跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-19AI 評分49

HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation

HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation

AI 導讀

HandsOn 是一個跨機體模擬平台及靈巧操作基準,評估機械臂、靈巧手、物件和組合任務之間的泛化能力。平台支援 5 款機械臂、6 款靈巧手,並提供約 200 個資產、18,000 段人類示範及 66 項經人工驗證的任務;最佳受訓多任務策略在 Core-50 的成功率為 29.1%。

正文

Published on Oct 19

·

Submitted by

罗天蔚

on Oct 20

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

HandsOn is a cross-embodiment simulation benchmark and platform for dexterous manipulation that evaluates generalization across robotic arms, hands, objects, and composed tasks, revealing substantial gaps in current multi-task policies and foundation-model-based control.

General-purpose manipulation requires reliable behavior across embodiments, objects, and task demands. We introduce HandsOn, a composable simulation platform and benchmark for cross-embodiment dexterous manipulation. It supports five robotic arms, six dexterous hands, and approximately 200 rigid, articulated, and deformable assets in randomized scenes. The benchmark pairs 18,000 curated human demonstrations with 66 human-verified tasks: Core-50 supports demonstration-based learning and execution tests, while Transfer-16 evaluates asset and relation transfer, skill composition, and deformable manipulation without target-task training demonstrations. Qualitative real-robot rollouts illustrate sim-to-real transfer. Across diffusion, vision-language-action, world-action, and prompted VLM-based methods, the best trained multi-task policy achieves 29.1% Core-50 success. Without benchmark finetuning, GPT-6 using move_eef for palm-and-finger control achieves 5.2% on Core-50 and 1.9% on Transfer-16 over 660 trials. Trained-policy stage diagnostics expose failures in contact establishment, action coordination, and maintaining achieved goals, with additional sequencing errors in composed tasks. HandsOn provides a shared basis for investigating manipulation generalization and the limits of reliable physical interaction.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.26765

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/2610.26765 in a model README.md to link it from this page.

Datasets citing this paper 1

Cyan666/HandsOn-Datasets

rokae_wuji1 •

Updated about 1 hour ago

•

18k episodes

•

2.8k

•

2

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.26765 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