PiH Dataset for Determining Exception Context in Assembly Operations form Multimodal Data

PiH Dataset used in Simonič, M.; Majcen Hrovat, M.; Džeroski, S.; Ude, A.; Nemec, B. Determining Exception Context in Assembly Operations from Multimodal Data. Sensors 2022, 22, 7962. https://doi.org/10.3390/s22207962

The dataset consists of color images of different outcomes of the PiH task as well as the corresponding Cartesian pose of the robot end-effector and force torque data. Data is organized into two folders, representing one of the two possible insertion slots. In each of the folders, data is further split into the following cases:
- error in insertion target position ranging from -10 to 10 mm in x direction in 1 mm steps,
- error in insertion target position ranging from -10 to 10 mm in y direction in 1 mm steps,
- no positional error.

Multiple attempts were made for each case.

Each entry has unique date-time tag and comprises: RGB image (.jpg) and .mat file with states object that contains reference and measured target pose in Cartesian space (positions and quaternions) and raw force-torque sensor data and force-torque data transformed to the tool frame.

The experiments were performed with Franka Emika Panda collaborative robot. For acquisition of image data an Intel Realsense D435 RGB-D camera has been utilized.