The Effects of Selected Object Features on a Pick-and-Place Task: a Human Multimodal Dataset
The dataset was jointly created by the University of Genoa and the Italian Institute of Technology, focusing on the influence of object‑specific characteristics on human grasping and placing actions. It contains 1,200 pick‑and‑place actions performed by 15 participants, captured with a multimodal setup (multiple cameras, motion‑capture system, and wrist‑mounted inertial measurement units). The dataset aims to investigate intent recognition and motion generation for object interaction in robotics by analyzing human kinematics.
Dataset description and usage context
Dataset Overview
Dataset Name
Effects of Object Characteristics on Manipulations
Description
The dataset investigates how specific object attributes affect human grasping and placing motions while allowing comparison of kinematics captured by different sensor modalities. It supports broader learning challenges in hand‑object interaction, including intent recognition and motion generation, with direct relevance to robotics. Data were collected from 15 participants performing 80 pick‑and‑place tasks under various experimental conditions, totaling 1,200 instances. The multimodal setup includes multiple cameras, a motion‑capture system, and wrist‑worn inertial measurement units. Objects shared shape, size, and appearance, but differed in weight and liquid fill, requiring varying levels of handling delicacy.
Detailed Description
For full details, see the dataset paper: Lastrico L, Belcamino V, Carfì A, et al. The effects of selected object features on a pick‑and‑place task: A human multimodal dataset. International Journal of Robotics Research. 2024;43(1):98‑109. doi:10.1177/02783649231210965
Software Helper Functions
Helper functions are available on GitHub.
Version
2
Keywords
- Topic: Science & Technology, Computer Science, Artificial Intelligence
- Technology: Neural Networks, LSTM
- Task: Multi‑label Classification
- Data Type: Multimodal Data
- Task: Pose Detection
License
Attribution‑NonCommercial 4.0 International (CC BY‑NC 4.0)
Identifier
2319925
Included in Data Catalogs
Kaggle
Creators
Alessandro Carfì
Distribution
- Format: zip
- Size: 77,427,764,879 bytes
- Download link: Download
Interaction Statistics
- Comments: 0
- Downloads: 9
- Views: 134
- Likes: 0
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.