mlsanityData to 7 Oct 2026

BITS: Bi-level Imitation for Traffic Simulation

arXiv 2208.12403 ↗First posted 26 Aug 2022cs.RO cs.LGcited by 80

Not on the map. Why?

Cited by 25 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Simulation is the key to scaling up validation and verification for robotic systems such as autonomous vehicles. Despite advances in high-fidelity physics and sensor simulation, a critical gap remains in simulating realistic behaviors of road users. This is because, unlike simulating physics and graphics, devising first principle models for human-like behaviors is generally infeasible. In this work, we take a data-driven approach and propose a method that can learn to generate traffic behaviors from real-world driving logs. The method achieves high sample efficiency and behavior diversity by exploiting the bi-level hierarchy of driving behaviors by decoupling the traffic simulation problem into high-level intent inference and low-level driving behavior imitation. The method also incorporates a planning module to obtain stable long-horizon behaviors. We empirically validate our method, named Bi-level Imitation for Traffic Simulation (BITS), with scenarios from two large-scale driving datasets and show that BITS achieves balanced traffic simulation performance in realism, diversity, and long-horizon stability. We also explore ways to evaluate behavior realism and introduce a suite of evaluation metrics for traffic simulation. Finally, as part of our core contributions, we develop and open source a software tool that unifies data formats across different driving datasets and converts scenes from existing datasets into interactive simulation environments. For additional information and videos, see https://sites.google.com/view/nvr-bits2022/home

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 35 of its 65 references that are in the map. First posted on arXiv 26 Aug 2022.

Builds on

35 of 65 references.

References · 35

  1. 2017Mask R-CNNcited by 7,259
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  4. 2021Implicit Behavioral Cloningcited by 442
  5. 2016The Option-Critic Architecturecited by 433
  6. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  7. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  8. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  9. 2019Learning Latent Plans from Playcited by 310
  10. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  11. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 239
  12. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
23 more
  1. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  2. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 192
  3. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  4. 2019Multiple Futures Predictioncited by 178
  5. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  6. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  7. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  8. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  9. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 121
  10. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  11. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrationscited by 114
  12. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  13. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  14. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92
  15. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  16. 2019IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Datacited by 85
  17. 2017Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learningcited by 77
  18. 2021SimNet: Learning Reactive Self-driving Simulations from Real-world Observationscited by 77
  19. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 61
  20. 2022Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulationcited by 61
  21. 2020Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictorscited by 60
  22. 2022MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Drivingcited by 21
  23. 2021Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertaintycited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 21; 2024: 23; 2025: 24; 2026: 9.

80 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  2. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  3. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 189
  4. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 158
  5. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  6. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 137
  7. 2023Language-Guided Traffic Simulation via Scene-Level Diffusioncited by 110
  8. 2023The Waymo Open Sim Agents Challengecited by 86
  9. 2023Language Conditioned Traffic Generationcited by 86
  10. 2025Robust Autonomy Emerges from Self-Playcited by 64
  11. 2024BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Predictioncited by 49
  12. 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rolloutcited by 47
38 more
  1. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusioncited by 46
  2. 2024GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPScited by 43
  3. 2024Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Modelscited by 40
  4. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 37
  5. 2022DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehiclescited by 36
  6. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversariescited by 36
  7. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  8. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  9. 2023Data-driven Traffic Simulation: A Comprehensive Reviewcited by 29
  10. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environmentscited by 27
  11. 2023Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Drivingcited by 26
  12. 2024CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learningcited by 26
  13. 2023Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023cited by 25
  14. 2023trajdata: A Unified Interface to Multiple Human Trajectory Datasetscited by 25
  15. 2023Learning Realistic Traffic Agents in Closed-loopcited by 24
  16. 2024Causal Composition Diffusion Model for Closed-loop Traffic Generationcited by 22
  17. 2023Reinforcement Learning with Human Feedback for Realistic Traffic Simulationcited by 20
  18. 2024Promptable Closed-loop Traffic Simulationcited by 20
  19. 2025Building reliable sim driving agents by scaling self-playcited by 20
  20. 2024Language-Driven Interactive Traffic Trajectory Generationcited by 19
  21. 2024Hybrid-Prediction Integrated Planning for Autonomous Drivingcited by 18
  22. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generationcited by 18
  23. 2024Human-compatible driving partners through data-regularized self-play reinforcement learningcited by 17
  24. 2024Extrapolated Urban View Synthesis Benchmarkcited by 13
  25. 2025UniMM: A Unified Mixture Model Framework for Multi-Agent Simulationcited by 13
  26. 2024Learning to Drive via Asymmetric Self-Playcited by 11
  27. 2025LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulationcited by 11
  28. 2023Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulationcited by 10
  29. 2023Categorical Traffic Transformer: Interpretable and Diverse Behavior Prediction with Tokenized Latentcited by 10
  30. 2024SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generationcited by 10
  31. 2022Receding Horizon Planning with Rule Hierarchies for Autonomous Vehiclescited by 7
  32. 2025DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Modelscited by 7
  33. 2024TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characterscited by 6
  34. 2025DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learningcited by 5
  35. 2023Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-makingcited by 4
  36. 2025RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulationcited by 4
  37. 2023Hierarchical Imitation Learning for Stochastic Environmentscited by 3
  38. 2024Adversarial and Reactive Traffic Entities for Behavior-Realistic Driving Simulation: A Reviewcited by 3

50 most cited of 80 All 80 (JSON)