mlsanityData to 7 Oct 2026

Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models

arXiv 2502.10012 ↗First posted 14 Feb 2025cs.AI cs.ROcited by 1

On the map: World models → World models for autonomous driving

Abstract (arXiv)

Differentiable simulators represent an environment's dynamics as a differentiable function. Within robotics and autonomous driving, this property is used in Analytic Policy Gradients (APG), which relies on backpropagating through the dynamics to train accurate policies for diverse tasks. Here we show that differentiable simulation also has an important role in world modeling, where it can impart predictive, prescriptive, and counterfactual capabilities to an agent. Specifically, we design three novel task setups in which the differentiable dynamics are combined within an end-to-end computation graph not with a policy, but a state predictor. This allows us to learn relative odometry, optimal planners, and optimal inverse states. We collectively call these predictors Analytic World Models (AWMs) and demonstrate how differentiable simulation enables their efficient, end-to-end learning. In autonomous driving scenarios, they have broad applicability and can augment an agent's decision-making beyond reactive control.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in World models for autonomous driving, one of 11 directions in World models. Builds on 33 of its 42 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

33 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research12 Oct
  2. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networks12 Jul
  3. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning26 Sep
  4. 2017CARLA: An Open Urban Driving Simulator10 Nov

Other references · 29

  1. 2018World Modelscited by 1,444
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  4. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  5. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  6. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  7. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  8. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  9. 2020Learning to Control PDEs with Differentiable Physicscited by 131
  10. 2016A Differentiable Physics Engine for Deep Learning in Roboticscited by 107
  11. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  12. 2023The Waymo Open Sim Agents Challengecited by 86
17 more
  1. 2021DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cuttingcited by 62
  2. 2022Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real worldcited by 56
  3. 2021An End-to-End Differentiable Framework for Contact-Aware Robot Designcited by 53
  4. 2024BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Predictioncited by 49
  5. 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
  6. 2020Model-based Reinforcement Learning: A Surveycited by 39
  7. 2018VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Controlcited by 34
  8. 2020Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learningcited by 27
  9. 2022InterSim: Interactive Traffic Simulation via Explicit Relation Modelingcited by 27
  10. 2017Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Carscited by 26
  11. 2023Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023cited by 25
  12. 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
  13. 2024Learning Quadruped Locomotion Using Differentiable Simulationcited by 22
  14. 2022Training Efficient Controllers via Analytic Policy Gradientcited by 16
  15. 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulationcited by 14
  16. 2024TrafficBots V1.5: Traffic Simulation via Conditional VAEs and Transformers with Relative Pose Encodingcited by 13
  17. 2024TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characterscited by 6

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Autonomous Vehicle Path Planning by Searching With Differentiable Simulationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Autonomous Vehicle Controllers From End-to-End Differentiable Simulation
  2. 2025Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving
  3. 2026Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving
  4. 2021Learning to drive from a world on rails
  5. 2025A Survey of World Models for Autonomous Driving
  6. 2024Integrating Decision-Making Into Differentiable Optimization Guided Learning for End-to-End Planning of Autonomous Vehicles
  7. 2026Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges
  8. 2024Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies