Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Graph Learning-based Fleet Scheduling for Urban Air Mobility under Operational Constraints, Varying Demand & Uncertainties (2401.04851v1)

Published 9 Jan 2024 in cs.MA, cs.AI, and cs.LG

Abstract: This paper develops a graph reinforcement learning approach to online planning of the schedule and destinations of electric aircraft that comprise an urban air mobility (UAM) fleet operating across multiple vertiports. This fleet scheduling problem is formulated to consider time-varying demand, constraints related to vertiport capacity, aircraft capacity and airspace safety guidelines, uncertainties related to take-off delay, weather-induced route closures, and unanticipated aircraft downtime. Collectively, such a formulation presents greater complexity, and potentially increased realism, than in existing UAM fleet planning implementations. To address these complexities, a new policy architecture is constructed, primary components of which include: graph capsule conv-nets for encoding vertiport and aircraft-fleet states both abstracted as graphs; transformer layers encoding time series information on demand and passenger fare; and a Multi-head Attention-based decoder that uses the encoded information to compute the probability of selecting each available destination for an aircraft. Trained with Proximal Policy Optimization, this policy architecture shows significantly better performance in terms of daily averaged profits on unseen test scenarios involving 8 vertiports and 40 aircraft, when compared to a random baseline and genetic algorithm-derived optimal solutions, while being nearly 1000 times faster in execution than the latter.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. [n. d.]. See electric rates available to your home/business (updated today):. https://www.electricchoice.com/electricity-prices-by-state/
  2. 2023. Urban Air Mobility (UAM) Concept of Operations -v2.0. https://www.faa.gov/sites/faa.gov/files/Urban%20Air%20Mobility%20%28UAM%29%20Concept%20of%20Operations%202.0_0.pdf
  3. Exploratory combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1909.04063 (2019).
  4. Dung David Chuwang and Weiya Chen. 2022. Forecasting daily and weekly passenger demand for urban rail transit stations based on a time series model approach. Forecasting 4, 4 (2022), 904–924.
  5. Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility. arXiv preprint arXiv:2302.07337 (2023).
  6. Transforming Auto-Encoders. In Artificial Neural Networks and Machine Learning – ICANN 2011, Timo Honkela, Włodzisław Duch, Mark Girolami, and Samuel Kaski (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 44–51.
  7. Shyh In Hwang and Sheng Tzong Cheng. 2001. Combinatorial Optimization in Real-Time Scheduling: Theory and Algorithms. Journal of Combinatorial Optimization (2001). https://doi.org/10.1023/A:1011449311477
  8. Woodrow Bellamy III. [n. d.]. Evtol investments will continue billion dollar trend in 2021. http://interactive.aviationtoday.com/avionicsmagazine/february-march-2021/evtol-investments-will-continue-billion-dollar-trend-in-2021/
  9. Reconfiguring Unbalanced Distribution Networks using Reinforcement Learning over Graphs. In 2022 IEEE Texas Power and Energy Conference (TPEC). 1–6. https://doi.org/10.1109/TPEC54980.2022.9750805
  10. Are flying cars preparing for takeoff? https://www.morganstanley.com/ideas/autonomous-aircraft
  11. Yoav Kaempfer and Lior Wolf. 2018. Learning the Multiple Traveling Salesmen Problem with Permutation Invariant Pooling Networks. ArXiv abs/1803.09621 (2018).
  12. Nitin Kamra and Nora Ayanian. 2015. A mixed integer programming model for timed deliveries in multirobot systems. In 2015 IEEE International Conference on Automation Science and Engineering (CASE). IEEE, 612–617.
  13. Sang Hyun Kim. 2020. Receding Horizon Scheduling of On-Demand Urban Air Mobility With Heterogeneous Fleet. IEEE Trans. Aerospace Electron. Systems 56, 4 (2020), 2751–2761. https://doi.org/10.1109/TAES.2019.2953417
  14. V. Konda and J. Tsitsiklis. 2003. OnActor-Critic Algorithms. SIAM J. Control. Optim. 42 (2003), 1143–1166.
  15. Attention, learn to solve routing problems!. In 7th International Conference on Learning Representations, ICLR 2019. arXiv:1803.08475
  16. Fast Decision Support for Air Traffic Management at Urban Air Mobility Vertiports using Graph Learning. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 1580–1585.
  17. Combinatorial optimization with graph convolutional networks and guided tree search. In Advances in Neural Information Processing Systems. 539–548.
  18. Integer programming formulation of traveling salesman problems. Journal of the ACM (JACM) 7, 4 (1960), 326–329.
  19. H. Mühlenbein. 1991. Parallel genetic algorithms, population genetics and combinatorial optimization. In Parallelism, Learning, Evolution, J. D. Becker, I. Eisele, and F. W. Mündemann (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 398–406.
  20. A note on learning algorithms for quadratic assignment with graph neural networks. stat 1050 (2017), 22.
  21. Steve Paul and Souma Chowdhury. 2022a. A Graph-based Reinforcement Learning Framework for Urban Air Mobility Fleet Scheduling. In AIAA AVIATION 2022 Forum. 3911.
  22. Steve Paul and Souma Chowdhury. 2022b. A Scalable Graph Learning Approach to Capacitated Vehicle Routing Problem Using Capsule Networks and Attention Mechanism. In International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol. 86236. American Society of Mechanical Engineers, V03BT03A045.
  23. Learning Scalable Policies over Graphs for Multi-Robot Task Allocation using Capsule Attention Networks. In 2022 International Conference on Robotics and Automation (ICRA). IEEE, 8815–8822.
  24. Hierarchical Vertiport Network Design for On-Demand Multi-modal Urban Air Mobility. In 2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC). 1–8. https://doi.org/10.1109/DASC55683.2022.9925782
  25. Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art. Data Science and Engineering (2021), 1–23.
  26. Priyank Pradeep and Peng Wei. 2018. Heuristic Approach for Arrival Sequencing and Scheduling for eVTOL Aircraft in On-Demand Urban Air Mobility. In 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC). 1–7. https://doi.org/10.1109/DASC.2018.8569225
  27. Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research 22, 268 (2021), 1–8. http://jmlr.org/papers/v22/20-1364.html
  28. Ant colony optimization for real-world vehicle routing problems. Swarm Intelligence 1, 2 (2007), 135–151. https://doi.org/10.1007/s11721-007-0005-x
  29. Marc Josef Schoppmann. 2022. The operation of eVTOLs in the urban air mobility sector: use case & operator assessment. Ph. D. Dissertation.
  30. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG]
  31. Optimal eVTOL Fleet Dispatch for Urban Air Mobility and Power Grid Services. AIAA AVIATION 2020 FORUM (2020).
  32. Multi-agent routing value iteration network. In 37th International Conference on Machine Learning, ICML 2020. arXiv:2007.05096
  33. Urban air mobility airspace integration concepts and considerations. In 2018 Aviation Technology, Integration, and Operations Conference. 3676.
  34. Multi-Robot Coverage and Exploration using Spatial Graph Neural Networks. ArXiv abs/2011.01119 (2020).
  35. United States. Federal Highway Administration (Ed.). 2010. Our Nation’s Highways 2010. FHWA-PL-10-023 (Jan. 2010). https://rosap.ntl.bts.gov/view/dot/904
  36. Attention Is All You Need. CoRR abs/1706.03762 (2017). arXiv:1706.03762 http://arxiv.org/abs/1706.03762
  37. Saurabh Verma and Zhi Li Zhang. 2018. Graph capsule convolutional neural networks. arXiv:1805.08090
  38. Novel Ant Colony Optimization Methods for Simplifying Solution Construction in Vehicle Routing Problems. IEEE Transactions on Intelligent Transportation Systems 17, 11 (2016), 3132–3141. https://doi.org/10.1109/TITS.2016.2542264
  39. Scheduling of Urban Air Mobility Services with Limited Landing Capacity and Uncertain Travel Times. In 2021 American Control Conference (ACC). 1681–1686. https://doi.org/10.23919/ACC50511.2021.9482700
  40. Team scheduling by genetic search. In Intelligent Processing and Manufacturing of Materials, 1999. IPMM’99. Proceedings of the Second International Conference on, Vol. 2. IEEE, 839–844.
  41. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 11106–11115.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now