The GRASP Taxonomy of Human Grasp Types

By Thomas Feix, Javier Romero, H. Schmiedmayer, Aaron M. Dollar, Danica Kragic. IEEE Transactions on Human-Machine Systems, 2016

982 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/c6f117170d227ad9742be3e52bb5539865ed16a5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Francesc Moreno-Noguer

Citations in the corpus

Human Hands as Probes for Interactive Object Understanding (2021, methodology): “This understanding can take different forms: grasp type classification [3,51,63] from a hand-defined taxonomy [15], hand keypoint and pose estimation [17], understanding gestures [18], detecting hands, their states and objects of interaction [55, 56], 3D reconstruction of the hand and the object of ”
Learning Dexterous In-Hand Manipulation. (2018, neutral): “Classified according to [18].”
High-Force Soft Printable Pneumatics for Soft Robotic Applications (2016, neutral): “37 The payload-to-weight ratio of the robotic hand is * 300%.”
Learning dexterous in-hand manipulation (2018, neutral): “Classiﬁed according to [18].”
In the Eye of the Beholder: Gaze and Actions in First Person Video (2020, methodology): “gaze estimation [10], [12], [13], hand analysis [72], [73], [74], [75], [76], pose estimation [14], [15], physiological parameter estimation [77], [78], user identification [79], [80], [81] and video summarization [16], [17], [18].”
GRAB: A Dataset of Whole-Body Human Grasping of Objects (2020, background): “This work has explored the object shape and purpose of grasps [10], contact areas on the hand captured by sinking objects in ink [27], pose and contact areas [3] captured with an integrated data-glove [11] and tactile-glove [51], or number of fingers in contact with the object and thumb position [14”
GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes (2020, methodology): “Formally, given an image I , we train a model M that provides a hand pose P and shape V , and grasp type C for every object of interest in I : where shape V is the set of vertices of the hand mesh and C is a coarse hand representation, within the 33-grasp taxonomy of [18].”
Grasping Field: Learning Implicit Representations for Human Grasps (2020, methodology): “In [33], the model learns to predict the best grasp type from the grasp taxonomy [36] according to the RGB images of the objects.”