mlsanityData to 7 Oct 2026

Efficient Differentiable Simulation of Articulated Bodies

arXiv 2109.07719 ↗First posted 16 Sep 2021cs.LG cs.GR cs.ROcited by 38

Not on the map. Why?

Abstract (arXiv)

We present a method for efficient differentiable simulation of articulated bodies. This enables integration of articulated body dynamics into deep learning frameworks, and gradient-based optimization of neural networks that operate on articulated bodies. We derive the gradients of the forward dynamics using spatial algebra and the adjoint method. Our approach is an order of magnitude faster than autodiff tools. By only saving the initial states throughout the simulation process, our method reduces memory requirements by two orders of magnitude. We demonstrate the utility of efficient differentiable dynamics for articulated bodies in a variety of applications. We show that reinforcement learning with articulated systems can be accelerated using gradients provided by our method. In applications to control and inverse problems, gradient-based optimization enabled by our work accelerates convergence by more than an order of magnitude.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 41 of its 77 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

41 of 77 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  6. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  7. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  8. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  9. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  10. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  11. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  12. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
29 more
  1. 2020Lagrangian Neural Networkscited by 388
  2. 2016The CMA Evolution Strategy: A Tutorialcited by 364
  3. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  4. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  5. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  6. 2019Symplectic Recurrent Neural Networkscited by 148
  7. 2020Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Predictioncited by 137
  8. 2020Learning to Control PDEs with Differentiable Physicscited by 131
  9. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
  10. 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
  11. 2016A Differentiable Physics Engine for Deep Learning in Roboticscited by 107
  12. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  13. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 100
  14. 2018ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Roboticscited by 98
  15. 2018Flexible Neural Representation for Physics Predictioncited by 91
  16. 2016Memory-Efficient Backpropagation Through Timecited by 78
  17. 2020NeuralSim: Augmenting Differentiable Simulators with Neural Networkscited by 77
  18. 2020Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEcited by 76
  19. 2020Scalable Differentiable Physics for Learning and Controlcited by 72
  20. 2018Propagation Networks for Model-Based Control Under Partial Observationcited by 64
  21. 2018SPNets: Differentiable Fluid Dynamics for Deep Neural Networkscited by 62
  22. 2020Dynamic Tensor Rematerializationcited by 45
  23. 2019gradSLAM: Automagically differentiable SLAMcited by 27
  24. 2019Interactive Differentiable Simulationcited by 17
  25. 2020ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contactcited by 17
  26. 2020Memory Optimization for Deep Networkscited by 15
  27. 2020Learning to Slide Unknown Objects with Differentiable Physics Simulationscited by 12
  28. 2019JAX, M.D.: A Framework for Differentiable Physicscited by 7
  29. 2020A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Enginescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 8; 2024: 6; 2025: 8; 2026: 3.

38 papers.

Sort:

By area:

  1. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  2. 2023Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamicscited by 56
  3. 2022NeuPhysics: Editable Neural Geometry and Physics from Monocular Videoscited by 50
  4. 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
  5. 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
  6. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 38
  7. 2022RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimationcited by 29
  8. 2022Rethinking Optimization with Differentiable Simulation from a Global Perspectivecited by 21
  9. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 19
  10. 2025Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physicscited by 19
  11. 2024Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulationcited by 14
  12. 2023Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learningcited by 10
26 more
  1. 2024NeuralFluid: Neural Fluidic System Design and Control with Differentiable Simulationcited by 10
  2. 2022Differentiable Hybrid Traffic Simulationcited by 8
  3. 2023Gradient Informed Proximal Policy Optimizationcited by 8
  4. 2023Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contactcited by 7
  5. 2022Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?cited by 6
  6. 2023Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updatescited by 6
  7. 2023Neural Field Dynamics Model for Granular Object Piles Manipulationcited by 6
  8. 2022Learning Object Manipulation Skills from Video via Approximate Differentiable Physicscited by 5
  9. 2023Improving Gradient Computation for Differentiable Physics Simulation with Contactscited by 5
  10. 2022Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulationscited by 4
  11. 2022Traffic-Aware Autonomous Driving with Differentiable Traffic Simulationcited by 4
  12. 2022Differentiable Analog Quantum Computing for Optimization and Controlcited by 4
  13. 2025Accelerating Visual-Policy Learning through Parallel Differentiable Simulationcited by 4
  14. 2024Stabilizing Backpropagation Through Time to Learn Complex Physicscited by 3
  15. 2024Gradient-based Trajectory Optimization with Parallelized Differentiable Traffic Simulationcited by 2
  16. 2025Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisionscited by 2
  17. 2023Diff-Transfer: Model-based Robotic Manipulation Skill Transfer via Differentiable Physics Simulationcited by 1
  18. 2025Accelerated Learning with Linear Temporal Logic using Differentiable Simulationcited by 1
  19. 2025Offline Reinforcement Learning with Penalized Action Noise Injectioncited by 1
  20. 2024Differentiable Quantum Computing for Large-scale Linear Controlcited by 0
  21. 2025An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfercited by 0
  22. 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learningcited by 0
  23. 2025Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contextscited by 0
  24. 2026BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Modelscited by 0
  25. 2026Ostrich: Taking Large Strides Through Stiff Contact in Differentiable Dynamicscited by 0
  26. 2026Accelerating Visual Policy Learning with Sampling-Based Model Predictive Controlcited by 0