Local Curvature Estimation and Grasp Stability Prediction Based on Proximity Sensors on a Multi-Fingered Robot Hand

This study aims to realize a precision grasp of unknown-shaped objects. Precision grasping requires a detailed understanding of the surface shapes such as concavity and convexity. If an accurate shape model is not given in advance, it must be addressed by sensing. We have proposed a method for recognizing detailed object shapes using proximity sensors equipped on each fingertip of a multi-fingered robot hand. Direct sensing of the object’s surface from the fingertips enables both avoidance of unintended collision during the approach process and recognition of surface profiles for use in planning and executing stable grasping. This paper introduces local surface curvature estimation to improve the accuracy of local surface recognition. We propose practical and accurate models to estimate local curvature based on various characteristic tests on the proximity sensor and to estimate the distance to the nearest point. In actual experiments, it was shown that it was possible to estimate the position of the nearest point with a mean error of less than 2 mm and to predict grasping stability in reasonable real-time for the object shape.