Surface Patch Primitive Based Object Modeling from CAD Data

2012 ◽  
Vol 162 ◽  
pp. 179-183 ◽  
Author(s):  
Sukhan Lee ◽  
Kyeong Dae Yoo ◽  
Jae Woong Kim ◽  
Moon Ju Lee
Keyword(s):  
Automated Reasoning ◽  
Direct Application ◽  
Robotic Manipulation ◽  
Surface Patch ◽  
Geometric Information ◽  
Grasp Planning ◽  
Manufacturing Automation ◽  
Novel Method ◽  
Robotic Automation ◽  
Geometric Primitives

For manufacturing automation, for instance, the robotic automation of automobile sub-assembly, CAD data serves as DB offering the geometric information of parts essential for robotic manipulation. However, a direct application of CAD for the robotic manipulation of parts may be of an issue, due to the fact that the particular format of the CAD data available, e.g., STL, does not directly provide certain geometric entities such as surface patch primitives and/or features that are required for robotic manipulation. In this paper, we present a novel method for extracting geometric primitives and/or features, such surface patch primitives as planar, cylindrical, conic, and spherical patches, from the STL format of CAD data, such that an industrial part/object can be represented as a logical sum of these surface patch primitives extracted. This surface patch primitive based modeling makes the automated reasoning involved in the recognition and pose estimation, as well as the grasp planning, of parts/objects easy to be done. The proposed method is applied to various CAD data samples for experimentation: the results demonstrate the reliability as well as the computational efficiency of the proposed method in the extraction of surface patch primitives.

Mechanisms for Robotic Grasping and Manipulation

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Vincent Babin ◽  
Clément Gosselin
Keyword(s):  
Online Publication ◽  
Autonomous Systems ◽  
Robotic Manipulation ◽  
Annual Review ◽  
Publication Date ◽  
Robotic Grasping ◽  
Grasp Planning ◽  
Grasping And Manipulation

This article reviews the literature on the design of robotic mechanical grippers, with a focus on the mechanical aspects, which are believed to be the main bottleneck for effective designs. Our discussion includes gripper architectures and means of actuation, anthropomorphism and grasp planning, and robotic manipulation, emphasizing the complementary concepts of intrinsic and extrinsic dexterity. We also consider interactions of robotic grippers with the environment and with the objects to be grasped and argue that the proper handling of such interactions is key to the development of grasping and manipulation tools and scenarios. Finally, we briefly present examples of recent designs to support the discussion. Expected final online publication date for the Annual Review of Control, Robotics, and Autonomous Systems, Volume 4 is May 3, 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

A Computable Characterization of the Extrinsic Mean of Reflection Shapes and Its Asymptotic Properties

2015 ◽  
Vol 32 (01) ◽  
pp. 1540005
Author(s):  
Chao Ding ◽  
Hou-Duo Qi
Keyword(s):  
Hypothesis Test ◽  
Asymptotic Properties ◽  
Shape Space ◽  
Direct Application ◽  
Symmetric Matrices ◽  
Geometric Information ◽  
Computable Formula ◽  
Arbitrary Dimensions ◽  
Extrinsic Mean

The reflection shapes of configurations in ℜm with k landmarks consist of all the geometric information that is invariant under compositions of similarity and reflection transformations. By considering the corresponding Schoenberg embedding, we embed the reflection shape space into the Euclidean space of all (k - 1) by (k - 1) real symmetric matrices. In this paper, we provide a computable formula of the extrinsic mean of the reflection shapes in arbitrary dimensions. Moreover, the asymptotic analysis of the extrinsic mean of the reflection shapes is studied. By using the differentiability of spectral operators, we obtain a central limit theorem of the sample extrinsic mean of the reflection shapes. As a direct application, the two-example hypothesis test of the reflection shapes is also derived.

scholarly journals O2A: One-Shot Observational Learning with Action Vectors

2021 ◽  
Vol 8 ◽  
Author(s):  
Leo Pauly ◽  
Wisdom C. Agboh ◽  
David C. Hogg ◽  
Raul Fuentes
Keyword(s):  
Robotic Manipulation ◽  
Reward Function ◽  
Learning Domains ◽  
Comparable Performance ◽  
Third Person ◽  
Novel Method ◽  
Real Robot ◽  
3D Cnn ◽  
Demonstration Video ◽  
First Time

We present O2A, a novel method for learning to perform robotic manipulation tasks from a single (one-shot) third-person demonstration video. To our knowledge, it is the first time this has been done for a single demonstration. The key novelty lies in pre-training a feature extractor for creating a perceptual representation for actions that we call “action vectors”. The action vectors are extracted using a 3D-CNN model pre-trained as an action classifier on a generic action dataset. The distance between the action vectors from the observed third-person demonstration and trial robot executions is used as a reward for reinforcement learning of the demonstrated task. We report on experiments in simulation and on a real robot, with changes in viewpoint of observation, properties of the objects involved, scene background and morphology of the manipulator between the demonstration and the learning domains. O2A outperforms baseline approaches under different domain shifts and has comparable performance with an Oracle (that uses an ideal reward function). Videos of the results, including demonstrations, can be found in our: project-website.

Knowledge-Based Personalization

2011 ◽  
pp. 26-33
Author(s):  
Tamara Babaian
Keyword(s):  
Artificial Intelligence ◽  
Automated Reasoning ◽  
Personal Information ◽  
End User ◽  
Collaborative System ◽  
Knowledge Based ◽  
Planning Framework ◽  
Novel Method ◽  
Precise Time ◽  
The Way

We present a novel method for software personalization. Personalization is understood broadly as a set of mechanisms by which an application is tailored to a particular end user and his or her task. The presented method outlined here is motivated by and remedies a few widely recognized problems in the way customization is carried out. The proposed method has been used in a collaborative system called Writer’s Aid. It relies on a declarative specification of preconditions and effects of system’s actions and applies artificial intelligence, automated reasoning, and planning framework and techniques to dynamically recognize the lack or availability of the personal information at the precise time when it affects a system action and initiates an interaction with the user aimed at eliciting this information in case it has not yet been specified.

scholarly journals Monocular Visual Inertial Direct SLAM with Robust Scale Estimation for Ground Robots/Vehicles

Robotics ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 23
Author(s):  
Bismaya Sahoo ◽  
Mohammad Biglarbegian ◽  
William Melek
Keyword(s):  
Pose Prediction ◽  
Geometric Information ◽  
Land Vehicles ◽  
Tightly Coupled ◽  
Novel Method ◽  
Epipolar Constraints ◽  
Inertial Measurements ◽  
Primary Contribution ◽  
Alignment Step ◽  
Indoor And Outdoor

In this paper, we present a novel method for visual-inertial odometry for land vehicles. Our technique is robust to unintended, but unavoidable bumps, encountered when an off-road land vehicle traverses over potholes, speed-bumps or general change in terrain. In contrast to tightly-coupled methods for visual-inertial odometry, we split the joint visual and inertial residuals into two separate steps and perform the inertial optimization after the direct-visual alignment step. We utilize all visual and geometric information encoded in a keyframe by including the inverse-depth variances in our optimization objective, making our method a direct approach. The primary contribution of our work is the use of epipolar constraints, computed from a direct-image alignment, to correct pose prediction obtained by integrating IMU measurements, while simultaneously building a semi-dense map of the environment in real-time. Through experiments, both indoor and outdoor, we show that our method is robust to sudden spikes in inertial measurements while achieving better accuracy than the state-of-the art direct, tightly-coupled visual-inertial fusion method.

scholarly journals Segmentation of Online Freehand Sketching Based on Speed Feature

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Guanfeng Wang ◽  
Shouxia Wang ◽  
Jingjing Kang ◽  
Shuxia Wang
Keyword(s):  
User Study ◽  
Feature Points ◽  
Sketch Recognition ◽  
Average Speed ◽  
Freehand Sketch ◽  
Novel Method ◽  
Geometric Primitives ◽  
Threshold Technique

We present a novel method to extract speed feature points for segmenting hand-drawn strokes into geometric primitives. The method consists of three steps. Firstly, the input strokes are classified into uniform and nonuniform speed strokes, representing a stroke drawn at relatively constant or uneven speeds, respectively. Then, a sharpening filter is used to enhance the peak features of the uniform speed strokes. Finally, a three-threshold technique that uses the average speed of the pen and its upper and lower deviations is used to extract speed feature points of strokes. We integrate the proposed method into our freehand sketch recognition (FSR) system to improve its robustness to support multiprimitive strokes. Through a user study with 8 participants, we demonstrate that the proposed method achieves higher segmentation efficiency in finding speed feature points than the existing method based on a single speed threshold.

Contributions to the mechanisms of mitosis and roles of cytoplasmic microtubules from ultrastructural analyses of fungi

1978 ◽  
Vol 36 (2) ◽  
pp. 266-267
Author(s):  
I. Brent Heath
Keyword(s):  
Nuclear Envelope ◽  
Direct Application ◽  
Ultrastructural Analysis ◽  
General Interest ◽  
Research Results ◽  
Organelle Motility ◽  
Cytoplasmic Microtubules

Detailed ultrastructural analysis of fungal mitotic systems and cytoplasmic microtubules might be expected to contribute to a number of areas of general interest in addition to the direct application to the organisms of study. These areas include possibly fundamental general mechanisms of mitosis; evolution of mitosis; phylogeny of organisms; mechanisms of organelle motility and positioning; characterization of cellular aspects of microtubule properties and polymerization control features. This communication is intended to outline our current research results relating to selected parts of the above questions.Mitosis in the oomycetes Saprolegnia and Thraustotheca has been described previously. These papers described simple kinetochores and showed that the kineto- chores could probably be used as markers for the poorly defined chromosomes. Kineto- chore counts from serially sectioned prophase mitotic nuclei show that kinetochore replication precedes centriole replication to yield a single hemispherical array containing approximately the 4 n number of kinetochore microtubules diverging from the centriole associated "pocket" region of the nuclear envelope (Fig. 1).

On the Shape of Field-Ion Emitters

1976 ◽  
Vol 34 ◽  
pp. 520-521
Author(s):  
H.C. Eaton ◽  
B.N. Ranganathan ◽  
T.W. Burwinkle ◽  
R. J. Bayuzick ◽  
J.J. Hren
Keyword(s):  
Grain Boundary ◽  
Spherical Shape ◽  
Theoretical Strength ◽  
Evaporation Process ◽  
Field Evaporation ◽  
Geometric Information ◽  
Field Ion Microscopy ◽  
Considerable Error ◽  
True Shape ◽  
Ion Microscopy

The shape of the emitter is of cardinal importance to field-ion microscopy. First, the field evaporation process itself is closely related to the initial tip shape. Secondly, the imaging stress, which is near the theoretical strength of the material and intrinsic to the imaging process, cannot be characterized without knowledge of the emitter shape. Finally, the problem of obtaining quantitative geometric information from the micrograph cannot be solved without knowing the shape. Previously published grain-boundary topographies were obtained employing an assumption of a spherical shape (1). The present investigation shows that the true shape deviates as much as 100 Å from sphericity and boundary reconstructions contain considerable error as a result.Our present procedures for obtaining tip shape may be summarized as follows. An empirical projection, D=f(θ), is obtained by digitizing the positions of poles on a field-ion micrograph.

The removal and morphology of intact biofilms from implanted venous access devices

1995 ◽  
Vol 53 ◽  
pp. 1020-1021
Author(s):  
M.A. Gregory ◽  
G.P. Hadley
Keyword(s):  
Patient Selection ◽  
Surgical Oncology ◽  
Venous Access ◽  
Common Procedure ◽  
Indwelling Catheters ◽  
Careful Patient ◽  
Novel Method ◽  
The Subject ◽  
Vascular Catheters ◽  
Venous Access Devices

The insertion of implanted venous access systems for children undergoing prolonged courses of chemotherapy has become a common procedure in pediatric surgical oncology. While not permanently implanted, the devices are expected to remain functional until cure of the primary disease is assured. Despite careful patient selection and standardised insertion and access techniques, some devices fail. The most commonly encountered problems are colonisation of the device with bacteria and catheter occlusion. Both of these difficulties relate to the development of a biofilm within the port and catheter. The morphology and evolution of biofilms in indwelling vascular catheters is the subject of ongoing investigation. To date, however, such investigations have been confined to the examination of fragments of biofilm scraped or sonicated from sections of catheter. This report describes a novel method for the extraction of intact biofilms from indwelling catheters.15 children with Wilm’s tumour and who had received venous implants were studied. Catheters were removed because of infection (n=6) or electively at the end of chemotherapy.

Sign in / Sign up

Export Citation Format

Share Document