There is a newer version of the record available.

Published May 19, 2023 | Version v1
Dataset Open

EEG and EMG dataset for the detection of errors introduced by an active orthosis device

  • 1. DFKI-RIC
  • 2. SMT-University of Duisburg-Essen
  • 3. DFKI-RIC, Robotics Lab-University of Bremen
  • 4. DFKI-RIC, SMT-University of Duisburg-Essen


This dataset is a part of the training data for the IJCAI 2023 competition : CC6: IntEr-HRI: Intrinsic Error Evaluation during Human-Robot Interaction (IJCAI'23 Official Website). This dataset repository is divided into 2 versions:

  • Version 1: Training data + Metadata
  • Version 2: Test data 


After conducting a small survey to determine the willingness of the participating teams to travel to Macao, it became evident that a significant number of them preferred not to travel. With this in mind, we have decided to modify the initial plan for the online stage of the competition wherein the participating teams can participate from anywhere on Earth. Hope that this motivates more teams to participate. For more detailed information, please visit our competition webpage.

Although the registration for the offline stage is officially closed, if you still wish to participate, please reach out to us via the contact form available on our webpage.

This dataset contains recordings of the electroencephalogram (EEG) data from eight subjects who were assisted in moving their right arm by an active orthosis. This is only a part of the complete dataset which also contains electromyogram (EMG) data and the complete dataset will be made public after the end of the competition.

The orthosis-supported movements were elbow joint movements, i.e., flexion and extension of the right arm. While the orthosis was actively moving the subject's arm, some errors were deliberately introduced for a short duration of time. During this time, the orthosis moved in the opposite direction. The errors are very simple and easy to detect. EEG and EMG data are provided. The recorded EEG data follows the BrainVision Core Data Format 1.0, consisting of a binary data file (.eeg), a header file (.vhdr), and a marker file (.vmrk) ( For ease of use, the data can be exported into the widely adopted BIDS format. Furthermore, for data analysis, processing, and classification, two popular options are available - MNE (Python) and EEGLAB (MATLAB). 

If you use our dataset, cite our paper.

arXiv-issued DOI:

BibTeX citation:

      title={EEG and EMG dataset for the detection of errors introduced by an active orthosis device}, 
      author={Niklas Kueper and Kartik Chari and Judith Bütefür and Julia Habenicht and Su Kyoung Kim and Tobias Rossol and Marc Tabie and Frank Kirchner and Elsa Andrea Kirchner},


Files (1.8 GB)

Name Size Download all
1.8 GB Preview Download
8.2 kB Preview Download