Functional Analysis of Grasping Motion
grasping, trajectory, principal component analysis, dynamics, taxonomy, joints, robots, grasping motion representation, functional grasping motion analysis, functional principal component analysis, ten-fold cross validation approach, naturally clustered grasping motion trajectories, data-driven taxonomy, grasping motion collection, PCA-plus-fPCA space, Cutkosky grasp taxonomy, grasp types, low-dimensional space, PCA-based approach, motion dynamic features
Digital Object Identifier (DOI)
This paper presents a novel grasping motion analysis technique based on functional principal component analysis (fPCA). The functional analysis of grasping motion provides an effective representation of grasping motion and emphasizes motion dynamic features that are omitted by classic PCA-based approaches. The proposed approach represents, processes, and compares grasping motion trajectories in a low-dimensional space. An experiment was conducted to record grasping motion trajectories of 15 different grasp types in Cutkosky grasp taxonomy. We implemented our method for the analysis of collected grasping motion in the PCA+fPCA space, which generated a new data-driven taxonomy of the grasp types, and naturally clustered grasping motion into 5 consistent groups across 5 different subjects. The robustness of the grouping was evaluated and confirmed using a tenfold cross validation approach.
Was this content written or created while at USF?
Citation / Publisher Attribution
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, 2013, p. 3507-3513.
Scholar Commons Citation
Dei, Wei; Sun, Yu; and Qian, Xiaoning, "Functional Analysis of Grasping Motion" (2013). Computer Science and Engineering Faculty Publications. 88.