LabDex: A Hierarchical Benchmark for Dexterous Manipulation in Laboratories

📅 2026-08-19
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
为解决实验室中灵巧操作的系统训练和评估问题,提出LabDex基准,通过分层任务分类法整合现实与模拟平台,支持多级实验操作。
📝 Abstract
Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instruments and execute long-horizon, state-dependent experimental procedures. Yet existing benchmarks do not jointly capture dexterous hand use, real-world laboratory interactions, and multi-stage experimental procedures, limiting systematic training and evaluation. To bridge this gap, we introduce LabDex, a large-scale real-world dataset and benchmark for dexterous manipulation in chemistry laboratories, organized around a hierarchical task taxonomy spanning atomic skills, compositional tasks, and long-horizon experiments. First, LabDex is cross-platform and, for the first time, unifies real-world and simulation platforms under a common framework, providing standardized task definitions, demonstrations, and evaluation protocols. Second, LabDex is large-scale and systematically organizes chemistry laboratory operations into three interconnected levels: Atomic Skills, which characterize fundamental dexterous manipulation capabilities; Compositional Skills; and Long-Horizon Laboratory Workflows. This hierarchical design not only supports the evaluation of end-task performance, but also enables the analysis of how fundamental dexterous skills compose and influence more complex laboratory operations. We conduct cross-level evaluations of representative robot learning methods in both real-world and simulation environments. The experimental results validate the effectiveness of the LabDex task design and demonstration data, and show that the benchmark supports the training and systematic evaluation of existing robotic policies across laboratory dexterous manipulation tasks at different levels, providing a foundation for further research and development of autonomous laboratory robots.
Problem

Research questions and friction points this paper is trying to address.

dexterous manipulation
laboratory interactions
multi-stage experimental procedures
Innovation

Methods, ideas, or system contributions that make the work stand out.

dexterous manipulation
hierarchical task taxonomy
cross-platform
standardized evaluation
autonomous laboratories
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Zhipeng Tang
Zhipeng Tang
UMass Amherst
S
Sihang Chen
University of Science and Technology of China
Sha Zhang
Sha Zhang
The Chinese University of Hong Kong
Scene UnderstandingEmbodied AI
P
Peihao Yang
University of Science and Technology of China
Y
Yan Liu
University of Science and Technology of China
W
Wentao Zhao
University of Science and Technology of China
X
Xinrui Liu
University of Science and Technology of China
R
Rui Huang
University of Science and Technology of China
W
Wensheng Du
University of Science and Technology of China
Y
Yuting Huang
University of Science and Technology of China
Jiajun Deng
Jiajun Deng
The Chinese University of Hong Kong
Speech Signal ProcessingSpeech Laguage Modeling
L
Lidian Wang
University of Science and Technology of China
Y
Yuan Zhang
iFLYTEK
Yanyong Zhang
Yanyong Zhang
University of Science and Technology of China ; Rutgers University (Adjunct Visiting Professor)
SensingCyber-Physical SystemsMulti-Modal PerceptionEfficient AI Systems