|
7 | 7 | [](https://pytorchkorea.github.io/Awesome-Physical-AI) |
8 | 8 | [](https://pytorchkorea.github.io/Awesome-Physical-AI) |
9 | 9 | [](https://pytorchkorea.github.io/Awesome-Physical-AI) |
10 | | -[](https://github.com/PyTorchKorea/Awesome-Physical-AI) |
| 10 | +[](https://github.com/PyTorchKorea/Awesome-Physical-AI) |
11 | 11 | [](https://pytorchkorea.github.io/Awesome-Physical-AI) |
12 | 12 |
|
13 | 13 | > **[👉 인터랙티브 대시보드에서 필터링 및 시각화 보기 | View Interactive Dashboard](https://pytorchkorea.github.io/Awesome-Physical-AI)** |
|
30 | 30 |
|
31 | 31 | | Name | Organization | Year | Category | Hardware | Learning | ⭐ Stars | Links | |
32 | 32 | |------|-------------|------|----------|----------|----------|---------|-------| |
33 | | -| [LeRobot](https://github.com/huggingface/lerobot) | Hugging Face | 2024 | manipulation | manipulator | IL, diffusion, VLA | 23,337 | [📄](https://arxiv.org/abs/2408.01730) [🤗](https://huggingface.co/lerobot) | |
34 | | -| [π0 (pi-zero)](https://github.com/Physical-Intelligence/openpi) | Physical Intelligence | 2024 | manipulation, whole-body | manipulator, humanoid | VLA, diffusion | 11,365 | [📄](https://arxiv.org/abs/2410.24164) [🤗](https://huggingface.co/physical-intelligence/pi0) | |
35 | | -| [GR00T N1](https://github.com/NVIDIA/Isaac-GR00T) | NVIDIA | 2025 | manipulation, whole-body | humanoid | VLA, IL | 6,729 | [📄](https://arxiv.org/abs/2503.14734) [🤗](https://huggingface.co/nvidia/GR00T-N1-2B) | |
36 | | -| [OpenVLA](https://github.com/openvla/openvla) | Stanford / UC Berkeley | 2024 | manipulation | manipulator | VLA | 5,936 | [📄](https://arxiv.org/abs/2406.09246) [🤗](https://huggingface.co/openvla/openvla-7b) | |
37 | | -| [Mobile ALOHA](https://github.com/MarkFzp/mobile-aloha) | Stanford | 2024 | manipulation, navigation, whole-body | mobile, manipulator | IL | 4,407 | [📄](https://arxiv.org/abs/2401.02117) | |
38 | | -| [Diffusion Policy](https://github.com/real-stanford/diffusion_policy) | Columbia University | 2023 | manipulation | manipulator | IL, diffusion | 4,026 | [📄](https://arxiv.org/abs/2303.04137) | |
39 | | -| [ACT (Action Chunking with Transformers)](https://github.com/tonyzhaozh/act) | Stanford | 2023 | manipulation, dexterous | manipulator | IL | 1,879 | [📄](https://arxiv.org/abs/2304.13705) | |
40 | | -| [Octo](https://github.com/octo-models/octo) | UC Berkeley / Stanford / CMU / others | 2023 | manipulation | manipulator, mobile | IL, VLA | 1,623 | [📄](https://arxiv.org/abs/2405.12213) [🤗](https://huggingface.co/rail-berkeley/octo-base) | |
41 | | -| [HumanPlus](https://github.com/MarkFzp/humanplus) | Stanford | 2024 | manipulation, whole-body | humanoid | IL | 837 | [📄](https://arxiv.org/abs/2406.10454) | |
| 33 | +| [LeRobot](https://github.com/huggingface/lerobot) | Hugging Face | 2024 | manipulation | manipulator | IL, diffusion, VLA | 23,709 | [📄](https://arxiv.org/abs/2408.01730) [🤗](https://huggingface.co/lerobot) | |
| 34 | +| [π0 (pi-zero)](https://github.com/Physical-Intelligence/openpi) | Physical Intelligence | 2024 | manipulation, whole-body | manipulator, humanoid | VLA, diffusion | 11,638 | [📄](https://arxiv.org/abs/2410.24164) [🤗](https://huggingface.co/physical-intelligence/pi0) | |
| 35 | +| [GR00T N1](https://github.com/NVIDIA/Isaac-GR00T) | NVIDIA | 2025 | manipulation, whole-body | humanoid | VLA, IL | 6,912 | [📄](https://arxiv.org/abs/2503.14734) [🤗](https://huggingface.co/nvidia/GR00T-N1-2B) | |
| 36 | +| [OpenVLA](https://github.com/openvla/openvla) | Stanford / UC Berkeley | 2024 | manipulation | manipulator | VLA | 6,051 | [📄](https://arxiv.org/abs/2406.09246) [🤗](https://huggingface.co/openvla/openvla-7b) | |
| 37 | +| [Mobile ALOHA](https://github.com/MarkFzp/mobile-aloha) | Stanford | 2024 | manipulation, navigation, whole-body | mobile, manipulator | IL | 4,414 | [📄](https://arxiv.org/abs/2401.02117) | |
| 38 | +| [Diffusion Policy](https://github.com/real-stanford/diffusion_policy) | Columbia University | 2023 | manipulation | manipulator | IL, diffusion | 4,091 | [📄](https://arxiv.org/abs/2303.04137) | |
| 39 | +| [ACT (Action Chunking with Transformers)](https://github.com/tonyzhaozh/act) | Stanford | 2023 | manipulation, dexterous | manipulator | IL | 1,917 | [📄](https://arxiv.org/abs/2304.13705) | |
| 40 | +| [Octo](https://github.com/octo-models/octo) | UC Berkeley / Stanford / CMU / others | 2023 | manipulation | manipulator, mobile | IL, VLA | 1,642 | [📄](https://arxiv.org/abs/2405.12213) [🤗](https://huggingface.co/rail-berkeley/octo-base) | |
| 41 | +| [HumanPlus](https://github.com/MarkFzp/humanplus) | Stanford | 2024 | manipulation, whole-body | humanoid | IL | 840 | [📄](https://arxiv.org/abs/2406.10454) | |
42 | 42 | | [RoboFlamingo](https://github.com/RoboFlamingo/RoboFlamingo) | ByteDance | 2023 | manipulation | manipulator | VLA | 429 | [📄](https://arxiv.org/abs/2311.01378) | |
43 | | -| [GR-1](https://github.com/bytedance/GR-1) | BAAI / Beijing Academy of AI | 2024 | manipulation | manipulator | VLA, IL | 309 | [📄](https://arxiv.org/abs/2312.13139) | |
44 | | -| [CrossFormer](https://github.com/rail-berkeley/crossformer) | UC Berkeley / others | 2024 | manipulation | manipulator, mobile | IL, VLA | 282 | [📄](https://arxiv.org/abs/2408.11812) [🤗](https://huggingface.co/rail-berkeley/crossformer) | |
| 43 | +| [GR-1](https://github.com/bytedance/GR-1) | BAAI / Beijing Academy of AI | 2024 | manipulation | manipulator | VLA, IL | 310 | [📄](https://arxiv.org/abs/2312.13139) | |
| 44 | +| [CrossFormer](https://github.com/rail-berkeley/crossformer) | UC Berkeley / others | 2024 | manipulation | manipulator, mobile | IL, VLA | 281 | [📄](https://arxiv.org/abs/2408.11812) [🤗](https://huggingface.co/rail-berkeley/crossformer) | |
45 | 45 |
|
46 | 46 | --- |
47 | 47 |
|
|
51 | 51 |
|
52 | 52 | | Name | Organization | Year | Category | Source | Modality | Trajectories | ⭐ Stars | Links | |
53 | 53 | |------|-------------|------|----------|--------|----------|-------------|---------|-------| |
54 | | -| [ManiSkill2](https://github.com/haosulab/ManiSkill) | UC San Diego / Shanghai AI Lab | 2023 | manipulation, dexterous | simulation | rgb, rgbd, proprioception | 36,000 | 2,797 | [📄](https://arxiv.org/abs/2302.04659) [🤗](https://huggingface.co/datasets/haosulab/ManiSkill) | |
55 | | -| [Meta-World](https://github.com/Farama-Foundation/Metaworld) | Stanford / Berkeley | 2019 | manipulation | simulation | proprioception | — | 1,793 | [📄](https://arxiv.org/abs/1910.10897) | |
56 | | -| [Open X-Embodiment (OXE)](https://github.com/google-deepmind/open_x_embodiment) | Google DeepMind / RT-X Team | 2023 | manipulation | real, teleoperation | rgb, rgbd, proprioception | 1,000,000 | 1,782 | [📄](https://arxiv.org/abs/2310.08864) [🤗](https://huggingface.co/datasets/jxu124/OpenX-Embodiment) | |
57 | | -| [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO) | UMass Amherst / Bosch | 2023 | manipulation | simulation | rgb, proprioception | 130,000 | 1,742 | [📄](https://arxiv.org/abs/2306.03310) [🤗](https://huggingface.co/datasets/openvla/modified_libero_spatial) | |
58 | | -| [HumanoidBench](https://github.com/carlosferrazza/humanoid-bench) | CMU / UC San Diego / MIT | 2024 | locomotion, manipulation, whole-body | simulation | rgb, proprioception | — | 748 | [📄](https://arxiv.org/abs/2403.10506) | |
59 | | -| [RoboAgent Dataset](https://github.com/rail-berkeley/roboagent) | CMU | 2023 | manipulation | real, teleoperation | rgb, proprioception | 7,500 | 390 | [📄](https://arxiv.org/abs/2309.01918) | |
| 54 | +| [ManiSkill2](https://github.com/haosulab/ManiSkill) | UC San Diego / Shanghai AI Lab | 2023 | manipulation, dexterous | simulation | rgb, rgbd, proprioception | 36,000 | 2,848 | [📄](https://arxiv.org/abs/2302.04659) [🤗](https://huggingface.co/datasets/haosulab/ManiSkill) | |
| 55 | +| [Open X-Embodiment (OXE)](https://github.com/google-deepmind/open_x_embodiment) | Google DeepMind / RT-X Team | 2023 | manipulation | real, teleoperation | rgb, rgbd, proprioception | 1,000,000 | 1,818 | [📄](https://arxiv.org/abs/2310.08864) [🤗](https://huggingface.co/datasets/jxu124/OpenX-Embodiment) | |
| 56 | +| [Meta-World](https://github.com/Farama-Foundation/Metaworld) | Stanford / Berkeley | 2019 | manipulation | simulation | proprioception | — | 1,807 | [📄](https://arxiv.org/abs/1910.10897) | |
| 57 | +| [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO) | UMass Amherst / Bosch | 2023 | manipulation | simulation | rgb, proprioception | 130,000 | 1,797 | [📄](https://arxiv.org/abs/2306.03310) [🤗](https://huggingface.co/datasets/openvla/modified_libero_spatial) | |
| 58 | +| [HumanoidBench](https://github.com/carlosferrazza/humanoid-bench) | CMU / UC San Diego / MIT | 2024 | locomotion, manipulation, whole-body | simulation | rgb, proprioception | — | 753 | [📄](https://arxiv.org/abs/2403.10506) | |
| 59 | +| [RoboAgent Dataset](https://github.com/robopen/roboagent) | CMU | 2023 | manipulation | real, teleoperation | rgb, proprioception | 7,500 | 364 | [📄](https://arxiv.org/abs/2309.01918) | |
| 60 | +| [DROID](https://github.com/droid-dataset/droid) | UC Berkeley / Stanford / others | 2024 | manipulation | real, teleoperation | rgb, rgbd, proprioception | 76,000 | 356 | [📄](https://arxiv.org/abs/2403.12945) [🤗](https://huggingface.co/datasets/droid-dataset/droid) | |
60 | 61 | | [Language-Table](https://github.com/google-research/language-table) | Google | 2023 | manipulation | real, simulation, teleoperation | rgb, proprioception | 600,000 | 356 | [📄](https://arxiv.org/abs/2210.01911) [🤗](https://huggingface.co/datasets/google/language_table) | |
61 | | -| [DROID](https://github.com/droid-dataset/droid) | UC Berkeley / Stanford / others | 2024 | manipulation | real, teleoperation | rgb, rgbd, proprioception | 76,000 | 345 | [📄](https://arxiv.org/abs/2403.12945) [🤗](https://huggingface.co/datasets/droid-dataset/droid) | |
62 | 62 | | [BridgeData V2](https://github.com/rail-berkeley/bridge_data_v2) | UC Berkeley | 2023 | manipulation | real, teleoperation | rgb, proprioception | 60,096 | 279 | [📄](https://arxiv.org/abs/2308.12952) [🤗](https://huggingface.co/datasets/rail-berkeley/bridge_orig) | |
63 | | -| [RH20T](https://github.com/rh20t/rh20t_api) | Shanghai AI Lab | 2023 | manipulation, dexterous | real, teleoperation | rgb, rgbd, tactile, proprioception, audio | 110,000 | 105 | [📄](https://arxiv.org/abs/2307.00595) | |
| 63 | +| [RH20T](https://github.com/rh20t/rh20t_api) | Shanghai AI Lab | 2023 | manipulation, dexterous | real, teleoperation | rgb, rgbd, tactile, proprioception, audio | 110,000 | 108 | [📄](https://arxiv.org/abs/2307.00595) | |
64 | 64 |
|
65 | 65 | --- |
66 | 66 |
|
|
70 | 70 |
|
71 | 71 | | Name | Organization | Year | Type | GPU | ROS2 | Language | ⭐ Stars | Paper | |
72 | 72 | |------|-------------|------|------|-----|------|----------|---------|-------| |
73 | | -| [Genesis](https://github.com/Genesis-Embodied-AI/Genesis) | Genesis Authors (MIT/CMU/Stanford) | 2024 | physics_engine | ✅ | — | python | 28,523 | [📄](https://arxiv.org/abs/2501.00599) | |
74 | | -| [MuJoCo](https://github.com/google-deepmind/mujoco) | DeepMind / Google | 2022 | physics_engine | — | — | c, python, c++ | 8,700 | [📄](https://arxiv.org/abs/2103.09615) | |
75 | | -| [Isaac Lab](https://github.com/isaac-sim/IsaacLab) | NVIDIA | 2023 | rl_framework | ✅ | ✅ | python | 6,962 | [📄](https://arxiv.org/abs/2301.04195) | |
76 | | -| [dm_control](https://github.com/google-deepmind/dm_control) | DeepMind | 2018 | benchmark | — | — | python | 3,800 | [📄](https://arxiv.org/abs/2006.12983) | |
77 | | -| [Brax](https://github.com/google/brax) | Google | 2021 | physics_engine | ✅ | — | python | 2,400 | [📄](https://arxiv.org/abs/2106.13281) | |
78 | | -| [Robosuite](https://github.com/ARISE-Initiative/robosuite) | Stanford / UT Austin | 2020 | benchmark | — | — | python | 1,700 | [📄](https://arxiv.org/abs/2009.12293) | |
79 | | -| [RoboCasa](https://github.com/robocasa/robocasa) | UT Austin | 2024 | full_stack | — | — | python | 1,400 | [📄](https://arxiv.org/abs/2406.02523) | |
80 | | -| [SimplerEnv](https://github.com/simpler-env/SimplerEnv) | UC Berkeley / Google | 2024 | benchmark | — | — | python | 950 | [📄](https://arxiv.org/abs/2405.05941) | |
81 | | -| [SAPIEN](https://github.com/haosulab/SAPIEN) | UC San Diego / others | 2020 | physics_engine | ✅ | — | python, c++ | 900 | [📄](https://arxiv.org/abs/2003.08515) | |
| 73 | +| [Genesis](https://github.com/Genesis-Embodied-AI/Genesis) | Genesis Authors (MIT/CMU/Stanford) | 2024 | physics_engine | ✅ | — | python | 28,605 | [📄](https://arxiv.org/abs/2501.00599) | |
| 74 | +| [MuJoCo](https://github.com/google-deepmind/mujoco) | DeepMind / Google | 2022 | physics_engine | — | — | c, python, c++ | 13,327 | [📄](https://arxiv.org/abs/2103.09615) | |
| 75 | +| [Isaac Lab](https://github.com/isaac-sim/IsaacLab) | NVIDIA | 2023 | rl_framework | ✅ | ✅ | python | 7,080 | [📄](https://arxiv.org/abs/2301.04195) | |
| 76 | +| [dm_control](https://github.com/google-deepmind/dm_control) | DeepMind | 2018 | benchmark | — | — | python | 4,564 | [📄](https://arxiv.org/abs/2006.12983) | |
| 77 | +| [Brax](https://github.com/google/brax) | Google | 2021 | physics_engine | ✅ | — | python | 3,145 | [📄](https://arxiv.org/abs/2106.13281) | |
| 78 | +| [Robosuite](https://github.com/ARISE-Initiative/robosuite) | Stanford / UT Austin | 2020 | benchmark | — | — | python | 2,392 | [📄](https://arxiv.org/abs/2009.12293) | |
| 79 | +| [RoboCasa](https://github.com/robocasa/robocasa) | UT Austin | 2024 | full_stack | — | — | python | 1,369 | [📄](https://arxiv.org/abs/2406.02523) | |
| 80 | +| [SimplerEnv](https://github.com/simpler-env/SimplerEnv) | UC Berkeley / Google | 2024 | benchmark | — | — | python | 1,053 | [📄](https://arxiv.org/abs/2405.05941) | |
| 81 | +| [SAPIEN](https://github.com/haosulab/SAPIEN) | UC San Diego / others | 2020 | physics_engine | ✅ | — | python, c++ | 761 | [📄](https://arxiv.org/abs/2003.08515) | |
82 | 82 |
|
83 | 83 | --- |
84 | 84 |
|
|
0 commit comments