pHRI-BTN-TACT: Button Dataset from Intrinsic Robot Tactile Sensing

The pHRI-BTN-TACT dataset provides time-series data captured from an uninstrumented, 3D-printed touchpad interface mounted on the end-effector of a collaborative robot featuring nine virtual buttons. This dataset facilitates research in intuitive robot control, physical human-robot collaboration, tactile sensing, and machine learning for touch recognition. It contains data collected using the intrinsic tactile sensing capabilities of a KUKA LBR iiwa 7 R800 robot, leveraging its joint torque sensors to interpret touch events on the touchpad. The dataset is presented in two versions:

• pHRI-BTN-TACT_SingleUser: this dataset includes 2700 time series, with 300 samples corresponding to each of the nine virtual buttons on the touchpad. All data was recorded from a single user interacting with the robot.
• pHRI-BTN-TACT_MultipleUsers: this dataset also contains 2700 time series (300 per button), but the data was collected from six different users (2 female, 4 male; 5 right-handed, 1 left-handed). This version allows for the analysis of inter-user variability in touch patterns.

Data format:

Both datasets are provided as a single .mat file. Each .mat file contains a 2700x2 cell array.

• Column 1: time-series data for each touch event. Each time series is represented as a 100x5 cell array. This represents the 100 temporal samples, each containing different information described below.
• Column 2: string label indicating the virtual button pressed (b1, b2, b3, b4, b5, b6, b7, b8, b9). 

The time series data is not ordered by button label and has been randomized for each dataset. Each time series represents approximately 3 seconds of data and is composed of 100 samples containing the following 5 cells:

• (1x7 cell) Robot joint torques (Nm).
• (1x7 cell) Robot joint positions (rad).
• (1x3 cell) Cartesian position of the end-effector (mm).
• (1x3 cell) Forces at the end-effector (N).
• (1x3 cell) Moments at the end-effector (Nm).    

Hardware:

• Collaborative robot: KUKA LBR iiwa 7 R800.
• Touchpad: 3D printed, uninstrumented.