1,720,995 research outputs found
Improving Ego-Lane Detection by Incorporating Source Reliability
No full textThis paper presents a framework for robust lane detection towards automated driving using multiple sensors. Since every single source (e.g., camera, digital map, etc.) can fail in certain situations, several independent sources need to be combined. Moreover, the reliability of each source strongly depends on environmental conditions, e.g., existence or visibility of lane markings. Thus, we introduce a concept of estimating and incorporating reliability into the fusion. First, a new sensor-independent error metric is applied to assess the quality of the estimated ego-lanes based on the angle deviation. Secondly, we deploy a boosting algorithm to select the highly discriminant features among the extracted information. Based on the selected features, we apply different classifiers to learn the reliabilities of the sources. Thirdly, we use Dempster-Shafer evidence theory to stabilize the estimated reliabilities over time. Using a big collection of real data recordings from different situations, the experimental results support our concept
Rock, paper, scissor: What's a substitute for hammer? : an approach to substitute selection for missing tool using robot-centric conceptual knowledge about objects
Full text linkWhen a robot is operating in a dynamic environment, it cannot be assumed that a
tool required to solve a given task will always be available. Consider, for instance,
a scenario where a robot is asked to serve drinks where the robot has to use a tray
to serve the drinks. If the robot finds the tray, the task will progress, but what if
the tray is unavailable. Such situations are common occurrences in our daily lives.
In situations like these a robot would be expected to improvise like humans from
the other available objects, for example, by using an eating plate for serving. This
skill is significant when operating in a dynamic, uncertain environment because
it allows a robot to adapt to unforeseen situations. The question is: how can a
robot determine which object in the environment is a suitable substitute for a
missing tool?
For substitute selection, we took inspiration from the way humans select a substitute
from the existing objects for a missing tool wherein humans take into
consideration conceptual knowledge about object’s physical and functional properties.
For instance, consider a scenario in which one has to choose between a
plate and a mouse pad as an alternative for a tray. For a tray whose designated
purpose is to carry, rigid and flat are more relevant to carry than a material or a
color of a tray. In order to find a suitable substitute, the relevant properties of the
missing tool need to correspond, as large a degree as possible, to the properties
of the available objects. In this work, we have proposed an approach to substitute
selection where a conceptual knowledge-driven computation is performed to
identify the relevant properties of the missing tool and determine a substitute
on the basis of shared relevant properties. The question is, how to acquire such
knowledge about the properties.
An argument has been put forth in cognitive science for bottom-up generation of
knowledge in which humans and animals alike develop conceptual understanding
of objects based on their own perceptual experiences with objects. We have
followed suit and propose that knowledge about properties should be generated
from the sensory measurements of the properties. We have termed such bottomup
generation of knowledge from the sensory measurements as robot-centric
knowledge. We propose an extensible property estimation framework which
consists of estimations methods to obtain the sensory measurements of physical
properties (rigidity, weight, etc.) and functional properties (containment,
support, etc.) from household objects. In our second contribution we employ 1)
unsupervised clustering methods to transformthe sensory measurements of the
properties into symbols, and then 2) bivariate joint frequency distributions and
sample proportion to generate conceptual knowledge about objects.
In this work, we have presented a proof of concept of the proposed approaches.
We acquired a dataset comprising six physical and four functional properties of
110 household objects using the proposed property estimation methods. This dataset was used to evaluate the property estimation methods and the semantics
of the considered properties within the dataset. Furthermore, the dataset is used
to generate the proposed robot-centric conceptual knowledge which is then used
by our proposed substitute selection system to identify a substitute from the
available objects in different missing tool scenarios.Wenn ein Roboter in einer dynamischen Umgebung agiert, kann nicht davon
aus-gegangen werden, dass einWerkzeug, das zur Lösung einer bestimmten Aufgabebenötigt
wird, immer verfügbar ist. Nehmen wir zum Beispiel ein Szenario,
indem ein Roboter aufgefordert wird, Getränke zu servieren, wobei der Roboter
ein Tablett benutzen muss, um die Getränke zu servieren. Wenn der Roboter
das Tablett findet, wird die Aufgabe erfüllt, aber was ist, wenn das Tablett nicht
verfügbar ist? Solche Situationen kommen in unseremtäglichen Leben häufig
vor. Insolchen Situationen wird von einem Roboter erwartet, dass er wie einMensch
ausanderen verfügbaren Gegenständen improvisiert, indem er zumBeispiel
einen Essteller zum Servieren verwendet. Diese Fähigkeit zur Improvisation ist
von großer Bedeutung, wenn er in einer dynamischen, unbekannten Umgebung
eingesetzt wird, denn sie ermöglicht es einem Roboter, sich an unvorhergesehene
Situationen anzupassen. Die Frage ist: Wie kann ein Roboter feststellen,
welches Objekt in derUmgebung ein geeigneter Ersatz für ein fehlendesWerkzeug
darstellt
Für die Auswahl eines Ersatzes haben wir uns von der Art undWeise inspirieren
lassen, wie Menschen einen solche Aufgabe aus den bereits vorhandenen Objekten
lösen. Dazu berücksichtigenMenschen insbesondere das konzeptionelle
Wissen über die physischen und funktionalen Eigenschaften des Objekts. Betrachten
wir zumBeispiel ein Szenario, in demman zwischen einem Teller und
einemMauspad als Alternative für ein Tablett wählen muss. Bei einem Tablett,
dessen Hauptzweck das Tragen ist, sind die Eigenschaften wie starr und flach
wichtiger als das Material oder die Farbe eines Tabletts. Um einen geeigneten
Ersatz zu finden, müssen die relevanten Eigenschaften des fehlendenWerkzeugs
so weit wie möglich mit den Eigenschaften der verfügbaren Objekte übereinstimmen.
In dieser Forschungsarbeit haben wir einen Ansatz für die Auswahl
eines Ersatz es vorgeschlagen, bei dem eine konzeptionelle, wissensbasierte
Berechnung durchgeführt wird, umdie relevanten Eigenschaften des fehlenden
Werkzeugs zu ermitteln und einen Ersatz auf der Grundlage der gemeinsamen relevanten
Eigenschaften zu bestimmen. Die Frage ist, wieman sich diesesWissen
über die Eigenschaften aneignet.
In der Kognitionswissenschaft wurde ein Argument für die Bottom-up-Erzeugung
vonWissen vorgebracht, wonachMenschen und Tiere gleichermaßen ein begriffliches
Verständnis von Objekten auf derGrundlage ihrer eigenenWahrnehmungserfahrungen
mit Objekten entwickeln. Wir sind diesem Beispiel gefolgt und
schlagen vor, dass das Wissen über Eigenschaften aus den sensorischen Messungen
der Eigenschaften gewonnen werden sollte. Wir haben eine solche
Bottom-up-Generierung von Wissen aus den sensorischen Messungen als
roboterzentriertes Wissen bezeichnet. Wir schlagen einen erweiterbaren Rahmen
für die Schätzung von Eigenschaften vor, der aus Schätzungs methoden
besteht, um die sensorischen Messungen der physikalischen Eigenschaften (Steifigkeit,Gewicht usw.) und der funktionalen Eigenschaften (Behältnis, Halt
usw.) von Haushaltsgegenständen zu erhalten. In unserem zweiten Beitrag
schlagen wir 1) unüberwachte Clustering-Methoden vor, umdie sensorischen
Messungen der Eigenschaften in Symbole umzuwandeln, und dann 2) bivariate
gemeinsame Häufigkeitsverteilungen und Stichprobenanteile, um konzeptionellesWissenüber
Objekte zu generieren.
In dieser Forschungsarbeit haben wir ein Proof of Concept der vorgeschlagenen
Ansätze vorgestellt. Wir haben einen Datensatz mit sechs physikalischen
und vier funktionalen Eigenschaften von 110 Haushaltsgegenständen erstellt
und dabei die vorgeschlagenen Methoden zur Eigenschaftsschätzung verwendet.
Dieser Datensatz wurde verwendet, um die Methoden zur Schätzung der
Eigenschaftenund die Semantik der betrachteten Eigenschaften innerhalb des
Datensatzes zubewerten. Darüber hinaus wird der Datensatz verwendet, um das
vorgeschlagene roboterzentrierte konzeptionelleWissen zu generieren, das dann
von unserem vorgeschlagenen Ersatzauswahlsystem verwendet wird, um einen
Ersatz aus den verfügbaren Objekten in verschiedenen Szenarien mit fehlendem
Werkzeug zu identifizieren
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
A General Reliability-Aware Fusion Concept Using DST and Supervised Learning with Its Applications in Multi-Source Road Estimation
No full textVariations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
