科研
在应用层面，我的工作沿着空中交通管制中一次飞行的三个阶段展开：理解天气等不确定性如何影响航路运行，通过自动化提升进近管制区运行的效率与安全，以及研究机场场面运行的安全性与可靠性。近年来，我还开展了先进空中交通与自主运行方面的工作，例如 NASA 山火项目，这类运行场景有望成为未来空域系统的重要组成部分。
在理论层面，我关注风险与可靠性、安全与信息安全，以及人工智能系统的可信性，这类系统正越来越多地用于空中交通管制等安全攸关的场景。
1. 多源不确定性（气象等）对航路运行影响的研究
在航路阶段，我研究对流天气等不确定性如何影响航班与交通流：
- 天气不确定性下的航空器概率轨迹预测
- 面向流量管理的空中交通态势与密度预测
- 基于工作负荷学习预测的动态空域扇区划分
- 管制员认知工作负荷预测
1.1 Air Traffic Controller Cognitive Workload Level Prediction using Conformal Dynamical Graph Learning. Pang, Y., Hu, J., Lieber, C., Cooke, N., & Liu, Y. Advanced Engineering Informatics, 2023. [bib]
1.2 Data-driven trajectory prediction with weather uncertainties: A Bayesian deep learning approach. Pang, Y., Zhao, X., Yan, H., & Liu, Y. Transportation Research Part C: Emerging Technologies, 2021. [bib]
1.3 PIGAT: Physics-Informed Graph Attention Transformer for Air Traffic State Prediction. Xu, Q., Pang, Y., Zhou, X., & Liu, Y. IEEE Transactions on Intelligent Transportation Systems, 2024. [bib]
该方向的全部论文（另有 12 篇）
1.4 Probabilistic Aircraft Trajectory Prediction with Weather Uncertainties using Approximate Bayesian Variational Inference to Neural Networks. Pang, Y., Wang, Y., & Liu, Y. AIAA AVIATION 2020 Forum, 2020. [bib]
1.5 Conditional Generative Adversarial Networks (CGAN) for Aircraft Trajectory Prediction considering weather effects. Pang, Y. & Liu, Y. AIAA SciTech 2020 Forum, 2020. [bib]
1.6 Probabilistic Aircraft Trajectory Prediction Considering Weather Uncertainties Using Dropout As Bayesian Approximate Variational Inference. Pang, Y. & Liu, Y. AIAA SciTech 2020 Forum, 2020. [bib]
1.7 Aircraft trajectory prediction using LSTM neural network with embedded convolutional layer. Pang, Y., Hu, J., Cheng, S., & Liu, Y. 11th Annual Conference of the Prognostics and Health Management Society, 2019. [bib]
1.8 A Recurrent Neural Network Approach for Aircraft Trajectory Prediction with Weather Features From Sherlock. Pang, Y., Yao, H., Hu, J., & Liu, Y. AIAA AVIATION 2019 Forum, 2019. [bib]
1.9 Dynamic airspace sectorization with machine learning enhanced workload prediction and clustering. Xu, Q., Pang, Y., & Liu, Y. Journal of Air Transport Management, 2024. [bib]
1.10 Systems and Methods for Air Traffic Controller Workload Level Prediction using Conformalized Dynamical Graph Learning. Liu, Y., Pang, Y., & Hu, J. U.S. Patent, 2024. [bib]
1.11 Air Traffic Density Prediction using Bayesian Ensemble Graph Attention Network (BEGAN). Xu, Q., Pang, Y., & Liu, Y. Transportation Research Part C: Emerging Technologies, 2023. [bib]
1.12 Uncertainty quantification and reduction in aircraft trajectory prediction using Bayesian-Entropy information fusion. Wang, Y., Pang, Y., Chen, O., Iyer, H. N., Dutta, P., Menon, P. K., & Liu, Y. Reliability Engineering & System Safety, 2021. [bib]
1.13 Aircraft Trajectory Prediction and Risk Assessment Using Bayesian Updating. Wang, Y., Pang, Y., Liu, Y., Dutta, P., & Yang, B. J. AIAA AVIATION 2019 Forum, 2019. [bib]
1.14 Systems and Methods for Dynamic Airspace Sectorization with Machine Learning Enhanced Workload Prediction and Clustering. Liu, Y., Xu, Q., & Pang, Y. U.S. Patent, 2024. [bib]
1.15 Spatio-temporal Anomaly Detection, Diagnostics, and Prediction of the Air-traffic Trajectory Deviation using Convective Weather. Zhao, X., Yan, H., Li, J., Pang, Y., & Liu, Y. Annual Conference of the PHM Society, Vol. 11, 2019. [bib]
2. 基于自动化技术的进近管制区运行的效率与安全
在终端机动区，我为进港运行构建自动化方法，并量化终端飞行程序的安全边界：
- 基于轨迹的进港排序与下降程序协同优化
- 风场不确定性下的燃油最优下降程序
- 多机与程序感知的轨迹预测
- 机器学习增强的着陆排序与自主着陆
- 通信与人因不确定性影响下的跑道容量
- 避撞控制律及其容量极限
2.1 Trajectory-Based Co-Optimization of Arrival Scheduling and Descent Path Design in the Terminal Maneuvering Area. Pang, Y.* & Clarke, J. Under review at Aerospace Science and Technology. [bib]
2.2 Modeling the Impact of Communication and Human Uncertainties on Runway Capacity in Terminal Airspace. Pang, Y.*, Kendall, A., & Clarke, J. Journal of Air Transport Management, 2026. [bib]
2.3 Optimal TRACON Descent Procedures under Wind Uncertainty and Fuel Savings Factors. Pang, Y.* & Clarke, J. Under review at AIAA Journal of Aircraft. [bib]
2.4 Trajectory-Based Optimization for Air Traffic Control in the Terminal Maneuvering Area. Pang, Y.*, Delahaye, D., & Clarke, J. Under review at Transportation Research Part C. [bib]
该方向的全部论文（另有 9 篇）
2.5 Geometric Trajectory Optimization for TRACON Arrivals: An NLP Approach with ATC Vectoring Maneuver Modeling. Pang, Y., Delahaye, D., & Clarke, J. Annual Modeling and Simulation Conference 2026, 2026. [bib]
2.6 A Reactive Control Law for Aircraft Collision Avoidance and Its Capacity Limits. Pang, Y.*, Kendall, A., & Clarke, J. 工作论文，撰写中。 [bib]
2.7 V-STAR: VectorNet-Augmented Spatio-Temporal Attention and Reasoning for Procedure-Aware Aircraft Trajectory Prediction. Pang, Y., Hu, J., Iyer, H., Zhao, X., & Clarke, J. Under review at Transportation Research Part C. [bib]
2.8 Machine Learning-Enhanced Aircraft Landing Scheduling under Uncertainties. Pang, Y., Zhao, P., Hu, J., & Liu, Y. Transportation Research Part C: Emerging Technologies, 2024. [bib]
2.9 Bayesian Spatio-Temporal Graph Transformer Network (B-STAR) for Multi-Aircraft Trajectory Prediction. Pang, Y., Zhao, X., Hu, J., Yan, H., & Liu, Y. Knowledge-Based Systems, 2022. [bib]
2.10 Data-driven governing equation identification of near terminal air traffic flow dynamics. Xu, Q., Pang, Y., & Liu, Y. Journal of Air Transport Management, 2025. [bib]
2.11 Systems and Methods for Machine Learning-Enhanced Aircraft Landing Scheduling Under Uncertainties. Liu, Y., Pang, Y., & Hu, J. U.S. Patent, 2024. [bib]
2.12 A Voice Communication-Augmented Simulation Framework for Aircraft Trajectory Simulation. Wang, Y., Pang, Y., Gorceski, S., Kostiuk, P., Mohen, M. T., Menon, P. K., & Liu, Y. IEEE Transactions on Intelligent Transportation Systems, 2021. [bib]
2.13 Deep Q-Network With Lagrangian Relaxation for Autonomous Aircraft Landing. Momit, M. A., Jiang, W., Hussain, B. Z., Ammar, M., Bhujel, S., Pang, Y., et al., & Hu, J. AIAA SCITECH 2026 Forum, 2026. [bib]
3. 机场场面运行的安全性与可靠性研究
在机场场面，我把飞行员与管制员的话音通信和监视数据转化为安全与效率工具：
- 基于陆空通话的场面移动碰撞风险评估
- 融合管制话音与 ADS-B 的实时跑道侵入告警
- 着陆航空器的跑道与滑行道脱离口预测
3.1 Data-Driven Runway and Taxiway Exits Prediction of Landing Aircraft: A Case Study at Hartsfield-Jackson Atlanta International Airport. Porcayo, A., Pang, Y.*, Thomas, M., & Clarke, J. Journal of Air Transport Management, 2026. [bib]
3.2 From Voice to Safety: Language AI Powered Pilot-ATC Communication Understanding for Airport Surface Movement Collision Risk Assessment. Pang, Y.*, Kendall, A. P., Porcayo, A., Barsotti, M., Jain, A., & Clarke, J. Transportation Research Part C: Emerging Technologies, 2026. [bib]
该方向的全部论文（另有 2 篇）
3.3 A Probabilistic Runway Occupancy Conflict Alerting Framework for Real-Time Runway Incursion Detection from ATC Speech and ADS-B. Dong, Z., Pang, Y.*, & Clarke, J. Under review at AIAA Journal of Aerospace Information Systems. [bib]
3.4 Physics-Based Learning for Aircraft Waiting Time Prediction. Xu, Q., Pang, Y., Zhang, Z., & Liu, Y. AIAA AVIATION 2022 Forum, 2022. [bib]
4. 先进空中交通与自主运行
在有人驾驶航空之外，我研究先进空中交通、遥控驾驶航空器与自主配送运行：
- 通信不确定性下遥控驾驶航空器的可靠性
- 自主运行中通信水平与自主等级的权衡
- 带容量与时限保证的最后一公里与当日配送路径规划
- 无人机包裹投送的空气动力学
- 面向分布式决策的多智能体强化学习
4.1 The Reliability of Remotely Piloted Aircraft System Performance under Aeronautical Communication Uncertainties. Pang, Y.*, Kendall, A., & Clarke, J. Reliability Engineering & System Safety, 2026. [bib]
4.2 Optimizing Same-Day Delivery: A Framework Incorporating Vehicle Capacity and Time Guarantees. Liang, J., Pang, Y.*, & Clarke, J. Under review at International Journal of Systems Science: Operations & Logistics. [bib]
4.3 Decentralized graph-based multi-agent reinforcement learning using reward machines. Hu, J., Xu, Z., Wang, W., Qu, G., Pang, Y., & Liu, Y. Neurocomputing, 2023. [bib]
该方向的全部论文（另有 3 篇）
4.4 An Optimization Formulation for Last-Mile Delivery Using Ring Widget Structure. Liang, J., Pang, Y.*, & Clarke, J. 工作论文，撰写中。 [bib]
4.5 Communication and Autonomy Level Tradeoff for Autonomous Systems Resource Allocation. Pang, Y.*, Kendall, A., & Clarke, J. 工作论文，撰写中。 [bib]
4.6 Aerodynamic Effects of Fuselage-Package Separation Distance on UAV Performance. Bhujel, S., Pang, Y., Snyder, P., Tang, C., & Hu, J. AIAA AVIATION 2026 Forum, 2026. [bib]
5. 可靠性与可信人工智能
支撑上述应用的，是可信机器学习与可靠性工程方面的方法研究：
- 航空安全报告的可解释风险分析
- 面向深度学习的贝叶斯不确定性量化
- 用于断裂与结构健康监测的物理信息学习
- 贝叶斯神经网络的对抗鲁棒性
- 不确定性下的维修排程
5.1 A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Counterfactual Analysis. Pang, Y., Tian, Y., Xie, J., Zhao, X., Hu, J., Jacobsen, H., & Clarke, J. To be submitted to Advanced Engineering Informatics. [bib]
5.2 Epistemic and aleatoric uncertainty quantification for crack detection using a Bayesian Boundary Aware Convolutional Network. Rathnakumar, R., Pang, Y., & Liu, Y. Reliability Engineering & System Safety, 2023. [bib]
5.3 Posterior Regularized Bayesian Neural Network Incorporating Soft and Hard Knowledge Constraints. Huang, J., Pang, Y., Zhao, X., Liu, Y., & Yan, H. Knowledge-Based Systems, 2022. [bib]
该方向的全部论文（另有 6 篇）
5.4 Robust Satellite Image Classification with Bayesian Deep Learning. Pang, Y., Xu, N., & Liu, Y. 2022 Integrated Communication, Navigation and Surveillance Conference (ICNS), 2022. [bib]
5.5 Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks. Pang, Y., Cheng, S., Hu, J., & Liu, Y. CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems, 2021. [bib]
5.6 Bayesian Approach for Uncertainty Quantification of Neural Networks-Based Crack Diagnostics. Rathnakumar, R., Liu, Y., & Pang, Y. AIAA SCITECH 2025 Forum, 2025. [bib]
5.7 FBC-ANet: A Semantic Segmentation Model for UAV Forest Fire Images Combining Boundary Enhancement and Context Awareness. Zhang, L., Wang, M., Ding, Y., Wan, T., Qi, B., & Pang, Y. Drones, 2023. [bib]
5.8 Optimal maintenance scheduling under uncertainties using Linear Programming-enhanced Reinforcement Learning. Hu, J., Wang, Y., Pang, Y., & Liu, Y. Engineering Applications of Artificial Intelligence, 2022. [bib]
5.9 Fracture Pattern Prediction with Random Microstructure using Physics-Informed Deep Neural Networks. Wei, H., Yao, H., Pang, Y., & Liu, Y. Engineering Fracture Mechanics, 2022. [bib]