mlsanityData to 14 Oct 2026

A Differentiable Physics Engine for Deep Learning in Robotics

arXiv 1611.01652 ↗First posted 5 Nov 2016cs.NE cs.AI cs.ROcited by 108

Not on the map. Why?

Abstract (arXiv)

An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose the implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 26; 2022: 23; 2023: 13; 2024: 19; 2025: 11; 2026: 15.

108 papers.

Sort:

By area:

  1. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  2. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  3. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 104
  4. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 103
  5. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  6. 2021Gradients are Not All You Needcited by 86
  7. 2022A Survey on Model-based Reinforcement Learningcited by 66
  8. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 65
  9. 2021Robot Learning from Randomized Simulations: A Reviewcited by 63
  10. 2021DiffPD: Differentiable Projective Dynamicscited by 62
  11. 2023Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamicscited by 57
  12. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
38 more
  1. 2021An End-to-End Differentiable Framework for Contact-Aware Robot Designcited by 54
  2. 2021Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contactcited by 52
  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. 2021Efficient Differentiable Simulation of Articulated Bodiescited by 39
  6. 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
  7. 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 34
  8. 2022Learning differentiable solvers for systems with hard constraintscited by 34
  9. 2022RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimationcited by 29
  10. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  11. 2020Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learningcited by 27
  12. 2021Learning neural network potentials from experimental data via Differentiable Trajectory Reweightingcited by 26
  13. 2022Rethinking Optimization with Differentiable Simulation from a Global Perspectivecited by 23
  14. 2022Training Efficient Controllers via Analytic Policy Gradientcited by 22
  15. 2021Combining Physics and Deep Learning to learn Continuous-Time Dynamics Modelscited by 20
  16. 2024Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulationcited by 20
  17. 2025Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomycited by 20
  18. 2023DiffMimic: Efficient Motion Mimicking with Differentiable Physicscited by 19
  19. 2021SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learningcited by 16
  20. 2022Contact Points Discovery for Soft-Body Manipulations with Differentiable Physicscited by 14
  21. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 14
  22. 2025UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulationcited by 12
  23. 2021NURBS-Diff: A Differentiable Programming Module for NURBScited by 11
  24. 2021Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarkingcited by 10
  25. 2024ElastoGen: 4D Generative Elastodynamicscited by 10
  26. 2021Differentiable Implicit Soft-Body Physicscited by 9
  27. 2021DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolationcited by 9
  28. 2022Fine-grained differentiable physics: a yarn-level model for fabricscited by 9
  29. 2022Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulationcited by 9
  30. 2021Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimizationcited by 8
  31. 2023Differentiable Simulations for Enhanced Sampling of Rare Eventscited by 8
  32. 2023DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulationcited by 8
  33. 2023Gradient Informed Proximal Policy Optimizationcited by 8
  34. 2022Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?cited by 7
  35. 2023Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contactcited by 7
  36. 2023Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithmscited by 7
  37. 2023Differentiable Visual Computing for Inverse Problems and Machine Learningcited by 7
  38. 2022SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Criticscited by 6

50 most cited of 108 All 108 (JSON)