The following data was obtained from the TacTip tactile sensor mounted on a UR5 robotics arm. A flat object was allowed to slip across the surface to the TacTip and the pin positions were recorded. 40 data files are included of which 20 were used to train support vector machine classifiers to detect slip. The remaining 20 were used to evaluate the success of the classifier. The support vector machines used in the study are also included in the data folder.
Supported by EPSRC Centre for Doctoral Training in Future Autonomous and Robotic Systems (FARSCOPE) at Bristol Robotics Laboratory, EPSRC
grant on ‘Tactile superresolution sensing’ (EP/M02993X/1) and Leadership Award from the Leverhulme Trust on `A biomimetic forebrain for robot touch' (RL-2016-39).