Organization and Understanding of a Tactile Information Dataset TacAct During Physical Human-Robot Interactions
This dataset addresses the need for tactile intelligence in service robots to enhance safety and interaction, though it is incremental as it builds on existing data collection efforts.
The authors introduced the TacAct dataset, containing 24,000 touch actions from 50 subjects to capture real-time pressure distribution during human-robot interactions, and validated it using a LeNet-5 CNN for classifying touch types.
Advanced service robots require superior tactile intelligence to guarantee human-contact safety and to provide essential supplements to visual and auditory information for human-robot interaction, especially when a robot is in physical contact with a human. Tactile intelligence is an essential capability of perception and recognition from tactile information, based on the learning from a large amount of tactile data and the understanding of the physical meaning behind the data. This report introduces a recently collected and organized dataset "TacAct" that encloses real-time pressure distribution when a human subject touches the arms of a nursing-care robot. The dataset consists of information from 50 subjects who performed a total of 24,000 touch actions. Furthermore, the details of the dataset are described, the data are preliminarily analyzed, and the validity of the collected information is tested through a convolutional neural network LeNet-5 classifying different types of touch actions. We believe that the TacAct dataset would be more than beneficial for the community of human interactive robots to understand the tactile profile under various circumstances.