based intelligent assignment strategy is adopted. This scheme is capable of quickly generating the optimal assignment in the complex and variable engagement environment by virtue of the self-learning and reward mechanism. Following the optimal assignment, a cooperative interception technique is used to ensure the interception mission efficiently and accurately. Finally, simulation results illustrate the validity of the proposed engagement framework.
- 25 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (4) , 3104-3115
Evaluation Model, Intelligent Assignment, and Cooperative Interception in Multimissile and Multitarget Engagement
A complete engagement framework, including evaluation model, intelligent assignment, and cooperative interception is proposed to address the issue of multimissile and multitarget engagement (MME). The concepts of targets threat degree and missiles interception effective degree are included in the evaluation model, which fully considers both the offensive and defensive sides. Then, the multitarget assignment is carried out based on the obtained evaluation model, and a reinforcement learning-based intelligent assignment strategy is adopted. This scheme is capable of quickly generating the optimal assignment in the complex and variable engagement environment by virtue of the self-learning and reward mechanism. Following the optimal assignment, a cooperative interception technique is used to ensure the interception mission efficiently and accurately. Finally, simulation results illustrate the validity of the proposed engagement framework.