mlsanityData to 14 Oct 2026

A Diffusion-Model of Joint Interactive Navigation

arXiv 2309.12508 ↗First posted 21 Sep 2023cs.LG cs.ROcited by 16

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors. The use of prerecorded real-world traffic scenarios in simulation ensures realism but the rarity of safety critical events makes large scale collection of driving scenarios expensive. In this paper, 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. On popular trajectory forecasting datasets, we report state of the art performance on joint trajectory metrics. In addition, we demonstrate how DJINN flexibly enables direct test-time sampling from a variety of valuable conditional distributions including goal-based sampling, behavior-class sampling, and scenario editing.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 49 of its 55 references that are in the map. First posted on arXiv 21 Sep 2023.

Builds on

49 of 55 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion4 Apr
  2. 2022Guided Conditional Diffusion for Controllable Traffic Simulation31 Oct

Other references · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  12. 2022Video Diffusion Modelscited by 2,305
35 more
  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  2. 2023Consistency Modelscited by 1,822
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  4. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  5. 2020On Layer Normalization in the Transformer Architecturecited by 922
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  7. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  8. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  9. 2023Zero-shot Image-to-Image Translationcited by 505
  10. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  11. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  12. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  13. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  14. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
  15. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  16. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  17. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  18. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
  19. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  20. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  21. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  22. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  23. 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
  24. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 193
  25. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 179
  26. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  27. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  28. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  29. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  30. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  31. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  32. 2021Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulationcited by 32
  33. 2021Autonomy 2.0: Why is self-driving always 5 years away?cited by 30
  34. 2020ReCoG: A Deep Learning Framework with Heterogeneous Graph for Interaction-Aware Trajectory Predictioncited by 20
  35. 2021StarNet: Joint Action-Space Prediction with Star Graphs and Implicit Global Frame Self-Attentioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 10; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rolloutcited by 48
  2. 2024Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuningcited by 42
  3. 2024WcDT: World-centric Diffusion Transformer for Traffic Scene Generationcited by 32
  4. 2025SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Modelcited by 20
  5. 2025Constrained Generative Modeling with Manually Bridged Diffusion Modelscited by 8
  6. 2025MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policiescited by 7
  7. 2024A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Researchcited by 4
  8. 2025Safety-Critical Traffic Simulation with Guided Latent Diffusion Modelcited by 4
  9. 2025Control-ITRA: Controlling the Behavior of a Driving Modelcited by 2
  10. 2025Rolling Ahead Diffusion for Traffic Scene Simulationcited by 2
  11. 2025Direct Preference Optimization-Enhanced Multi-Guided Diffusion Model for Traffic Scenario Generationcited by 2
  12. 2025Diffusion-based Planning with Learned Viability Filterscited by 2
4 more
  1. 2025Using Ensemble Diffusion to Estimate Uncertainty for End-to-End Autonomous Drivingcited by 2
  2. 2026Improved Constrained Generation by Bridging Pretrained Generative Modelscited by 2
  3. 2025DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environmentscited by 0
  4. 2026Integration Matters: Rollout-Based Training for Constrained Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-Based Environment-Aware Trajectory Prediction
  2. 2026Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
  3. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
  4. 2024Versatile Behavior Diffusion for Generalized Traffic Agent Simulation
  5. 2025CoPlanner: An Interactive Motion Planner with Contingency-Aware Diffusion for Autonomous Driving
  6. 2024Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecasting
  7. 2025Path Diffuser: Diffusion Model for Data-Driven Traffic Simulator
  8. 2026One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation