Monash University

embargo required for identifiable data

Reason: This segment of the dataset contains identifiable recordings of the participants. Thus, researchers who wish to access the FACT-raw dataset should sign the EULA to ensure that the data is used for research purpose only and will not be distributed further.

FACT HRC (FACT-raw): a dataset of Wizard-of-Oz human-robot handovers and collaboration in Functional And Creative Tasks

posted on 2022-12-14, 04:25 authored by Leimin TianLeimin Tian, Kerry He, Shiyu (Eric) Xu, Akansel Cosgun, Dana Kulić

Dataset accompanying our HRI 2023 paper:

Leimin Tian, Kerry He, Shiyu Xu, Akansel Cosgun, and Dana Kulić. 2023. Crafting with a Robot Assistant: Use Social Cues to Inform Adaptive Handovers in Human-Robot Collaboration. In Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction (HRI '23), March 13–16, 2023, Stockholm, Sweden. ACM, New York, NY, USA, 9 pages. (ACM copy, arXiv copy)

This record contains one out of three segments of the FACT dataset, namely FACT-raw:

Identifiable recordings as ROS bags, including all the synchronised raw data from the two camera feeds, the robot's status, the controls of the teleoperation framework, the estimates of facial and upper body keypoints from the RGB-D camera feed, and the emotion estimates from both camera feeds. (Here is an example script if you want to save raw images or other information from the ROS bags to extract your own features instead of using the upper body keypoints and other extracted data in FACT-processed)

Please sign the EULA and send it to for approval if you wish to gain access to FACT-raw. Thank you!

FACT-processed and FACT-support:

Please see 


Interactive learning for robots in human environments

Australian Research Council

Find out more...