OASIS is a framework that leverages 3D generative asset reconstruction and simulation-based teleoperation to train high-performance, zero-shot visuomotor policies for humanoid loco-manipulation tasks.</p>\n","updatedAt":"2026-06-09T03:42:29.529Z","author":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","fullname":"taesiri","name":"taesiri","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":312,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8019284009933472},"editors":["taesiri"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.08548","authors":[{"_id":"6a278b3e6dde1c5ef75bcfcb","name":"Zehao Yu","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfcc","name":"Jiakun Zheng","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfcd","name":"Weiji Xie","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfce","name":"Jiyuan Shi","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfcf","name":"Chenyun Zhang","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfd0","name":"Chenjia Bai","hidden":false},{"_id":"6a278b3e6dde1c5ef75bcfd1","name":"Xuelong Li","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/6039478ab3ecf716b1a5fd4d/uuJ2H9wTQZe0i1a7lEeOw.mp4"],"publishedAt":"2026-06-07T00:00:00.000Z","submittedOnDailyAt":"2026-06-09T00:00:00.000Z","title":"OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user","name":"taesiri"},"summary":"Recent progress in robot manipulation has been largely driven by learning from large-scale demonstrations. For humanoid robot loco-manipulation tasks, however, existing data sources force an unsatisfying tradeoff between trajectory quality and scalability. Real-world teleoperation provides the highest-quality trajectories but requires dedicated physical space and time-consuming scene resets. Simulation offers an alternative way out of this dilemma: it can produce clean, embodiment-aligned data at scale without any physical hardware. In this paper, we propose OASIS, a simulation-data-driven framework for humanoid loco-manipulation. OASIS automatically reconstructs realistic object assets from real-world images using a 3D generative model. Based on these assets, trajectories are first collected through teleoperation in simulation, and then augmented under diverse domain randomizations in a post-processing stage. With the resulting simulation data, we further design a hierarchical visuomotor policy for humanoid loco-manipulation. Extensive experiments on the real humanoid robot show that, under zero-shot deployment, the policy trained on our simulation data achieves higher success rates on most tasks than that trained on real-robot teleoperation data, owing largely to the broad lighting and environmental variations covered by our simulation rendering, which real-robot data fails to capture. The project page is available at https://oasis-humanoid.github.io/.","upvotes":1,"discussionId":"6a278b3f6dde1c5ef75bcfd2","projectPage":"https://oasis-humanoid.github.io/","ai_summary":"A simulation-data-driven framework for humanoid loco-manipulation that uses 3D generative models to create realistic assets and hierarchical visuomotor policies trained on simulated data achieves better zero-shot performance than real-robot training.","ai_keywords":["3D generative model","simulation-data-driven framework","humanoid loco-manipulation","hierarchical visuomotor policy","domain randomization","teleoperation","trajectory collection","visual servoing"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.08548.md"}">
OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation
Abstract
A simulation-data-driven framework for humanoid loco-manipulation that uses 3D generative models to create realistic assets and hierarchical visuomotor policies trained on simulated data achieves better zero-shot performance than real-robot training.
Recent progress in robot manipulation has been largely driven by learning from large-scale demonstrations. For humanoid robot loco-manipulation tasks, however, existing data sources force an unsatisfying tradeoff between trajectory quality and scalability. Real-world teleoperation provides the highest-quality trajectories but requires dedicated physical space and time-consuming scene resets. Simulation offers an alternative way out of this dilemma: it can produce clean, embodiment-aligned data at scale without any physical hardware. In this paper, we propose OASIS, a simulation-data-driven framework for humanoid loco-manipulation. OASIS automatically reconstructs realistic object assets from real-world images using a 3D generative model. Based on these assets, trajectories are first collected through teleoperation in simulation, and then augmented under diverse domain randomizations in a post-processing stage. With the resulting simulation data, we further design a hierarchical visuomotor policy for humanoid loco-manipulation. Extensive experiments on the real humanoid robot show that, under zero-shot deployment, the policy trained on our simulation data achieves higher success rates on most tasks than that trained on real-robot teleoperation data, owing largely to the broad lighting and environmental variations covered by our simulation rendering, which real-robot data fails to capture. The project page is available at https://oasis-humanoid.github.io/.
Community
OASIS is a framework that leverages 3D generative asset reconstruction and simulation-based teleoperation to train high-performance, zero-shot visuomotor policies for humanoid loco-manipulation tasks.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.08548 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.08548 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.08548 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.