A survey of unknown object grasping and our fast grasping algorithm-C shape grasping

Abstract

Grasping of unknown objects with neither appearance data nor object models given in advance is very important for robots that work in an unfamiliar environment. In recent years, extensive research has been conducted in the domain of unknown object grasping and many successful grasping algorithms for unknown objects are created. However, So far there is not a very general fast grasping algorithm suits various kinds of unknown objects. Therefore, choice among different grasping algorithms becomes necessary for users. In order to make it more convenient for users to quickly understand and choose a suitable grasping algorithm, a survey about the latest research results of unknown object grasping is made in this paper. We compared different grasping algorithms with each other and obtained a table to clearly show the result of comparison. The comparison could give researchers meaningful information in order to quickly pick a grasping approach with their requirements. Meanwhile, we briefly showed our latest fast grasping algorithm which employs only a partial point cloud of the target object as input, and the grasping algorithm can quickly work out a suitable grasp for most objects within 2 seconds on a common personal computer. Simulations are used to examine the performance of our algorithm and successful results are obtained