ENB 223, 4202 E Fowler Ave, Tampa 33620, FL, USA
yusun AT usf.edu
813-974-7506 (813-385-4612)
To represent motions from a mechanical point of view, this paper explores motion embedding using the motion taxonomy. With this taxonomy, manipulations can be described and represented as binary strings called motion codes. Motion codes capture mechanical properties, such as contact type and trajectory, that should be used to define suitable distance metrics between motions or loss functions for deep learning and reinforcement learning.
Read more
Video understanding is one of the most challenging topics in computer vision. In this project, a four-stage video understanding pipeline was presented to simultaneously recognize all atomic actions and the single ongoing activity in a video. The pipeline used objects and motions from the video and a graph-based knowledge representation network as prior reference.
Read more
Pouring is a simple task people perform daily. It is the second most frequently executed motion in cooking scenarios, after pick-and-place. We present a pouring trajectory generation approach, which uses force feedback from the cup to determine the future velocity of pouring.
Read more
In the paper, we propose an automated multimodal approach that utilizes a combination of both behavioral and physiological pain indicators to assess infants’ pain. We also present a unimodal approach that depends on a single pain indicator for assessment.
Read more
In one embodiment, a method for projecting images on a subject includes determining a pose and position of the subject, adjusting a three-dimensional model of an anatomical structure of the subject to match the determined pose and position, and projecting an image of the anatomical structure onto the subject
Read more
In the paper, we take a significant step forward by reviewing datasets that were published in the last 10 years and that are directly related to object manipulation and grasping. We report on modalities, activities, and annotations for each individual dataset and we discuss our view on its use for object manipulation.
Read more
The paper introduces two grasp quality measures that are derived from the two manipulation requirements: interactive wrench requirements and motion requirements for accomplishing a manipulation task
Read more
This paper presents a novel structured knowledge representation called functional object-oriented network (FOON) to model the connectivity of the functional-related objects and their motions in manipulation tasks. The graphical model FOON is learned by observing object state change and human manipulations with the objects.
Read more
In one embodiment, planning a robot grasp of an object includes determining a grasp type that would be used by a human being to grasp the object, determining a position and orientation of the human being's thumb relative to the object, and planning the robot grasp based upon the determined grasp type and thumb position and orientation.
Read more
