JEPA4R:具身 JEPA 世界模型以 4D 點雲進行規劃
JEPA4R: Embodied JEPA World Models with 4D Point Planning
論文提出 JEPA4R,一種以單部深度相機取得的點雲為觀測、在潛在空間預測及規劃,並透過凍結潛在表示上的策略頭執行動作的 JEPA 世界模型。解碼器生成的 4D 點雲在 200 步內平均點誤差維持在 1.1 cm 以內;在 MetaWorld 和 Adroit Relocate 分別取得 98.4% 和 88.0%,高於排名第二的 R3M 的 96.0% 和 65.3%。
Published on Nov 15
Authors:
,
,
,
,
Abstract
Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels and plan in latent space. Two challenges remain: 2D images leave the metric geometry that manipulation acts on implicit and entangled with appearance, and what these models imagine stays hidden, as they are mostly judged in simulation by short-horizon latent planning. We present JEPA4R, a JEPA world model that observes single-depth-camera point clouds, predicts and plans in their latent space, and acts through a policy head on its frozen latents; we call this 4D point planning. A decoder on the frozen world model shows what it imagines as 4D point clouds, with a mean point error within 1.1 cm over 200 steps. Under the policy-learning protocols of OGBench and CortexBench, JEPA4R leads pixel JEPA models on OGBench Cube-Single, Cube-Double, Cube-Triple and Scene, and ranks first on MetaWorld and Adroit Relocate with 98.4% and 88.0%, above the runner-up, R3M, at 96.0% and 65.3%. Trained only in a digital twin, JEPA4R and its policy heads run zero-shot on the real arm with both a gripper and a dexterous hand.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2611.19771
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.19771 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.19771 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.19771 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co