mlsanityData to 14 Oct 2026

TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios

arXiv 2210.06609 ↗First posted 12 Oct 2022cs.ROcited by 106

Not on the map. Why?

Cited by 31 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the fragmented human driving data collected in the real world and then can generate realistic traffic scenarios. TrafficGen is an autoregressive generative model with an encoder-decoder architecture. In each autoregressive iteration, it first encodes the current traffic context with the attention mechanism and then decodes a vehicle's initial state followed by generating its long trajectory. We evaluate the trained model in terms of vehicle placement and trajectories and show substantial improvements over baselines. TrafficGen can be also used to augment existing traffic scenarios, by adding new vehicles and extending the fragmented trajectories. We further demonstrate that importing the generated scenarios into a simulator as interactive training environments improves the performance and the safety of driving policy learned from reinforcement learning. More project resource is available at https://metadriverse.github.io/trafficgen

Key facts. Cited by 106 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Oct 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 19; 2024: 35; 2025: 31; 2026: 21.

106 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  2. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 305
  3. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 242
  4. 2024DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generationcited by 191
  5. 2023Street-View Image Generation from a Bird's-Eye View Layoutcited by 102
  6. 2024OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Drivingcited by 93
  7. 2023Language Conditioned Traffic Generationcited by 87
  8. 2023The Waymo Open Sim Agents Challengecited by 86
  9. 2025A Survey of World Models for Autonomous Drivingcited by 60
  10. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 54
  11. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusioncited by 47
  12. 2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
38 more
  1. 2024Solving Motion Planning Tasks with a Scalable Generative Modelcited by 40
  2. 2024Generative Artificial Intelligence: A Systematic Review and Applicationscited by 37
  3. 2024SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Predictioncited by 34
  4. 2024DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulationcited by 34
  5. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 32
  6. 2023Data-driven Traffic Simulation: A Comprehensive Reviewcited by 29
  7. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environmentscited by 28
  8. 2023DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratchcited by 27
  9. 2024Improving Agent Behaviors with RL Fine-tuning for Autonomous Drivingcited by 27
  10. 2023Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023cited by 25
  11. 2023Learning Realistic Traffic Agents in Closed-loopcited by 24
  12. 2023SceneDM: Scene-level Multi-agent Trajectory Generation with Consistent Diffusion Modelscited by 24
  13. 2025Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistencycited by 22
  14. 2023Reinforcement Learning with Human Feedback for Realistic Traffic Simulationcited by 21
  15. 2024Promptable Closed-loop Traffic Simulationcited by 20
  16. 2024AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusioncited by 20
  17. 2025SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Modelcited by 20
  18. 2024Language-Driven Interactive Traffic Trajectory Generationcited by 19
  19. 2025Compositional Generative Model of Unbounded 4D Citiescited by 17
  20. 2023Generating Driving Scenes with Diffusioncited by 16
  21. 2023Safety-Critical Scenario Generation Via Reinforcement Learning Based Editingcited by 16
  22. 2025Generative Models in Decision Making: A Surveycited by 15
  23. 2024Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Modelcited by 14
  24. 2024Extrapolated Urban View Synthesis Benchmarkcited by 13
  25. 2025CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Modelscited by 12
  26. 2025Generating Multimodal Driving Scenes via Next-Scene Predictioncited by 12
  27. 2025Decoupled Diffusion Sparks Adaptive Scene Generationcited by 12
  28. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectoriescited by 11
  29. 2024UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarioscited by 10
  30. 2024World Models: The Safety Perspectivecited by 9
  31. 2025Enhancing Autonomous Driving Safety with Collision Scenario Integrationcited by 9
  32. 2024Text-to-Drive: Diverse Driving Behavior Synthesis via Large Language Modelscited by 8
  33. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  34. 2024Leveraging Generative AI for Urban Digital Twins: A Scoping Review on the Autonomous Generation of Urban Data, Scenarios, Designs, and 3D City Models for Smart City Advancementcited by 7
  35. 2025DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Modelscited by 7
  36. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  37. 2025Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Modelscited by 7
  38. 2024Reviving Life on the Edge: Joint Score-Based Graph Generation of Rich Edge Attributescited by 6

50 most cited of 106 All 106 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior
  2. 2024Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic Simulations
  3. 2025Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge
  4. 2025Generative AI for Autonomous Driving: A Review
  5. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors
  6. 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
  7. 2025Generative Modeling for Adversarial Lane-Change Scenarios ↗
  8. 2022TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving