/Awesome-Differentiable-Simulation-Robotics

A comprehensive list of papers related to Physics-based and Learning-based Differentiable Simulation for Robotics, including papers, codes, and related websites

Awesome-Differentiable-Simulation-Robotics Awesome

This repo contains a curative list of Physics-based and Learning-based Differentiable Simulation papers relating to Robotics/Graphics domain, inspired by awesome-implicit-nerf-robotics

Please feel free to send me pull requests or email to add papers!

If you find this repository useful, please consider citing and STARing this list. Feel free to share this list with others!

Overview

Articulated Body Simulation

  • End-to-end differentiable physics for learning and control, Neurips, 2018. [Paper]
  • A differentiable physics engine for deep learning in robotics, Front. Neurorobot, 2019. [Paper]
  • Efficient Differentiable Simulation of Articulated Bodies, ICML, 2021. [Paper]
  • Nimble: Fast and feature-complete differentiable physics for articulated rigid bodies with contact, RSS, 2021. [Paper]
  • Dojo: A Differentiable Simulator for Robotics, CoRL, 2022. [Paper]
  • Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation, [code]

Cloth Simulation

  • Differentiable Cloth Simulation for Inverse Problems, Neurips, 2019. [Paper]
  • DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact, SIGGGRAPH, 2022. [Paper]

Soft Body Simulation

  • ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics, ICRA, 2019. [Paper]
  • Differentiable Simulation of Soft Multi-body Systems, Neurips, 2021. [Paper]
  • DiffPD: Differentiable projective dynamics, TOG, 2021. [Paper]

Rigid Body and Cloth/Deformable Coupling

  • Scalable Differentiable Physics for Learning and Control, ICML, 2020. [Paper]
  • ADD: Analytically differentiable dynamics for multi-body systems with frictional contact, TOG, 2020. [Paper]

Learning for Simulation

  • Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids, ICLR, 2019. [Paper]
  • Learning to simulate complex physics with graph networks, ICML, 2020. [Paper]
  • Differentiable Physics Simulation of Dynamics-Augmented Neural Objects, arXiv, 2022. [Paper]
  • Learning Multi-Object Dynamics with Compositional Neural Radiance Fields, CoRL, 2022. [Paper]

Survey

  • Differentiable Physics Simulation, ICLR Workshop, 2020. [Paper]
  • Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control, ICML Workshop, 2022. [Paper]

Citation

If you find this repository useful, please consider citing this list:

@misc{zhao2023differentiablesimulationresources,
    title = {Awesome Differentiable Simulation - A curated list of resources on Physics-based and Learning-based Differentiable Simulation relating to robotics and graphics},
    author = {Siheng Zhao},
    journal = {GitHub repository},
    url = {https://github.com/Hilbert-Johnson/Awesome-Differentiable-Simulation-Robotics},
    year = {2023},
}