Abstract

To solve the unfixed grasping tasks during the fruits picking and rating, grasping modeling is researched as the most important part of the robot hand solutions. A survey for grasping synthesis method with dexterous robot hand is presented in this paper. The difference of grasping characters is introduced between dexterous hand and underactuated hand. Especially, the feature of self-adaptive enveloping grasp achieved by underactuated finger mechanism is outlined, which has good performance in grasping unknown objects. In order to generate valid grasps for unknown target objects and apply in real-time control system for underactuated robot hand, a grasping strategy synthesis model for universal grasp tasks is proposed based on human knowledge analysis. It is composed by off-line neural networks training section and on-line compute section. Firstly, daily grasped objects are used to build a sample space by human experience. Then the discrete sample space is computed by fuzzy clustering method. The data is used to generate grasp decision scheme by rough set mixed artificial neural networks. An examination is simulated for grasp configurations choice of the underactuated robot hand with the aim to show the practical feasibility of the proposed grasp strategy.

Key words: Underactuated robot hand, grasp planning, neural network, fruits grasping.