Papers
Topics
Authors
Recent
2000 character limit reached

Origin-Destination Travel Time Oracle for Map-based Services

Published 6 Jul 2023 in cs.LG | (2307.03048v1)

Abstract: Given an origin (O), a destination (D), and a departure time (T), an Origin-Destination (OD) travel time oracle~(ODT-Oracle) returns an estimate of the time it takes to travel from O to D when departing at T. ODT-Oracles serve important purposes in map-based services. To enable the construction of such oracles, we provide a travel-time estimation (TTE) solution that leverages historical trajectories to estimate time-varying travel times for OD pairs. The problem is complicated by the fact that multiple historical trajectories with different travel times may connect an OD pair, while trajectories may vary from one another. To solve the problem, it is crucial to remove outlier trajectories when doing travel time estimation for future queries. We propose a novel, two-stage framework called Diffusion-based Origin-destination Travel Time Estimation (DOT), that solves the problem. First, DOT employs a conditioned Pixelated Trajectories (PiT) denoiser that enables building a diffusion-based PiT inference process by learning correlations between OD pairs and historical trajectories. Specifically, given an OD pair and a departure time, we aim to infer a PiT. Next, DOT encompasses a Masked Vision Transformer~(MViT) that effectively and efficiently estimates a travel time based on the inferred PiT. We report on extensive experiments on two real-world datasets that offer evidence that DOT is capable of outperforming baseline methods in terms of accuracy, scalability, and explainability.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Structured denoising diffusion models in discrete state-spaces. In NeurIPS, Vol. 34. 17981–17993.
  2. Fresh-product supply chain management with logistics outsourcing. Omega 41, 4 (2013), 752–765.
  3. A survey on map-matching algorithms. In ADC. Springer, 121–133.
  4. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In ACM SIGKDD. 785–794.
  5. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP. 1724–1734.
  6. History oblivious route recovery on road networks. In SIGSPATIAL. 1–10.
  7. Teodor Gabriel Crainic and Gilbert Laporte. 1997. Planning models for freight transportation. European journal of operational research 97, 3 (1997), 409–438.
  8. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR.
  9. Deepmove: Predicting human mobility with attentional recurrent networks. In WWW. 1459–1468.
  10. Compacteta: A fast inference system for travel time prediction. In ACM SIGKDD. 3337–3345.
  11. Travel Time Estimation Based on Neural Network with Auxiliary Loss. In SIGSPATIAL. 642–645.
  12. An attentional recurrent neural network for personalized next location recommendation. In AAAI, Vol. 34. 83–90.
  13. DeepTEA: effective and efficient online time-dependent trajectory outlier detection. Proc. VLDB Endow. 15, 7 (2022), 1493–1505.
  14. Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016).
  15. Denoising diffusion probabilistic models. In NeurIPS, Vol. 33. 6840–6851.
  16. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
  17. A learning-based method for computing shortest path distances on road networks. In ICDE. 360–371.
  18. Tsuyoshi Idé and Masashi Sugiyama. 2011. Trajectory regression on road networks. In AAAI, Vol. 25. 203–208.
  19. Christopher Jarzynski. 1997. Equilibrium free-energy differences from nonequilibrium measurements: A master-equation approach. Physical Review E 56, 5 (1997), 5018.
  20. Christian S. Jensen and Nerius Tradišauskas. 2009. Map Matching. In Encyclopedia of Database Systems. 1692–1696.
  21. Hierarchical neural architecture search for travel time estimation. In SIGSPATIAL. 91–94.
  22. A unified neural network approach for estimating travel time and distance for a taxi trip. arXiv preprint arXiv:1710.04350 (2017).
  23. Donald B Johnson. 1973. A note on Dijkstra’s shortest path algorithm. J. ACM 20, 3 (1973), 385–388.
  24. Lightgbm: A highly efficient gradient boosting decision tree. In NeurIPS, Vol. 30. 3146–3154.
  25. Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020).
  26. Spatial transition learning on road networks with deep probabilistic models. In ICDE. 349–360.
  27. Learning travel time distributions with deep generative model. In WWW. 1017–1027.
  28. Towards fast and accurate solutions to vehicle routing in a large-scale and dynamic environment. In SSTD. 119–136.
  29. Multi-task representation learning for travel time estimation. In ACM SIGKDD. 1695–1704.
  30. Pre-training context and time aware location embeddings from spatial-temporal trajectories for user next location prediction. In AAAI, Vol. 35. 4241–4248.
  31. Todd Litman. 2009. Transportation cost and benefit analysis. Victoria Transport Policy Institute 31 (2009), 1–19.
  32. Finding top-k shortest paths with diversity. IEEE Trans. on Know. and Data Eng. 30, 3 (2017), 488–502.
  33. A convnet for the 2020s. In IEEE CVPR. 11976–11986.
  34. Brian K Nelson. 1998. Time series analysis using autoregressive integrated moving average (ARIMA) models. Academic emergency medicine 5, 7 (1998), 739–744.
  35. PyTorch: An imperative style, high-performance deep learning library. In NeurIPS. 8024–8035.
  36. High-resolution image synthesis with latent diffusion models. In IEEE CVPR. 10684–10695.
  37. U-net: Convolutional networks for biomedical image segmentation. In MICCAI. 234–241.
  38. Doing in One Go: Delivery Time Inference Based on Couriers’ Trajectories. In ACM SIGKDD. 2813–2821.
  39. Jagan Sankaranarayanan and Hanan Samet. 2009. Distance Oracles for Spatial Networks. In ICDE. 652–663.
  40. Path Oracles for Spatial Networks. Proc. VLDB Endow. 2, 1 (2009), 1210–1221.
  41. Deep unsupervised learning using nonequilibrium thermodynamics. In ICML. 2256–2265.
  42. Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. In NeurIPS, Vol. 32. 11895–11907.
  43. Deep Fusion for Travel Time Estimation Based on Road Network Topology. IEEE Intelligent Systems 37, 3 (2022), 98–107.
  44. CSDI: Conditional score-based diffusion models for probabilistic time series imputation. In NeurIPS, Vol. 34. 24804–24816.
  45. Attention is all you need. In NeurIPS, Vol. 30. 5998–6008.
  46. Fine-Grained Trajectory-Based Travel Time Estimation for Multi-City Scenarios Based on Deep Meta-Learning. IEEE Trans. on Intelli. Trans. Sys. 23, 9 (2022), 15716–15728.
  47. When will you arrive? Estimating travel time based on deep neural networks. In AAAI, Vol. 32. 2500–2507.
  48. A simple baseline for travel time estimation using large-scale trip data. ACM Trans. on Intelli. Sys. and Tech. 10, 2 (2019), 1–22.
  49. Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graphs. ACM Trans. on Intelli. Sys. and Tech. 13, 1 (2021), 1–25.
  50. Travel time estimation of a path using sparse trajectories. In ACM SIGKDD. 25–34.
  51. Learning to estimate the travel time. In ACM SIGKDD. 858–866.
  52. Package pick-up route prediction via modeling couriers’ spatial-temporal behaviors. In IEEE ICDE. 2141–2146.
  53. Fan Wu and Lixia Wu. 2019. DeepETA: a spatial-temporal sequential neural network model for estimating time of arrival in package delivery system. In AAAI, Vol. 33. 774–781.
  54. Probabilistic robust route recovery with spatio-temporal dynamics. In SIGKDD. 1915–1924.
  55. TAML: A Traffic-aware Multi-task Learning Model for Estimating Travel Time. ACM Trans. on Intelli. Sys. and Tech. 12, 6 (2021), 1–14.
  56. Tadnm: A transportation-mode aware deep neural model for travel time estimation. In DASFAA. 468–484.
  57. Multitask Learning with Graph Neural Network for Travel Time Estimation. Computational Intelligence and Neuroscience 2022 (2022).
  58. Effective travel time estimation: When historical trajectories over road networks matter. In SIGMOD. 2135–2149.
  59. Flow prediction in spatio-temporal networks based on multitask deep learning. IEEE Trans. on Know. and Data Eng. 32, 3 (2019), 468–478.
  60. Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI, Vol. 35. 11106–11115.
  61. 3d shape generation and completion through point-voxel diffusion. In IEEE ICCV. 5826–5835.
Citations (14)
View on Semantic Scholar

Summary

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

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

Whiteboard

Paper to Video (Beta)

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up