Published October 28, 2022
| Version V1.0
Dataset
Open
Simultaneous Action Recognition and Human Whole-Body Motion and Dynamics Prediction from Wearable Sensors
Creators
- 1. Artificial and Mechanical Intelligence, Center for Robotics and Intelligent Systems, Istituto Italiano di Tecnologia (IIT), Genoa, Italy
- 2. Inria, Loria, CNRS, Université de Lorraine, Nancy, France
Description
This dataset contains data accompanying the work:
@INPROCEEDINGS{10000122,
author={Darvish, Kourosh and Ivaldi, Serena and Pucci, Daniele},
booktitle={2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)},
title={Simultaneous Action Recognition and Human Whole-Body Motion and Dynamics Prediction from Wearable Sensors},
year={2022},
volume={},
number={},
pages={488-495},
doi={10.1109/Humanoids53995.2022.10000122}}
The data folder is organized in directories, whose content can be outlined as follows:
- `models`: GMoE and LSTM models: similar to the models used in the paper results section.
- `annotated-data`: containing labeled data formatted column-wise. The first row defines the name of each column. The data are annotated. The data has a similar sampling rate to the `raw-data` folder.
- `raw-data`: containing data formatted column-wise. The first row defines the name of each column. The data is not annotated. The data is re-sampled from Wearables data.
- `wearable-data`: containing [wearables](https://github.com/robotology/wearables) logged data used for the paper analysis; data are collected using XSens suit and iFeel F/T shoes.
A more detailed description of the data and the code associated with this dataset
is available at: https://github.com/ami-iit/paper_darvish_2022_humanoids_action-kindyn-predicition
Files
data.zip
Files
(379.4 MB)
Name | Size | Download all |
---|---|---|
md5:8e952bd35a016b8c6a720e336edcced8
|
379.4 MB | Preview Download |