Top-down Traffic Scenario Generation via Joint Initial-Goal Diffusion and Trajectory Infilling

• URL: http://arxiv.org/abs/2608.11407v1
• Date: Tue, 11 Aug 2026 20:13:51 GMT
• Title: Top-down Traffic Scenario Generation via Joint Initial-Goal Diffusion and Trajectory Infilling
• Abstract summary: Existing traffic simulators require agents' initial states to generate trajectories.<n>We propose TrafficDiffuser, which generates high-level traffic scenarios, defined by initial and goal state pairs.<n>We demonstrate how the generated high-level traffic scenarios can be used, including constraining based on different trajectory modes.
• Score: 3.2061579211871387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust traffic simulators are crucial for developing and testing autonomous vehicles to reduce the costly, labor-intensive real-world data collection process and the need for physical presence on the road. However, existing simulators require agents' initial states to generate trajectories, which limits scalability and diversity due to restrictions on the given initial states. While data-driven agent initialization has been widely studied, the generated initial states are not interpretable in terms of why the agents are initialized at those specific locations. Given known initial states, trajectory generation is also a challenging problem, as the model must learn the variability of the destination and how agents should reach it over time. In this paper, we propose TrafficDiffuser, a top-down traffic scenario generation framework that generates high-level traffic scenarios, defined by initial and goal state pairs, by jointly modeling them. The high-level scenario generation makes initial states better interpretable and reduces trajectory generation into as simple as an infilling problem. We demonstrate how the generated high-level traffic scenarios can be used, including constraining based on different trajectory modes and integrating them with existing trajectory generation models. We conduct extensive experiments on the Argoverse 2 motion prediction dataset to evaluate how well the generated outputs capture real-world distributions. In addition to generating goal states, TrafficDiffuser outperforms the next-best approach for agent initialization, reducing speed distribution distance by 55.3% and the off-road rate by 2.8%.

Related papers

• Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling [54.94692733670454]
  Future trajectories of neighboring traffic agents have a significant influence on the path planning and decision-making of autonomous vehicles.<n>We propose a lightweight yet highly accurate streaming-based trajectory forecasting approach.<n>Our approach significantly reduces inference latency, making it well-suited for real-world deployment.
  arXiv  Detail & Related papers  (2026-03-02T13:44:23Z)
• InfGen: Scenario Generation as Next Token Group Prediction [49.54222089551598]
  InfGen is a scenario generation framework that outputs agent states and trajectories in an autoregressive manner.<n>Experiments demonstrate that InfGen produces realistic, diverse, and adaptive traffic behaviors.
  arXiv  Detail & Related papers  (2025-06-29T16:18:32Z)
• A Pretrained Probabilistic Transformer for City-Scale Traffic Volume Prediction [8.384075654211685]
  City-scale traffic volume prediction plays a pivotal role in intelligent transportation systems.<n>Current models are typically trained in a city-specific manner, which hinders their generalizability.<n>We introduce TrafficPPT, a Pretrained Probabilistic Transformer designed to model traffic volume as a distributional aggregation of trajectories.
  arXiv  Detail & Related papers  (2025-06-03T09:07:29Z)
• Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments [39.649242431308544]
  We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning.<n>It generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours.<n>Case study shows that Scenario Dreamer achieves superior generation quality with around 2x fewer parameters, 6x lower generation, and 10x training hours compared to the strongest baseline.
  arXiv  Detail & Related papers  (2025-03-28T15:03:41Z)
• Unifying Lane-Level Traffic Prediction from a Graph Structural Perspective: Benchmark and Baseline [21.37853568400125]
  We present the first systematic classification framework for lane-level traffic prediction, offering a structured taxonomy and analysis of existing methods.<n>We construct three representative datasets from two real-world road networks, covering both regular and irregular lane configurations.<n>This unified framework enables consistent evaluation across datasets and modeling paradigms.
  arXiv  Detail & Related papers  (2024-03-22T04:21:40Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• A Diffusion-Model of Joint Interactive Navigation [14.689298253430568]
  We present DJINN - a diffusion based method of generating traffic scenarios. Our approach jointly diffuses the trajectories of all agents, conditioned on a flexible set of state observations from the past, present, or future. We show how DJINN flexibly enables direct test-time sampling from a variety of valuable conditional distributions.
  arXiv  Detail & Related papers  (2023-09-21T22:10:20Z)
• Pre-training on Synthetic Driving Data for Trajectory Prediction [61.520225216107306]
  We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. We adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. We conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies.
  arXiv  Detail & Related papers  (2023-09-18T19:49:22Z)
• Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction [52.0977259978343]
  This paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD) The state vectors keep historical transaction information and are continuously updated according to the most recently happened transactions. Experiments are conducted on two real-world datasets from Beijing Subway and New York Taxi, and the results demonstrate the superiority of our model against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-30T03:37:50Z)
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
  We propose advances that address two key challenges in future trajectory prediction. multimodality in both training data and predictions and constant time inference regardless of number of agents.
  arXiv  Detail & Related papers  (2020-07-26T08:17:10Z)

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.