Tactile Enabled Robotic Grasping

In the scope of my Master Thesis, with the supervision of Carlo Sferrazza, and together with professor Raffaello D’Andrea, I worked on a novel slip detection pipeline that makes leverages the rich tactile feedback provided by a state of the art vision-based tactile sensor developed in house at IDSC, to reliably predict possibly failing grasps.

Grasping objects whose physical properties are unknown is still a great challenge in robotics. Most solutions rely entirely on visual data to plan the best grasping strategy. However, to match human abilities and be able to reliably pick and hold unknown objects, the integration of an artificial sense of touch in robotic systems is pivotal. This project proposes a novel model-based slip detection pipeline that can predict possibly failing grasps in real-time and signal a necessary increase in grip force, using uniquely sensory data provided by a state-of-the-art vision-based tactile sensor that accurately estimates distributed forces. A couple of such sensors were integrated in a grasping setup composed of a six degrees-of-freedom cobot and a two-finger gripper.

Results show that the system can reliably predict slip while manipulating objects of different shapes, materials and weight. The sensor can detect both translational and rotational slip in various scenarios, making it suitable to improve the stability of a grasp.