TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation

• URL: http://arxiv.org/abs/2606.29097v1
• Date: Sat, 27 Jun 2026 21:48:22 GMT
• Title: TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
• Abstract summary: TrafficAlign is an automated framework that synthesizes traffic scenarios based on real-world driving videos.<n>It reveals up to 10.8% more collisions on average across three autonomous driving models than state-of-the-art methods.<n>Fine-tuning these driving models with TrafficAlign-generated scenarios significantly reduced collision rates by 36.1%.
• Score: 5.181270975161224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research has investigated the use of large language models (LLMs) to generate traffic scenarios for autonomous driving. However, pretrained LLMs often fail to align with real-world traffic distributions. In this work, we present TrafficAlign, an automated framework that synthesizes traffic scenarios based on real-world driving videos, performs data validation, and aligns LLMs with the synthesized scenarios. The evaluation shows that traffic scenarios generated by TrafficAlign are highly effective, revealing up to 10.8% more collisions on average across three autonomous driving models than state-of-the-art methods. Furthermore, fine-tuning these driving models with TrafficAlign-generated scenarios significantly reduced collision rates by 36.1% compared with the original models. A qualitative study using traffic datasets from six geographically diverse regions shows that TrafficAlign-generated scenarios exhibit strong alignment with corresponding traffic distributions in these regions.

Related papers

• OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning [47.85568621735744]
  We introduce OmniTraffic, a controllable pipeline generation and benchmark for traffic reasoning.<n>It is built around 12 real-world intersections and reconstructed by surveillance footage from two countries.<n>It defines a three-level task hierarchy spanning scene perception, multi-view and temporal reasoning, and decision support.
  arXiv  Detail & Related papers  (2026-06-14T11:16:53Z)
• Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization [2.1347076448562867]
  We show that realistic urban traffic simulation can be achieved from minimal real-world observations.<n>This work demonstrates that realistic urban traffic simulation can be achieved from minimal real-world observations.
  arXiv  Detail & Related papers  (2026-06-02T16:04:01Z)
• Multi-modal Traffic Scenario Generation for Autonomous Driving System Testing [10.518062593457351]
  TrafficComposer is a multi-modal traffic scenario construction approach for autonomous driving systems (ADS) testing.<n>It generates the corresponding traffic scenario in a simulator, such as CARLA and LGSVL.<n>On a benchmark of 120 traffic scenarios, TrafficComposer achieves 97.0% accuracy, outperforming the best-performing baseline by 7.3%.
  arXiv  Detail & Related papers  (2025-05-20T20:12:08Z)
• TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation [14.470174593447702]
  Large language models (LLMs) have shown promising performance in various domains.<n>TrafficLLM introduces a dual-stage fine-tuning framework to learn generic traffic representation from raw traffic data.<n>It achieves F1-scores of 0.9875 and 0.9483, with up to 80.12% and 33.92% better performance than existing detection and generation methods.
  arXiv  Detail & Related papers  (2025-04-05T16:18:33Z)
• Calibration of Vehicular Traffic Simulation Models by Local Optimization [43.942239814508106]
  Calibrating simulation models using traffic count data is challenging because of complexity of environment, lack of data, and uncertainties in traffic dynamics.<n>This paper introduces a novel simulation-based traffic calibration technique.<n>We assess the proposed technique on a model of Brussels, Belgium, using data from real traffic monitoring devices.
  arXiv  Detail & Related papers  (2025-02-17T09:17:01Z)
• Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring [6.648291808015463]
  This research leverages the LLaVA visual grounding multimodal large language model (LLM) for traffic monitoring tasks on the real-time Quanser Interactive Lab simulation platform.<n>Cameras placed at multiple urban locations collect real-time images from the simulation, which are fed into the LLaVA model with queries for analysis.<n>The system achieves 84.3% accuracy in recognizing vehicle locations and 76.4% in determining steering direction, outperforming traditional models.
  arXiv  Detail & Related papers  (2025-02-16T23:03:26Z)
• Strada-LLM: Graph LLM for traffic prediction [62.2015839597764]
  A considerable challenge in traffic prediction lies in handling the diverse data distributions caused by vastly different traffic conditions.<n>We propose a graph-aware LLM for traffic prediction that considers proximal traffic information.<n>We adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.
  arXiv  Detail & Related papers  (2024-10-28T09:19:29Z)
• TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction [149.5716746789134]
  We show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving. Experiments on the open motion dataset show TrafficBots can simulate realistic multi-agent behaviors.
  arXiv  Detail & Related papers  (2023-03-07T18:28:41Z)
• Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [59.60483620730437]
  We propose TransFuser, a novel Multi-Modal Fusion Transformer, to integrate image and LiDAR representations using attention. Our approach achieves state-of-the-art driving performance while reducing collisions by 76% compared to geometry-based fusion.
  arXiv  Detail & Related papers  (2021-04-19T11:48:13Z)
• SceneGen: Learning to Generate Realistic Traffic Scenes [92.98412203941912]
  We present SceneGen, a neural autoregressive model of traffic scenes that eschews the need for rules and distributions. We demonstrate SceneGen's ability to faithfully model distributions of real traffic scenes.
  arXiv  Detail & Related papers  (2021-01-16T22:51:43Z)
• Deep traffic light detection by overlaying synthetic context on arbitrary natural images [49.592798832978296]
  We propose a method to generate artificial traffic-related training data for deep traffic light detectors. This data is generated using basic non-realistic computer graphics to blend fake traffic scenes on top of arbitrary image backgrounds. It also tackles the intrinsic data imbalance problem in traffic light datasets, caused mainly by the low amount of samples of the yellow state.
  arXiv  Detail & Related papers  (2020-11-07T19:57:22Z)

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.