The DREAM Dataset: Behavioural data from robot enhanced therapies for children with autism spectrum disorder

This dataset comprise behavioural data recorded from 61 children diagnosed with Autism Spectrum Disorders (ASD). The data was collected during a large-scale evaluation of Robot Enhanced Therapy (RET). The dataset covers over 3000 therapy sessions and more than 300 hours of therapy. Half of the children interacted with the social robot NAO supervised by a therapist. The other half, constituting a control group, interacted directly with a therapist. Both groups followed the Applied Behavior Analysis (ABA) protocol. Each session was recorded with three RGB cameras and two RGBD (Kinect) cameras, providing detailed information of children's behaviour during therapy. This public release of the dataset noes not include video recordings or other personal information. Instead, it comprises body motion, head position and orientation, and eye gaze variables, all specified as 3D data in a joint frame of reference. In addition, metadata including participant age, gender, and autism diagnosis (ADOS) variables are included. All data in this dataset is stored in JavaScript Object Notation (JSON) and can be downloaded here as DREAMdataset.zip. A much smaller archive comprising example data recorded from a single session is provided in DREAMdata-example.zip. The JSON format is specified in detail by the JSON Schema (dream.1.1.json) provided with this dataset. JSON data can be read using standard libraries in most programming languages. Basic instructions on how to load and plot the data using Python and Jupyter are available in DREAMdata-documentation.zip attached with this dataset. Please refer to https://github.com/dream2020/dataOpens in a new tab for more details. The DREAM Dataset can be visualized using the DREAM Data Visualizer, an open source software available at https://github.com/dream2020/DREAM-data-visualizerOpens in a new tab. The DREAM RET System that was used for collecting this dataset is available at https://github.com/dream2020/DREAMOpens in a new tab.