請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98584完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 蔡欣穆 | zh_TW |
| dc.contributor.advisor | Hsin-Mu Tsai | en |
| dc.contributor.author | 陳懷平 | zh_TW |
| dc.contributor.author | Huai-Ping Chen | en |
| dc.date.accessioned | 2025-08-18T00:58:23Z | - |
| dc.date.available | 2025-08-18 | - |
| dc.date.copyright | 2025-08-15 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-05 | - |
| dc.identifier.citation | References
[1] E. Itoh, E. Itoh, E. Itoh, M. Mitici, and M. Mitici, “Queue-based modeling of the aircraft arrival process at a single airport,” Aerospace, 2019. [2] P. Kopardekar, P. Kopardekar, K. D. Bilimoria, K. D. Bilimoria, B. Sridhar, and B. Sridhar, “Initial concepts for dynamic airspace configuration,” null, 2007. [3] M. Navarrete, M. Navarrete, P. S. Cugnasca, and P. S. Cugnasca, “Automatic dependent surveillance in the air traffic system —a probabilistic approach,” null, 2004. [4] E. Hernández-Romero, E. Hernández-Romero, B. Josefsson, B. Josefsson, A. Lemetti, A. Lemetti, T. Polishchuk, T. Polishchuk, C. Schmidt, and C. Schmidt, “Integrating weather impact in air traffic controller shift scheduling in remote and conventional towers,” EURO Journal on Transportation and Logistics, 2022. [5] J. Orasanu, J. Orasanu, B. Parke, B. Parke, N. Kraft, N. Kraft, Y. Tada, Y. Tada, A. Hobbs, A. Hobbs, A. Hobbs, A. Hobbs, B. R. Anderson, B. Anderson, B. R. Anderson, L. McDonnell, L. McDonnell, V. Dulchinos, and V. Dulchinos, “Evaluating the effectiveness of schedule changes for air traffic service (ats) providers: Controller alertness and fatigue monitoring study,” null, 2012. [6] Eurocontrol, “Air-ground communication safety study causes and recommendations,” https://skybrary.aero/sites/default/files/bookshelf/162.pdf, 2005, [Accessed 16-06-2025]. [7] G. Vouros, G. A. Vouros, G. Papadopoulos, G. . Papadopoulos, A. Bastas, A. Bastas, J. M. Cordero, J. M. C. Ferrera, R. R. Rodrigez, and R. R. Rodrigez, “Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers,” Cornell University - arXiv, 2022. [8] F. A. A. U. D. of Transportation, “NextGen Annual Report Fiscal Year 2023,” https://www.faa.gov/nextgen/NextGen-Annual-Report-2023.pdf, [Accessed 03-03-2025]. [9] H. Erzberger, H. Erzberger, and H. Erzberger, “Automated conflict resolution for air traffic control,” null, 2005. [10] K. Bousson and K. Bousson, “Model predictive control approach to global air collision avoidance,” Aircraft Engineering and Aerospace Technology, 2008. [11] L. Deori, L. Deori, S. Garatti, S. Garatti, M. Prandini, and M. Prandini, “A model predictive control approach to aircraft motion control,” American Control Conference, 2015. [12] M. Kopf, M. Kopf, E. Bullinger, E. Bullinger, E. Bullinger, E. Bullinger, H.-G. Giesseler, H.-G. Giesseler, S. Adden, S. Adden, R. Findeisen, and R. Findeisen, “Model predictive control for aircraft load alleviation: Opportunities and challenges,” American Control Conference, 2018. [13] D. Tol, D. Tol, J. Hoekstra, J. Hoekstra, J. Hoekstra, A. Jamshidnejad, and A. Jamshidnejad, “A bi-level local and global model predictive control architecture for air traffic management,” International Conference on Intelligent Transportation Systems, 2021. [14] B. Ivanovic, B. Ivanovic, K. Leung, K. Leung, E. Szczerbicki, E. Schmerling, M. Pavone, and M. Pavone, “Multimodal deep generative models for trajectory prediction: A conditional variational autoencoder approach,” null, 2020. [15] T. Salzmann, B. Ivanovic, P. Chakravarty, and M. Pavone, “Trajectron dynamically feasible trajectory forecasting with heterogeneous data,” arXiv: Robotics, 2020. [16] E. Barsoum, E. Barsoum, J. R. Kender, J. R. Kender, Z. Liu, Z. Liu, and Z. Liu, “Hpgan: Probabilistic 3d human motion prediction via gan,” arXiv: Computer Vision and Pattern Recognition, 2017. [17] B. Varadarajan, A. S. Hefny, A. Srivastava, K. S. Refaat, N. Nayakanti, A. Cornman, K. Chen, B. Douillard, C. Lam, D. Anguelov, and B. Sapp, “Multipath++: Efficient information fusion and trajectory aggregation for behavior prediction,” IEEE International Conference on Robotics and Automation, 2021. [18] N. Nayakanti, R. Al‐Rfou, A. Zhou, K. Goel, K. S. Refaat, and B. Sapp, “Wayformer: Motion forecasting via simple efficient attention networks,” IEEE International Conference on Robotics and Automation, 2023. [19] J. Philion, X. B. Peng, and S. Fidler, “Trajeglish: Traffic modeling as next-token prediction,” International Conference on Learning Representations, 2023. [20] H.-C. Choi, H.-C. Choi, C. Deng, C. Deng, I. Hwang, and I. Hwang, “Hybrid machine learning and estimation-based flight trajectory prediction in terminal airspace,” IEEE Access, 2021. [21] X. Chu, W. Zeng, and L. Wu, “Joint prediction of multi-aircraft trajectories in terminal airspace: A flight pattern-guided social long-short term memory network,” Engineering applications of artificial intelligence, 2025. [22] P. N. T. Tran, P. N. Tran, H. Q. V. N. Nguyen, H. Q. Nguyen, D.-T. Pham, D.-T. Pham, S. Alam, and S. Alam, “Aircraft trajectory prediction with enriched intent using encoder-decoder architecture,” IEEE Access, 2022. [23] C.-H. Jiang, A. Cornman, C.-H. Park, B. Sapp, Y. Zhou, and D. Anguelov, “Motiondiffuser: Controllable multi-agent motion prediction using diffusion,” Computer Vision and Pattern Recognition, 2023. [24] Y. Yin, S. Zhang, Y. Zhang, Y. Zhang, and S. Xiang, “Context-aware aircraft trajectory prediction with diffusion models,” 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023. [25] W. Zeng, W. Zeng, X. Chu, X. Chu, Z. Xu, Z. Xu, Y. Liu, Y. Liu, Z. Quan, and Z. Quan, “Aircraft 4d trajectory prediction in civil aviation: A review,” Aerospace, 2022. [26] M. Meides, “The OpenSky Network - Free ADS-B and Mode S data for Research — opensky-network.org,” https://opensky-network.org/, [Accessed 25-01-2025]. [27] J. Ho, J. Ho, A. N. Jain, A. Jain, P. Abbeel, and P. Abbeel, “Denoising diffusion probabilistic models.” Neural Information Processing Systems, 2020. [28] J. Betker, G. Goh, L. Jing, . TimBrooks, J. Wang, L. Li, . LongOuyang, . JuntangZhuang, . JoyceLee, . YufeiGuo, . WesamManassra, . PrafullaDhariwal, . CaseyChu, . YunxinJiao, and A. Ramesh, “Improving image generation with better captions,” null, null. [29] C. Saharia, W. Chan, S. Saxena, L. Li, J. Whang, E. L. Denton, S. K. S. Ghasemipour, B. K. Ayan, S. S. Mahdavi, R. G. Lopes, T. Salimans, J. Ho, D. J. Fleet, and M. Norouzi, “Photorealistic text-to-image diffusion models with deep language understanding,” Neural Information Processing Systems, 2022. [30] R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-resolution image synthesis with latent diffusion models,” Computer Vision and Pattern Recognition, 2022. [31] T. Brooks, B. Peebles, C. Holmes, W. DePue, L. J. Y. Guo, D. Schnurr, J. Taylor, T. Luhman, E. Luhman, C. Ng, R. Wang, and A. Ramesh, “Video generation models as world simulators.” OpenAI, 2024. [32] A. Vaswani, A. Vaswani, N. Shazeer, N. Shazeer, N. Parmar, N. Parmar, J. Uszkoreit, J. Uszkoreit, L. Jones, L. Jones, A. N. Gomez, A. N. Gomez, Łukasz Kaiser, L. Kaiser, I. Polosukhin, and I. Polosukhin, “Attention is all you need,” Neural Information Processing Systems, 2017. [33] D. E. Rumelhart, D. E. Rumelhart, G. E. Hinton, G. E. Hinton, R. J. Williams, R. J. Williams, and R. J. Williams, “Learning internal representations by error propagation,” null, 1988. [34] D. E. Rumelhart and D. E. Rumelhart, “Learning internal representations by error propagation, parallel distributed processing,” null, 1986. [35] S. Hochreiter, S. Hochreiter, J. Schmidhuber, and J. Schmidhuber, “Long short-term memory,” Neural Computation, 1997. [36] J. Xu, X. Sun, X. Sun, X. Sun, Z. Zhang, G. Zhao, and J. Lin, “Understanding and improving layer normalization,” arXiv: Learning, 2019. [37] W. S. Peebles and S. Xie, “Scalable diffusion models with transformers,” IEEE International Conference on Computer Vision, 2022. [38] “openScope Air Traffic Control Simulator — openscope.io,” https://www.openscope.io/, [Accessed 22-01-2025]. [39] “GitHub - openscope/ openscope: openScope Air Traffic Control Simulator — github.com,” https://github.com/openscope/openscope, [Accessed 22-01-2025]. [40] A. Blåberg, A. Blaberg, G. Lindahl, G. Lindahl, A. Gurtov, A. Gurtov, B. Josefsson, and B. Josefsson, “Simulating ads-b attacks in air traffic management,” Symposium on Dependable Autonomic and Secure Computing, 2020. [41] R. Cestaro, M. Conti, E. Mancini, and F. Turrin, “Openscope-sec: An ads-b simulator to support the security research,” ARES, 2023. [42] I. C. A. O. (ICAO), “Air Traffic Management (Doc 4444). 16th Edition, 2016.” https://recursosdeaviacion.com/wp-content/uploads/2021/01/icao-doc-4444-air-traffic-management.pdf, [Accessed 07-02-2025]. [43] F. A. A. U. D. of Transportation, “Stabilized approach and landing,” https://www.faa.gov/sites/faa.gov/files/2022-01/Stabilized%20Approach%20and%20Landing.pdf, [Accessed 05-07-2025]. [44] D. Karikawa, D. Karikawa, H. Aoyama, and H. Aoyama, “Visualization and analysis of controllers’ working processes in en route air traffic control,” Interacción, 2015. [45] G. Martín-Rodríguez and J. J. C. Hernández, “Seasonal variations in daily data: An application to air passenger arrivals,” Journal of Air Transport Management, 2023. [46] J. S. C. (JSC), “Operational procedures at tokyo international airport (haneda),” https://www.schedule-coordination.jp/archives/arc_hnd/2010/operational_procedure_at_hnd.pdf, 2010, [Accessed 16-06-2025]. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98584 | - |
| dc.description.abstract | 中交通管制員（Air Traffic Controllers, ATCOs）在高壓環境中執勤，其人為錯誤可能導致嚴重後果。為減輕其工作負擔並提升運營安全性，我們提出了一套創新系統 AeroGuide，採用 Diffusion-Transformer 模型精準預測單架飛機的未來軌跡。該系統利用 OpenSky Network 提供的 ADS-B 數據進行訓練，生成準確的軌跡預測，並無縫整合至 GlideControl，後者是一種基於規則的演算法，可將預測結果轉化為具體的空中交通管制指令。為驗證系統效能，我們對 OpenScope（一款開源空中交通管制模擬器）進行改造，構建了基於東京國際機場現實場景的測試環境，對 AeroGuide 和 GlideControl 的結合進行綜合評估。模擬結果顯示，在超過 90,000 秒（略多於一天）的運行時間中，系統穩定運作，並取得卓越的性能表現：調整後的降落率平均值達 97.08%，中位數為 97.36%；降落率平均值為 95.07%，中位數為 95.27%。我們的主要貢獻包括：(1) 使用 OpenSky Network的 ADS-B 數 據 集 進 行 模 型 訓 練 與 評 估，(2) 開 發 基 於 Diffusion-Transformer 的AeroGuide 軌跡預測模型，(3) 設計將預測結果轉化為可操作指令的 GlideControl，(4) 改造 OpenScope 為可擴展的模擬器以進行系統集成與性能測試。本研究強調了數據驅動方法在支持空中交通管理與提升複雜現實場景運營成果方面的潛力。 | zh_TW |
| dc.description.abstract | Air traffic controllers (ATCOs) operate in high-stress environments where human error can have significant consequences. To alleviate their workload and enhance operational safety, we propose AeroGuide, a novel system that leverages Diffusion-Transformer models to predict aircraft trajectories with high precision, one aircraft at a time. Using the OpenSky Network’s ADS-B data as the training dataset, our model generates accurate future trajectory predictions and integrates seamlessly with GlideControl, a rule-based algorithm that translates these predictions into actionable air traffic control commands. To validate our system, we modified OpenScope, an open-source air traffic control simulator, creating a testing environment where the combination of AeroGuide and GlideControl was evaluated under realistic scenarios at Tokyo International Airport. Results collected over 90,000 seconds of simulated time (slightly over one day) demonstrate stable performance across experimental runs. The adjusted landed rate achieved a mean of 97.08% and a median of 97.36%, while the landed rate reached a mean of 95.07% and a median of 95.27%. Our key contributions include: (1) the utilization of the OpenSky Network ADS-B dataset for model training and evaluation, (2) the development of AeroGuide, a Diffusion-Transformer-based model for trajectory prediction, (3) the design of GlideControl for translating predictions into actionable commands, and (4) the adaptation of OpenScope as a scalable simulator for system integration and evaluation. This study underscores the potential for data-driven approaches to support air traffic management and enhance operational outcomes in complex real-world settings. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-18T00:58:23Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-18T00:58:23Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書i
誌謝ii 摘要iii Abstract iv Contents vi List of Figures x List of Tables xiv Chapter 1 Introduction 1 Chapter 2 Related Work 6 2.1 Model Predictive Control . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Trajectory Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 Diffusion-Based Models for Trajectory Prediction . . . . . . . . . . . 8 Chapter 3 Preliminary 10 3.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.1 OpenSky Network Dataset . . . . . . . . . . . . . . . . . . . . . . 10 3.2 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.1 Diffusion Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.2 Transformer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2.3 Adaptive Normalization . . . . . . . . . . . . . . . . . . . . . . . . 14 3.3 Evaluation Tool . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.3.1 OpenScope Air Traffic Control Simulator . . . . . . . . . . . . . . 14 Chapter 4 System Design 16 4.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.2 OpenSky Data Processing . . . . . . . . . . . . . . . . . . . . . . . 17 4.2.1 Pre-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2.2 Post-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.3 OpenSky Storage . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.3.1 Feature Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.2 Sampled Dataset Structure . . . . . . . . . . . . . . . . . . . . . . 27 4.3.3 Data Sampling Methodology . . . . . . . . . . . . . . . . . . . . . 28 4.4 AeroGuide - Future Trajectory Predictor . . . . . . . . . . . . . . . . 29 4.4.1 Training Stage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.4.2 Inference Stage . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.5 OpenScope - Air Traffic Control Simulator . . . . . . . . . . . . . . 31 4.5.1 Custom API Integration . . . . . . . . . . . . . . . . . . . . . . . . 32 4.6 GlideControl - Trajectory Action Converter . . . . . . . . . . . . . . 34 4.6.1 Action Selection Index and Target Vector . . . . . . . . . . . . . . 34 4.6.2 Instrument Landing System . . . . . . . . . . . . . . . . . . . . . . 35 4.6.3 Action Decision Flow . . . . . . . . . . . . . . . . . . . . . . . . . 37 Chapter 5 Implementation 40 5.1 OpenSky Dataset Analysis and Insights . . . . . . . . . . . . . . . . 40 5.1.1 Data Selection and Scope Definition . . . . . . . . . . . . . . . . . 40 5.1.2 Runway Utilization and Trajectory Analysis . . . . . . . . . . . . . 41 5.1.3 Arrival Process . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 5.1.4 Separation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 5.2 Training Dataset Context Length . . . . . . . . . . . . . . . . . . . . 48 5.2.1 Sampling Time Duration . . . . . . . . . . . . . . . . . . . . . . . 50 5.2.2 The Number of Past and Future Trajectory Points . . . . . . . . . . 50 5.2.3 Number of Neighbor Aircraft . . . . . . . . . . . . . . . . . . . . . 52 5.3 AeroGuide Model Architecture . . . . . . . . . . . . . . . . . . . . 55 5.4 OpenScope Modification, Analysis, and Insights . . . . . . . . . . . 56 5.4.1 Sim-to-Real Gap . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 Chapter 6 Evaluation 60 6.1 Trajectory Prediction Performance . . . . . . . . . . . . . . . . . . . 60 6.1.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . 60 6.1.2 Prediction Error . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61 6.1.3 Baseline Comparison . . . . . . . . . . . . . . . . . . . . . . . . . 63 6.1.4 Case Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65 6.2 Integrated System Performance . . . . . . . . . . . . . . . . . . . . 67 6.2.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . 67 6.2.2 Performance Metrics . . . . . . . . . . . . . . . . . . . . . . . . . 68 6.2.3 Optimal AeroGuide Model Checkpoint Selection . . . . . . . . . . 70 6.2.4 Tuning GlideControl for Optimal Performance . . . . . . . . . . . . 72 6.2.5 Overall Performance . . . . . . . . . . . . . . . . . . . . . . . . . 74 6.2.6 Statistical Validation of Landed Time Period . . . . . . . . . . . . . 77 6.2.7 Separation Comparison . . . . . . . . . . . . . . . . . . . . . . . . 79 6.2.8 Case Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84 Chapter 7 Conclusion 90 References 92 | - |
| dc.language.iso | en | - |
| dc.subject | OpenScope 模擬器 | zh_TW |
| dc.subject | 航空交通管理 | zh_TW |
| dc.subject | OpenSky 網絡 | zh_TW |
| dc.subject | 擴散變壓器模型 | zh_TW |
| dc.subject | 飛機軌跡預測 | zh_TW |
| dc.subject | OpenScope Simulator | en |
| dc.subject | OpenSky Network | en |
| dc.subject | Diffusion-Transformer Models | en |
| dc.subject | Aircraft Trajectory Prediction | en |
| dc.subject | Air Traffic Management | en |
| dc.title | Auto-ATC：基於擴散變換器技術的自動空中交通管制系統 | zh_TW |
| dc.title | Auto-ATC: A Diffusion-Transformer-Based Automatic Air Traffic Control System | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 柯宗瑋;李濬屹;郭嘉偉 | zh_TW |
| dc.contributor.oralexamcommittee | Tsung-Wei Ke;Chun-Yi Lee;Chia-Wei Kuo | en |
| dc.subject.keyword | 航空交通管理,飛機軌跡預測,擴散變壓器模型,OpenSky 網絡,OpenScope 模擬器, | zh_TW |
| dc.subject.keyword | Air Traffic Management,Aircraft Trajectory Prediction,Diffusion-Transformer Models,OpenSky Network,OpenScope Simulator, | en |
| dc.relation.page | 98 | - |
| dc.identifier.doi | 10.6342/NTU202504041 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-08-11 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 18.98 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。