TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

• URL: http://arxiv.org/abs/2605.22355v1
• Date: Thu, 21 May 2026 11:42:33 GMT
• Title: TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
• Abstract summary: We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines.<n>Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations.
• Score: 18.721623620233107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.

Related papers

• 123D: Unifying Multi-Modal Autonomous Driving Data at Scale [58.4010470217018]
  We present 123D, an open-source framework that unifies such multi-modal driving data through a single API.<n>We consolidate eight real-world driving datasets spanning 3,300 hours and 90,000 kilometers, together with a synthetic dataset with collection scripts, and provide tools for data analysis and visualization.
  arXiv  Detail & Related papers  (2026-05-08T17:59:53Z)
• Fusing Cellular Network Data and Tollbooth Counts for Urban Traffic Flow Estimation [0.0]
  Traffic simulations, essential for planning urban transit infrastructure interventions, require origin-destination (OD) data.<n>Existing data sources are imperfect: sparse tollbooth sensors provide accurate vehicle counts by category, while extensive mobility data from cellular network activity captures aggregated crowd movement.<n>This study develops a machine learning framework to correct and disaggregate cellular network data using sparse tollbooth counts as ground truth.
  arXiv  Detail & Related papers  (2026-04-17T07:40:10Z)
• OpenNavMap: Structure-Free Topometric Mapping via Large-Scale Collaborative Localization [12.686154192361913]
  OpenNavMap is a lightweight, structure-free topometric system leveraging 3D geometric foundation models for on-demand reconstruction.<n>Our method unifies dynamic programming-based sequence matching, geometric verification, and confidence-calibrated optimization to robust, coarse-to-fine submap alignment.<n> Evaluations on the Map-Free benchmark demonstrate superior accuracy over structure-from-motion and regression baselines, achieving an average translation error of 0.62m.
  arXiv  Detail & Related papers  (2026-01-18T07:24:46Z)
• TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route [45.16008377814563]
  We create a large-scale evaluation dataset comprised of 36000 routes from 12 metropolises worldwide.<n>We introduce PathBuilder, a novel tool for converting natural language instructions into navigation routes.<n>We rigorously assess 11 state-of-the-art (SOTA) LLMs on the task of route reversal.
  arXiv  Detail & Related papers  (2025-09-17T15:00:03Z)
• TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models [2.3951780950929678]
  TransitGPT works by guiding LLMs to generate Python code that extracts and manipulates GTFS data relevant to a query.<n>It can accomplish a wide range of tasks, including data retrieval, calculations, and interactive visualizations, without requiring users to have extensive knowledge of GTFS or programming.
  arXiv  Detail & Related papers  (2024-12-07T00:35:41Z)
• Neural Semantic Map-Learning for Autonomous Vehicles [85.8425492858912]
  We present a mapping system that fuses local submaps gathered from a fleet of vehicles at a central instance to produce a coherent map of the road environment. Our method jointly aligns and merges the noisy and incomplete local submaps using a scene-specific Neural Signed Distance Field. We leverage memory-efficient sparse feature-grids to scale to large areas and introduce a confidence score to model uncertainty in scene reconstruction.
  arXiv  Detail & Related papers  (2024-10-10T10:10:03Z)
• NLP-enabled Trajectory Map-matching in Urban Road Networks using a Transformer-based Encoder-decoder [1.3812010983144802]
  This study introduces a data-driven, deep learning-based map-matching framework, formulating the task as machine translation, inspired by NLP.<n>A transformer-based encoder-decoder model learns contextual representations of noisy GPS points to infer trajectory behavior and road structures in an end-to-end manner.<n>Experiments on synthetic trajectories show that this approach outperforms conventional methods by integrating contextual awareness.
  arXiv  Detail & Related papers  (2024-04-18T18:39:23Z)
• Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehicles [63.20765930558542]
  3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization. We propose a new dataset, Navya 3D (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain. It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds.
  arXiv  Detail & Related papers  (2023-02-16T13:41:19Z)
• PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map [58.53373202647576]
  We propose PreTraM, a self-supervised pre-training scheme for trajectory forecasting. It consists of two parts: 1) Trajectory-Map Contrastive Learning, where we project trajectories and maps to a shared embedding space with cross-modal contrastive learning, and 2) Map Contrastive Learning, where we enhance map representation with contrastive learning on large quantities of HD-maps. On top of popular baselines such as AgentFormer and Trajectron++, PreTraM boosts their performance by 5.5% and 6.9% relatively in FDE-10 on the challenging nuScenes dataset.
  arXiv  Detail & Related papers  (2022-04-21T23:01:21Z)
• Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications [53.553924052102126]
  We present a complete pipeline for 3D semantic mapping solely based on a stereo camera system. The pipeline comprises a direct visual odometry front-end as well as a back-end for global temporal integration. We propose a simple but effective voting scheme which improves the quality and consistency of the 3D point labels.
  arXiv  Detail & Related papers  (2022-03-02T13:18:38Z)
• Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans [103.92680099373567]
  This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world. Changing the sampling parameters allows one to "steer" the generated datasets to emphasize specific information. Common architectures trained on a generated starter dataset reached state-of-the-art performance on multiple common vision tasks and benchmarks.
  arXiv  Detail & Related papers  (2021-10-11T04:21:46Z)
• Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars [39.94419250485135]
  Pit30M is a new image and LiDAR dataset with over 30 million frames, which is 10 to 100 times larger than those used in previous work. Pit30M is captured under diverse conditions (i.e., season, weather, time of the day, traffic), and provides accurate localization ground truth. We benchmark multiple existing methods for image and LiDAR retrieval and, in the process, introduce a simple, yet effective convolutional network-based LiDAR retrieval method.
  arXiv  Detail & Related papers  (2020-12-23T01:24:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.