Awesome Isaac Sim (Updating!)

📝 Introduction

This is a list some related resources of NVIDIA Isaac Sim, which is inspired by awesome-isaac-gym. The development progress is: Isaac Gym-->Isaac Sim-->Orbit-->Isaac Lab, where the latter two are built based on Isaac Sim. Notably, due to its lightweight nature and adequate performance, currently Isaac Gym remains more widely used in the RL field. However, the number of researchers using Isaac Sim is also rapidly increasing. If this project is helpful for your research, please give me a star and fork, thanks! If your work on Isaac Sim is accepted to top conferences or transactions, welcome to propose a issue or pull a request to remind me of updating your work!

Contribute to this list

We encourage you to add your IsaacSim-related work to this list! You can

Submit a Pull Request to contribute new algorithms, configuration files, or improvements via Github Pull Request to post your paper and code.

🔥 Papers

[CVPR2024] BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation [website] [paper] [code]
[Arxiv2024] LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control [website] [paper] [code]
[ICRA2024] ORBIT-Surgical: An Open-Simulation Framework for Learning Surgical Augmented Dexterity [website] [paper] [code]
[Arxiv2024] InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction [paper] [code]
[Arxiv2024] M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes [website] [paper]
[Arxiv2024] GRUtopia: Dream General Robots in a City at Scale [website] [paper] [code]
[Arxiv2024] MultiGripperGrasp: A Dataset for Robotic Grasping from Parallel Jaw Grippers to Dexterous Hands [website] [paper] [code]
[Arxiv2023] Less Is More: Robust Robot Learning via Partially Observable Multi-Agent Reinforcement Learning [paper] [code]
[ICCV2023] ARNOLD: A benchmark for language-grounded task learning with continuous states in realistic 3D scenes [website] [paper] [code]
[RAL2023] Orbit: A unified simulation framework for interactive robot learning environments [website] [paper][code]
[CORL2023] Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation [website] [paper][code]
[Arxiv2023] RANS: Highly-Parallelised Simulator for Reinforcement Learning based Autonomous Navigating Spacecrafts [paper][code]