Slip Labels and Inertial Data from Compliant Hand (SLID-CH)

Using a two-finger tendon-driven hand, I performed 195 manipulation trials involving both slip and environmental-sliding conditions. I then labeled this data automatically using motion-tracking data, and trained a convolutional neural network (CNN) to detect slip events based on data from two fingertip-mounted inertial measurement units (IMUs). This dataset contains the kinematics obtained from the motion tracking data (timestamped poses and velocities), the IMU data, features and labels for machine learning, and the trained models.