Determining the joints most strained in an underactuated robotic finger by adaptive neuro-fuzzy methodology

• Kinetostatic analyzing of the new finger structure.
• Selecting and analyzing of the most strained finger joints.
• Variable selection based on using adaptive neuro-fuzzy inference system.
• Improving the prediction performance of the predictors.
• Providing the most influential parameters on the predictor.

The main purpose of this paper is to determine what joints are most strained in the proposed underactuated finger by adaptive neuro-fuzzy methodology. For this, kinetostatic analysis of the finger structure is established with added torsional springs in every single joint. Since the finger’s grasping forces depend on torsional spring stiffness in the joints, it is preferable to determine which joints have the most influence on grasping forces. Hence, the finger joints experiencing the most strain during the grasping process should be determined. It is desirable to select and analyze a subset of joints that are truly relevant or the most influential to finger grasping forces in order to build a finger model with optimal grasping features. This procedure is called variable selection. In this study, variable selection is modeled using the adaptive neuro-fuzzy inference system (ANFIS). Variable selection using the ANFIS network is performed to determine how the springs implemented in the finger joints affect the output grasping forces. This intelligent algorithm is applied using the Matlab environment and the performance is analyzed. The simulation results presented in this paper show the effectiveness of the developed method.