Organizational Unit:
Georgia Tech Research Institute (GTRI)
Georgia Tech Research Institute (GTRI)
Permanent Link
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Organizational Unit
Includes Organization(s)
Organizational Unit
Organizational Unit
ArchiveSpace Name Record
Publication Search Results
Now showing
1 - 6 of 6
-
ItemDeep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning(Georgia Institute of Technology, 2014-09) Doshi, Jigar ; Mason, Celeste ; Wagner, Alan ; Kira, ZsoltWe examine the problem of visual scene understanding and abstraction from first person video. This is an important problem and successful approaches would enable complex scene characterization tasks that go beyond classification, for example characterization of novel scenes in terms of previously encountered visual experiences. Our approach utilizes the final layer of a convolutional neural network as a high-level, scene specific, representation which is robust enough to noise to be used with wearable cameras. Researchers have demonstrated the use of convolutional neural networks for object recognition. Inspired by results from cognitive and neuroscience, we use output maps created by a convolutional neural network as a sparse, abstract representation of visual images. Our approach abstracts scenes into constituent segments that can be characterized by the spatial and temporal distribution of objects. We demonstrate the viability of the system on video taken from Google Glass. Experiments examining the ability of the system to determine scene similarity indicate ρ (384) = ±0:498 correlation to human evaluations and 90% accuracy on a category match problem. Finally, we demonstrate high-level scene prediction by showing that the system matches two scenes using only a few initial segments and predicts objects that will appear in subsequent segments.
-
ItemKinematics and Verification of a Deboning Device(Georgia Institute of Technology, 2009-08) Zhou, Debao ; Daley, Wayne ; McMurray, GaryPoultry deboning process is one of the largest employers in the United States and mainly involves human workers due to the unstructured nature of the task. For the automation of this process, a cutting device with the adaptive capability has been developed. In this paper, we focused on the kinematics of this device and the accuracy of the actual cutting point location. We validated the kinematic formulation and proofed the confidence of the accurate cutting. The applied verification method can be generalized to be applicable to general kinematics verification.
-
ItemAutomation of the Bird Shoulder Joint Deboning(Georgia Institute of Technology, 2007-09) Zhou, Debao ; Holmes, Jonathan ; Holcombe, Wiley ; McMurray, GaryPoultry deboning processing is one of the largest employers of people in the United States. It involves mainly manual processes with only limited use of fixed automation. The main difficulty in this task is the unstructured nature of the task due to the natural variability of birds’ size and deformable bodies. To increase product safety and quality, the industry is looking to robotics to help solve these problems. This research has focused on automating cutting of bird front halves. The anatomic structure of the chicken shoulder joint was studied first. Thus the cutting locations on chicken front halves were identified. In conjunction with force control robotics, a 3-DOF device with the capability for size adaptation and deformation compensation was proposed and the cutting trajectory was simulated. The results of the dynamic simulation verified that the desired trajectory can be followed and the response time for bone detection can be satisfied. A functional prototype of this device has been built and is currently under evaluation.
-
ItemCutting, ‘by Pressing and Slicing’, Applied to Robotic Cutting Bio-materials, Part I: Modeling of Stress Distribution(Georgia Institute of Technology, 2006-05) Zhou, Debao ; Claffee, Mark R. ; Lee, Kok-Meng ; McMurray, Gary V.Bio-material cutting, such as meat deboning, is one the most common operations in food processing. Automating this process using robotic devices with closed-loop force control has shown some promise. The control of the force trajectory directly relates to the internal stress in the material being cut, and must provide enough force to initiate the cut. The ability to model the stress distribution in the bio-materials being cut would provide a better understanding of the influencing factors and help predict the required cutting force for the design of the cutting mechanism and for automating the cutting operations. This research is presented in two parts: part I models the stress distribution when a blade acts on the bio-material and part II discusses the principles of biomaterial cutting. Starting with modeling a point force in the normal and tangential direction on the boundary of a semi -infinite body, an analytical expression for the stress tensor has been obtained and simulated using direct integral method. This paper provides the theoretical basis for explaining the cutting phenomena and predicting the cutting forces, a topic to be presented in Part II.
-
ItemCutting, ‘by Pressing and Slicing’, Applied to the Robotic Cut of Bio-materials, Part II: Force during Slicing and Pressing Cuts(Georgia Institute of Technology, 2006-05) Zhou, Debao ; Claffee, Mark R. ; Lee, Kok-Meng ; McMurray, Gary V.The applications of robotics are becoming more and more common in non-traditional industries such as the medical industry including robotic surgery and sample microtoming as well as food industry that include the processing of meats, fruits and vegetables. In this paper, the influence of the blade edgeshape and its slicing angle on the cutting of biomaterials are formulated and discussed based on the stress analysis that has been presented in Part I. Through modeling the cutting force, an optimal slicing angle can be formulated to maximize the feed rate while minimizing the cutting forces. Moreover, the method offers a means to predict cutting forces between the blade and the biomaterials, and a basis for design of robust force control algorithms for automating the cutting of biomaterials.
-
ItemUncalibrated Eye-in-Hand Visual Servoing(Georgia Institute of Technology, 2002-05) Piepmeier, Jenelle Armstrong ; Gumpert, Ben A. ; Lipkin, HarveyThis paper presents uncalibrated control schemes for vision-guided robotic tracking of a moving target using a moving camera. These control methods are applied to an uncalibrated robotic system with eye-in-hand visual feedback. Without a priori knowledge of the robot's kinematic model or camera calibration, the system is able to track a moving object and maintain the desired features. These control schemes estimate the system Jacobian as well as changes in target features due to target motion. Four novel strategies are simulated, and a variety of parameters are investigated with respect to performance.