Bin Yang
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
Research Subjects
Research Interests
Bin Yang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Shuang Li
Nanjing University of Aeronautics and Astronautics
6 shared publications - Beichao Wang
Department of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication - Bin Wu
Department of Electrical and Computer Engineering, Ryerson University, Toronto, ON, Canada
1 shared publication Chunmei Guo
School of Energy and Safety Engineering Tianjin Chengjian University Tianjin China
1 shared publication- Hanqi Zhong
Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication Huan Zhang
1 shared publication
Latest Publications
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 12182-12195
Pursuit Strategy Design for Orbital Pursuit–Evasion–Defense Games via Costate Guided Reinforcement Learning
The orbital pursuit-evasion-defense (PED) game is a highly challenging engineering problem, as the pursuer must intercept an evader while simultaneously avoiding active defense. To address this challenge, the PED game is decomposed into a bi-level structure, where the pursuit-evasion interaction is modeled as a Nash equilibrium game and the defense-pursuit interaction as a Stackelberg game led by the pursuer. Based on this formulation, a sufficient feasibility criterion for the pursuer is derived under the free-time optimal control framework. Proximal Policy Optimization (PPO) is then employed to learn a feedback control policy that drives the pursuer from arbitrary initial states toward configurations satisfying the criterion. To overcome the slow convergence caused by sparse rewards, a costate alignment mechanism is proposed. The mechanism exploits costate derived structural information to construct dense rewards that encourage consistency between the pursuer's optimal controls in both subgames. Moreover, an accelerated reward evaluation scheme combining fixed-time approximation and warm-start strategies is developed to improve training efficiency. Numerical simulations demonstrate that the proposed method enables the pursuer to successfully complete pursuit tasks under maneuvering capabilities comparable to the defender's, and exhibits superior performance compared to conventional fixed-weight differential game methods.
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 12182-12195
Pursuit Strategy Design for Orbital Pursuit–Evasion–Defense Games via Costate Guided Reinforcement Learning
The orbital pursuit-evasion-defense (PED) game is a highly challenging engineering problem, as the pursuer must intercept an evader while simultaneously avoiding active defense. To address this challenge, the PED game is decomposed into a bi-level structure, where the pursuit-evasion interaction is modeled as a Nash equilibrium game and the defense-pursuit interaction as a Stackelberg game led by the pursuer. Based on this formulation, a sufficient feasibility criterion for the pursuer is derived under the free-time optimal control framework. Proximal Policy Optimization (PPO) is then employed to learn a feedback control policy that drives the pursuer from arbitrary initial states toward configurations satisfying the criterion. To overcome the slow convergence caused by sparse rewards, a costate alignment mechanism is proposed. The mechanism exploits costate derived structural information to construct dense rewards that encourage consistency between the pursuer's optimal controls in both subgames. Moreover, an accelerated reward evaluation scheme combining fixed-time approximation and warm-start strategies is developed to improve training efficiency. Numerical simulations demonstrate that the proposed method enables the pursuer to successfully complete pursuit tasks under maneuvering capabilities comparable to the defender's, and exhibits superior performance compared to conventional fixed-weight differential game methods.
- 14 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 11153-11166
Time Deviation Sampling for Uncertainty Quantification in Impulsive Maneuver Using Neural Networks
Accurately quantifying the maneuver time uncertainty and impulsive maneuver deviation of spacecraft is an effective means to ensure the smooth progress of rendezvous, docking, and orbit determination missions. A method for quantification and propagation of uncertainty in maneuver time is presented. This method uses deep neural networks to sample the maneuvering time deviation in response to the strong coupling between maneuvering time and spacecraft state, as well as the strong nonlinearity of orbital dynamics. First, a maneuver time uncertainty quantification and propagation model is proposed, followed by an analysis of the efficiency and effectiveness of different sampling strategies. Subsequently, combined with the conclusions drawn from the analysis of the sampling strategies, an optimized sampling model is developed to address the issue of accuracy in the quantification of maneuver uncertainty. Finally, a deep neural network is trained as a surrogate model to instantaneously map process parameters to the sampling strategies. This replaces the costly online optimization process, enabling rapid and high-fidelity uncertainty quantification and propagation. Simulation results demonstrate that the proposed method can effectively quantify both the uncertainty of the maneuver time and the maneuver deviation.
- 14 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 11153-11166
Time Deviation Sampling for Uncertainty Quantification in Impulsive Maneuver Using Neural Networks
Accurately quantifying the maneuver time uncertainty and impulsive maneuver deviation of spacecraft is an effective means to ensure the smooth progress of rendezvous, docking, and orbit determination missions. A method for quantification and propagation of uncertainty in maneuver time is presented. This method uses deep neural networks to sample the maneuvering time deviation in response to the strong coupling between maneuvering time and spacecraft state, as well as the strong nonlinearity of orbital dynamics. First, a maneuver time uncertainty quantification and propagation model is proposed, followed by an analysis of the efficiency and effectiveness of different sampling strategies. Subsequently, combined with the conclusions drawn from the analysis of the sampling strategies, an optimized sampling model is developed to address the issue of accuracy in the quantification of maneuver uncertainty. Finally, a deep neural network is trained as a surrogate model to instantaneously map process parameters to the sampling strategies. This replaces the costly online optimization process, enabling rapid and high-fidelity uncertainty quantification and propagation. Simulation results demonstrate that the proposed method can effectively quantify both the uncertainty of the maneuver time and the maneuver deviation.
- 22 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (12) , 11496-11508
Transformer-based fire detection using moderate resolution imaging spectroradiometer
- 22 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (12) , 11496-11508
Transformer-based fire detection using moderate resolution imaging spectroradiometer
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 4784-4798
Low-Thrust Trajectory Optimization via Knowledge-Enhanced Deep Neural Network
This paper introduces the warm restart approach with a knowledge-enhanced deep neural network for solving the low-thrust trajectory optimization problem, where a variable preprocessor, a warm initiator, and an exact solver are developed and cooperatively utilized in the warm restart framework. For the warm initiator, the sample form incorporating homotopic parameter is firstly designed to greatly improve sample generation efficiency and convenience. Additionally, a knowledge-enhanced training strategy utilizing the residual of the nonlinear equations as the loss function is proposed to achieve efficient training and accurate approximation of deep neural network while maintaining acceptable time and computational costs. For the exact solver, an adaptive homotopy coefficient solver with the adaptive step size adjustment strategy is presented to balance the solution time and success. Application results in the Jovian system demonstrate significant improvement in the accuracy and reliability of the deep neural network following enhanced training. The results of comparative simulations further verify that the proposed method exhibits remarkable advantages in terms of computational efficiency and stability for both time-optimal and fixed-time fuel-optimal low-thrust trajectory optimization problems.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 4784-4798
Low-Thrust Trajectory Optimization via Knowledge-Enhanced Deep Neural Network
This paper introduces the warm restart approach with a knowledge-enhanced deep neural network for solving the low-thrust trajectory optimization problem, where a variable preprocessor, a warm initiator, and an exact solver are developed and cooperatively utilized in the warm restart framework. For the warm initiator, the sample form incorporating homotopic parameter is firstly designed to greatly improve sample generation efficiency and convenience. Additionally, a knowledge-enhanced training strategy utilizing the residual of the nonlinear equations as the loss function is proposed to achieve efficient training and accurate approximation of deep neural network while maintaining acceptable time and computational costs. For the exact solver, an adaptive homotopy coefficient solver with the adaptive step size adjustment strategy is presented to balance the solution time and success. Application results in the Jovian system demonstrate significant improvement in the accuracy and reliability of the deep neural network following enhanced training. The results of comparative simulations further verify that the proposed method exhibits remarkable advantages in terms of computational efficiency and stability for both time-optimal and fixed-time fuel-optimal low-thrust trajectory optimization problems.
- 5 September 2025
- Published by Elsevier in Acta Astronautica
- Vol. 238, 724-738
Satellite maneuver detection using dual-moving window curve fitting
- 5 September 2025
- Published by Elsevier in Acta Astronautica
- Vol. 238, 724-738
Satellite maneuver detection using dual-moving window curve fitting
- 22 April 2023
- Published by Elsevier in Advances In Space Research
- Vol. 72 (5) , 1485-1495
Spacecraft attitude maneuver planning with multi–sensor pointing constraints using improved RRT–star algorithm
- 22 April 2023
- Published by Elsevier in Advances In Space Research
- Vol. 72 (5) , 1485-1495
Spacecraft attitude maneuver planning with multi–sensor pointing constraints using improved RRT–star algorithm
- Open Access
On-Board Pedestrian Trajectory Prediction Using Behavioral Features
This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image. In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.
Open AccessOn-Board Pedestrian Trajectory Prediction Using Behavioral Features
This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image. In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.
- 7 March 2022
- Published by Wiley in Software: Practice and Experience
- Vol. 54 (10) , 1833-1851
Edge intelligence based digital twins for internet of autonomous unmanned vehicles
It aims to explore the efficient and reliable wireless transmission and cooperative communication mechanism of Internet of Vehicles (IoV) based on edge intelligence technology. It first proposes an intelligent network architecture for IoV services by combining network slicing and deep learning (DL) technology, and then began to study the key technologies needed to achieve the architecture. It designs the cooperative control mechanism of unmanned vehicle network based on the full study of wireless resource allocation algorithm from the micro level. Second, in order to improve the safety of vehicle driving, deep reinforcement learning is used to configure the wireless resources of IoV network to meet the needs of various IoV services. The research results show that the accuracy rate of the improved AlexNet algorithm model can reach 99.64%, the accuracy rate is more than 80%, the data transmission delay is less than 0.02 ms, and the data transmission packet loss rate is less than 0.05. The algorithm model has practical application value for solving the data transmission related problems of vehicular internet communication, providing an important reference value for the intelligent development of unmanned vehicle internet.
- 7 March 2022
- Published by Wiley in Software: Practice and Experience
- Vol. 54 (10) , 1833-1851
Edge intelligence based digital twins for internet of autonomous unmanned vehicles
It aims to explore the efficient and reliable wireless transmission and cooperative communication mechanism of Internet of Vehicles (IoV) based on edge intelligence technology. It first proposes an intelligent network architecture for IoV services by combining network slicing and deep learning (DL) technology, and then began to study the key technologies needed to achieve the architecture. It designs the cooperative control mechanism of unmanned vehicle network based on the full study of wireless resource allocation algorithm from the micro level. Second, in order to improve the safety of vehicle driving, deep reinforcement learning is used to configure the wireless resources of IoV network to meet the needs of various IoV services. The research results show that the accuracy rate of the improved AlexNet algorithm model can reach 99.64%, the accuracy rate is more than 80%, the data transmission delay is less than 0.02 ms, and the data transmission packet loss rate is less than 0.05. The algorithm model has practical application value for solving the data transmission related problems of vehicular internet communication, providing an important reference value for the intelligent development of unmanned vehicle internet.