Low-Cost In-Hand Slippage Detection and Avoidance for Robust Robotic Grasping with Compliant Fingers

The act of grasping is fundamental for a robot to purposefully interact with its environment. However, all too often roboticists treat it as a singular event that can be solved with elaborate prior information such as kinematic models and planning thereupon. Instead, we advocate the view of grasping as a process that requires continuous adaptation to handle cases like (i) uncertainty in the objects’ shape or mass that may result in imperfect grasps; or (ii) objects slipping in the robot’s fingers. Recently, compliant fingers have been employed to address those challenges. However, it is still an open question how to properly integrate sensors to estimate the fingers’ grasping state.We propose the integration of low-cost – in terms of monetary expenses and integration effort – bend sensors and proximity sensors into a pair of flexible fingers. The resulting system enables the robot to detect and react to object slippage by relying on a simple sensor fusion scheme. We successfully demonstrate those capabilities over a set of objects that feature varying characteristics in terms of geometric shape, mass or rigidity. Two specially challenging objects are a fragile chocolate egg and a key chain that the robot still handles successfully.