Abstract:

For fabric autonomous grasp of textile and garment industry, low production efficiency will be caused by manual operation. Fabric is grasped by dexterous hand in this paper. Firstly, multi-fingered dexterous hand was designed and a method of kinematics analysis was used by describing coordinates transformation relation of fingers' connecting rod. Grasp mode planning was programmed by using Radial Basis Function (RBF) nrural network method. By identifying the fabric's  geometric feature and according to the requirements of the grasp tasks autonomous grasp is realized. In the process of grasp movement, the joint space trajectory planning and Cartesian space trajectory planning were combined to ensure the dexterous hand fingers can stably and accurately reach to the grasp point. Finally, multi-finger dexterous hand and grasp planning were simulated by using MatLab/Robotics Toolbox, and the simulation results show that the design of the dexterous hand joint parameters setting is reasonable, and fabric grasp meet the requirements.

Key words: multi-fingered dexterous hand, grasp mode planning, RBF neural network, trajectory planning, fabric grasp