Robotic Multifinger Grasping State Recognition Based on Adaptive Multikernel Dictionary Learning

Traditional grasping analysis of mechanical dexterous grippers tends to flatten a multifinger tactile series into 1-D, which ignores the force coupling between fingers and their different grasping force characteristics. To overcome this problem, this work proposes a novel adaptive multikernel dictionary learning (AMDL) method. First, in order to capture the nonlinear feature similarity of different tactile samples, multiple basic kernel functions are used to map all the training samples into Hilbert space, and the corresponding kernel matrix of each basic kernel is computed, respectively. Then, an adaptive kernel weight calculation method is developed to learn the adaptive kernel of each basic kernel. A composite kernel, which is the linear combination of multiple basic kernels by using the learned adaptive weights, is constructed to calculate the multidimensional kernel matrix. Finally, this work utilizes the proposed AMDL to fuse grasping tactile information of multiple fingers to further consider the force coupling among them, during which the sparse pattern of the coding vector of each finger's tactile data is restricted to be consistent. The proposed algorithm is compared with other state-of-the-art algorithms in terms of F1 score on the public BioTac SP tactile dataset and our collected tactile dataset. Its grasping state recognition result shows its validity and feasibility.

Automated summary

This study proposes a novel adaptive multikernel dictionary learning method for analyzing the grasping tactile information of mechanical dexterous grippers. By using multiple basic kernel functions and an adaptive kernel weight calculation method, the force coupling among fingers is effectively considered by combining the tactile information from multiple fingers.