{"success":true,"data":{"author":"Ropedia","bucketAccessType":"public","bucketName":"ropedia-ai/Xp-Teleop","bucketPrefix":"","category":"Robotics","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:10.855Z","description":"Xp-Teleop is the long-horizon humanoid loco-manipulation benchmark introduced with Ropedia W0 (arXiv:2610.26855). It records a Unitree G1 humanoid with Inspire FTP hands from a head-mounted RGB camera and cuts each teleoperated episode into individual actions. The card reports 27 episodes, 543 action segments and 96,064 frames at 30 fps and 1280x720. Each segment folder under takes/ holds clean RGB video (H.264 MP4), the same video with skeleton overlays, original frame timestamps (CSV), per-frame arrays (frames.npz), robot body masks (PNG in a zip), head IMU at about 1.6 kHz (CSV), Inspire tactile readings with 1,062 taxels per hand (JSONL) and the action caption (JSON). meta/ holds the schema (info.json), takes, segments, tasks and per-episode camera calibration as JSONL. Measured 2026-11-14 at about 7.9 GB. Read with numpy, pandas and PyAV or OpenCV. Useful for humanoid world models, action segmentation, video-language grounding and tactile-aware manipulation. Licensed under CC BY 4.0; cite the Ropedia W0 paper.","displayTitle":"Xp-Teleop: Long-Horizon Humanoid Loco-Manipulation Benchmark (Unitree G1)","id":"54199c96-3a68-5094-9df7-6bcfe8b478bc","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/ropedia-ai/Xp-Teleop","objectCountEstimate":4354,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2610.26855","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"ropedia-ai/Xp-Teleop\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"ropedia-ai/Xp-Teleop\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=ropedia-ai, license:cc-by-4.0, size_categories:n<1K, downloads=715"],"format":"mixed","generatedAt":"2026-11-14T14:15:14.894Z","layout":{"example":"meta/calibration.jsonl","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"{\"take_id\": \"bean_from_fridge_to_board\", \"source_take\": \"take_20260829_172227\", \"K\": [[653.6617885183305, 0.0, 640.0], [0.0, 653.6617885183305, 360.0], [0.0, 0.0, 1.0]], \"T_torso_cam\": [[0.015511818021212199, -0.8906005755828038, 0.4545217247538953, 0.1265131692792025], [-0.9990948466593537, -0.031813123794392356, -0.028238493818995465, -0.039601636857828484], [0.03960897474562518, -0.4536722825190245, -0.8902879248836182, 0.49117218179914035], [0.0, 0.0, 0.0, 1.0]], \"image_size\": [1280, 720], \"urdf\": \"g1_2","encoding":"utf8","key":"meta/calibration.jsonl","truncatedAt":512}],"sampleObjects":["meta/calibration.jsonl","meta/info.json","meta/raw_video_segments.jsonl","meta/raw_video_sources.jsonl","meta/segments.jsonl"],"sidecars":[{"bytes":"Attribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other rights holders may use to share\noriginal works of authorship and other material subject to copyright\nand certain other rights specified in the public license below. The\nfollowing considerations are for informational purposes only, are not\nexhaustive, and do not form part of our licenses.\n\n     Considerations for licensors: Our public licenses are\n     intended for use by those authorized to give the public\n     permission to use material in ways otherwise restricted by\n     copyright and certain other rights. Our licenses are\n     irrevocable. Licensors should read and understand the terms\n     and conditions of the license they choose before applying it.\n     Licensors should also secure all rights necessary before\n     applying our licenses so that the public can reuse the\n     material as expected. Licensors should clearly mark any\n     material not subject to the license. This includes other CC-\n     licensed material, or material used under an exception or\n     limitation to copyright. More considerations for licensors:\n    wiki.creativecommons.org/Considerations_for_licensors\n\n     Considerations for the public: By using one of our public\n     licenses, a licensor grants the public permission to use the\n     licensed material under specified terms and conditions. If\n     the licensor's permission is not necessary for any reason--for\n     example, because of any applicable exception or limitation to\n     copyright--then that use is not regulated by the license. Our\n     licenses grant only permissions under copyright and certain\n     other rights that a licensor has authority to grant. Use of\n     the licensed material may still be restricted for other\n     reasons, including because others have copyright or other\n     rights in the material. A licensor may make special requests,\n     such as asking that all changes be marked or described.\n     Although not required by our licenses, you are encouraged to\n     respect those requests where reasonable. More considerations\n     for the public:\n    wiki.creativecommons.org/Considerations_for_licensees\n\n=======================================================================\n\nCreative Commons Attribution 4.0 International Public License\n\nBy exercising the Licensed Rights (defined below), You accept and agree\nto be bound by the terms and conditions of this Creative Commons\nAttribution 4.0 International Public License (\"Public License\"). To the\nextent this Public License may be interpreted as a contract, You are\ngranted the Licensed Rights in consideration of Your acceptance of\nthese terms and conditions, and the Licensor grants You such rights in\nconsideration of benefits the Licensor receives from making the\nLicensed Material available under these terms and conditions.\n\n\nSection 1 -- Definitions.\n\n  a. Adapted Material means material subject to Copyright and Similar\n     Rights that is derived from or based upon the Licensed Material\n     and in which the Licensed Material is translated, altered,\n     arranged, transformed, or otherwise modified in a manner requiring\n     permission under the Copyright and Similar Rights held by the\n     Licensor. For purposes of this Public License, where the Licensed\n     Material is a musical work, performance, or sound recording,\n ","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":18657,"truncated":true},{"bytes":"---\nlicense: cc-by-4.0\nviewer: false\ntask_categories:\n- robotics\nlanguage:\n- en\nsize_categories:\n- n<1K\ntags:\n- robotics\n- humanoid\n- manipulation\n- keypoints\n---\n\n# Xp-Teleop\n\nLong-horizon humanoid manipulation on a Unitree G1 with Inspire FTP hands, recorded from a\nhead-mounted RGB camera and cut into individual actions.\n\nXp-Teleop is the long-horizon loco-manipulation benchmark introduced in [Ropedia W0](https://ropedia.github.io/ropedia-w0/) ([paper](https://arxiv.org/abs/2610.26855), [code](https://github.com/Ropedia/ropedia-w0)).\n\n27 episodes · 543 action segments · 96,064 frames · 30 fps · 1280×720\n\n## Layout\n\n```\nmeta/\n  info.json            schema for every field\n  takes.jsonl          27 episodes\n  segments.jsonl       543 action segments — the index\n  tasks.jsonl          task list\n  calibration.jsonl    camera intrinsics and extrinsics per episode\ntakes/<take_id>/segments/<segment_id>/\n  video_rgb.mp4        clean RGB, without burned-in annotations\n  video_keypoints.mp4  RGB with skeleton/keypoint overlays\n  frame_timestamps.csv original per-frame timestamps\n  frames.npz           per-frame arrays (see meta/info.json)\n  masks.zip            robot body mask, one PNG per frame\n  imu.csv              head IMU, ~1.6 kHz\n  tactile.jsonl        Inspire tactile, 1062 taxels per hand\n  caption.json         the action annotation\n```\n\n## Load\n\n```python\nimport json, numpy as np\n\nsegments = [json.loads(l) for l in open(\"meta/segments.jsonl\")]\ns = segments[0]\nd = np.load(f\"{s['path']}/frames.npz\", allow_pickle=True)\n\nd[\"uv\"]       # (n, 51, 2) keypoints in pixels\nd[\"xyz_cam\"]  # (n, 51, 3) keypoints in metres, camera frame\nd[\"cam_c2w\"]  # (n, 4, 4)  camera-to-world\nd[\"q\"]        # (n, 35)    joint angles\n```\n\n## Clean RGB video\n\n`video_rgb.mp4` in every segment is encoded directly from the original JPEG frames (1280×720, 30 fps, H.264, CRF 18), without burned-in annotations; frame n corresponds to row n of `frames.npz`. `frame_timestamps.csv` gives the original per-frame timestamps (`frame_idx`, `monotonic_ns`, `device_ts_usec`) in the same order. `video_keypoints.mp4` is the same footage with the robot skeleton rendered on top. The indices `meta/raw_video_segments.jsonl` and `meta/raw_video_sources.jsonl` list the source take and frame range of every segment.\n\n## Notes\n\n- `frame_timestamps.csv` also carries `color_path` / `depth_path`, the relative paths of the original colour JPEG and depth frames in the recording; those raw files are not part of this dataset.\n- In `pour_and_wash_the_plate`, segments `c026`–`c032` have a `video_keypoints.mp4` rendered from an earlier version of the skeleton; `frames.npz` and `video_rgb.mp4` are the reference.\n\n## License\n\n[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).\n\n## Citation\n\n```bibtex\n@article{liu2026ropedia,\n  title={Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience},\n  author={Liu, Tianqi and Zhao, Hanfei and Liang, Qifeng and Pang, Hui En and Xu, Jiarui and Mu, Sayang and Qiu, Penghao and Zhang, YingSheng and Wang, Jun and Cao, Ziang and Sun, Mingze and Cao, Yukang and Hong, Fangzhou and Chen, Zhaoxi and Liu, Ziwei},\n  journal={arXiv preprint arXiv:2610.26855},\n  year={2026}\n}\n```\n","encoding":"utf8","key":"README.md","name":"README.md","size":3248,"truncated":false}],"sourceObjectKey":"meta/calibration.jsonl","starterCell":"from datasets import load_dataset\nds = load_dataset(\"ropedia-ai/Xp-Teleop\")\nprint(ds)","starterSamplePath":"meta/calibration.jsonl","totalObjects":4354},"summary":"Xp-Teleop is the long-horizon humanoid loco-manipulation benchmark introduced with Ropedia W0 (arXiv:2610.26855).","title":"Xp-Teleop: Long-Horizon Humanoid Loco-Manipulation Benchmark (Unitree G1)","updatedAt":"2026-11-14T17:43:56.155Z","visibility":"public","websiteUrl":"https://ropedia.github.io/ropedia-w0/"}}