GOAG Paradigm: A successful grasp on an object induces dual contact zones on both object and gripper, at the intersection of the two geometries. Our method is built on this key observation: these contact zones are closely the same from either perspective. GOAG capitalizes on this by training exclusively on gripper geometry, allowing it to learn a robust and generalizable grasping strategy without ever being exposed to a grasp database with specific objects geometries.</p>\n","updatedAt":"2026-08-21T13:12:56.306Z","author":{"_id":"6687eb3ec056c55864f09152","avatarUrl":"/avatars/48efa05243507fbd1fe7a2f2139a19eb.svg","fullname":"Julien Mérand","name":"JulienMERAND","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9216815829277039},"editors":["JulienMERAND"],"editorAvatarUrls":["/avatars/48efa05243507fbd1fe7a2f2139a19eb.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.19759","authors":[{"_id":"6a883011404cbc83ad9f08a9","user":{"_id":"6687eb3ec056c55864f09152","avatarUrl":"/avatars/48efa05243507fbd1fe7a2f2139a19eb.svg","isPro":false,"fullname":"Julien Mérand","user":"JulienMERAND","type":"user","name":"JulienMERAND"},"name":"Julien Merand","status":"claimed_verified","statusLastChangedAt":"2026-08-21T12:56:52.336Z","hidden":false},{"_id":"6a883011404cbc83ad9f08aa","name":"Boris Meden","hidden":false},{"_id":"6a883011404cbc83ad9f08ab","name":"Mathieu Grossard","hidden":false},{"_id":"6a883011404cbc83ad9f08ac","name":"Liming Chen","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/6687eb3ec056c55864f09152/h6R01BPoeW1yIjdSQtDvI.png"],"publishedAt":"2026-08-20T00:00:00.000Z","submittedOnDailyAt":"2026-08-21T00:00:00.000Z","title":"GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation","submittedOnDailyBy":{"_id":"6687eb3ec056c55864f09152","avatarUrl":"/avatars/48efa05243507fbd1fe7a2f2139a19eb.svg","isPro":false,"fullname":"Julien Mérand","user":"JulienMERAND","type":"user","name":"JulienMERAND"},"summary":"Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets. We introduce a fundamentally different approach, grounded in the observation that the gripper and the object share identical surface geometry at their mutual contact points. We propose GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation, a novel deep generative model that learns a compact latent representation of a specific gripper's contact surface distribution, enabling the efficient sampling of valid grasp configurations without relying on object-specific training data. We show that by introducing object features only at inference time, our model can effectively retrieve admissible contact areas that are compatible with the gripper's capabilities. We validate our approach through extensive experiments on established grasp protocols in both simulated and real-world scenarios, demonstrating its effectiveness with different grippers from the literature. Our method delivers state-of-the-art results on the objects from the MultiDex dataset, achieving an average success rate of 86.93%. It offers significantly faster processing when generating numerous grasps, while matching the performance of leading approaches specifically trained on this dataset. Unlike these methods, our approach does not rely on object-specific training data, highlighting the advantages of object-agnostic learning. It effectively addresses the generalization challenges faced by traditional data-driven grasp planners. Code and videos are available on our project website https://cea-list.github.io/goagweb/ .","upvotes":1,"discussionId":"6a883011404cbc83ad9f08ad","projectPage":"https://cea-list.github.io/goagweb/","githubRepo":"https://github.com/CEA-LIST/GOAG","githubRepoAddedBy":"user","ai_summary":"GOAG is an object-agnostic deep generative grasp planner that learns a gripper-specific contact surface distribution to sample valid grasps for unseen objects without object-specific training.","ai_keywords":["deep generative model","latent representation","contact surface distribution","object-agnostic grasp planner","dexterous robotic manipulation","inference-time object features","admissible contact areas"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":3},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6687eb3ec056c55864f09152","avatarUrl":"/avatars/48efa05243507fbd1fe7a2f2139a19eb.svg","isPro":false,"fullname":"Julien Mérand","user":"JulienMERAND","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.19759.md","query":{}}">
GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
Abstract
GOAG is an object-agnostic deep generative grasp planner that learns a gripper-specific contact surface distribution to sample valid grasps for unseen objects without object-specific training.
Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets. We introduce a fundamentally different approach, grounded in the observation that the gripper and the object share identical surface geometry at their mutual contact points. We propose GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation, a novel deep generative model that learns a compact latent representation of a specific gripper's contact surface distribution, enabling the efficient sampling of valid grasp configurations without relying on object-specific training data. We show that by introducing object features only at inference time, our model can effectively retrieve admissible contact areas that are compatible with the gripper's capabilities. We validate our approach through extensive experiments on established grasp protocols in both simulated and real-world scenarios, demonstrating its effectiveness with different grippers from the literature. Our method delivers state-of-the-art results on the objects from the MultiDex dataset, achieving an average success rate of 86.93%. It offers significantly faster processing when generating numerous grasps, while matching the performance of leading approaches specifically trained on this dataset. Unlike these methods, our approach does not rely on object-specific training data, highlighting the advantages of object-agnostic learning. It effectively addresses the generalization challenges faced by traditional data-driven grasp planners. Code and videos are available on our project website https://cea-list.github.io/goagweb/ .
Community
GOAG Paradigm: A successful grasp on an object induces dual contact zones on both object and gripper, at the intersection of the two geometries. Our method is built on this key observation: these contact zones are closely the same from either perspective. GOAG capitalizes on this by training exclusively on gripper geometry, allowing it to learn a robust and generalizable grasping strategy without ever being exposed to a grasp database with specific objects geometries.
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/2608.19759 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.19759 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.19759 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.