Refine
Departments, institutes and facilities
- Fachbereich Informatik (31)
- Fachbereich Ingenieurwissenschaften und Kommunikation (16)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (13)
- Fachbereich Wirtschaftswissenschaften (7)
- Institut für Cyber Security & Privacy (ICSP) (7)
- Institut für Verbraucherinformatik (IVI) (6)
- Fachbereich Sozialpolitik und Soziale Sicherung (5)
- Institute of Visual Computing (IVC) (4)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (2)
- Zentrum für Innovation und Entwicklung in der Lehre (ZIEL) (2)
Document Type
- Conference Object (68) (remove)
Year of publication
- 2021 (68) (remove)
Has Fulltext
- no (68) (remove)
Keywords
- Cognitive robot control (2)
- Explainable robotics (2)
- Learning from experience (2)
- Usable Privacy (2)
- AES (1)
- Applications in Energy Transport (1)
- Architecture (1)
- Assistive robots (1)
- Augmented Reality (1)
- Automatic Differentiation (1)
Die soziale Netzwerkanalyse versucht menschliche Interaktion in einen analytischen und auswertbaren Zusammenhang zu bringen. Sie hat sich als Methode in den letzten Jahrzehnten über die Sozialwissenschaften hinaus in die Geschichtswissenschaften, Archäologie und Religionswissenschaften verbreitet. Dabei fanden verschiedene Paradigmenwechsel statt, zum Beispiel vom statischen Netzwerken mit dem Schwerpunkt auf quantitativ-struktureller Analyse hin zu heterogenen Handlungsnetzwerken wie zum Beispiel in der der Actor Network Theory (ANT) gewandelt. Der Fokus liegt aktuell eher auf der Frage des Informationsaustauschs und der Dynamik nicht statischer Netzwerke.
This paper gives an overview of how we can benefit from using container technology in our academic work. It aims to be a starting point for fellow researchers which also think about applying these technologies. Hence, we focus on decribing our own experiences and motivations instead of proving hard scientific facts.
Open-Source Software spielt sowohl zur Ausgestaltung von Lehr- und Lernszenarien (bspw. Organisation mit Editoren und Groupware, Kollaboration und Kommunikation via Chats und Webblogs), als auch für die Umsetzung von Forschunsprojekten (zum Beispiel Auswertung großer Datenbestände, Erprobung realer Situationen in vituellen Laboren, Evaluation neuer Oberflächenentwicklungen) eine wichtige Rolle. Um eine bestmögliche Passung der Software herzustellen, erfolgt Softwareentwicklung im Hochschulbereich entweder forschungsprojektbezogen oder Disziplin- und Einrichtungsübergreifend.
Das Kernanliegen des Datenschutzes ist es, natürliche Personen vor nachteiligen Effekten der Speicherung und Verarbeitung der sie betreffenden Daten zu schützen. Aber viele Personen scheinen gar nicht geschützt werden zu wollen. Im Gegenteil, viele Endanwender willigen “freiwillig“ – bewusst oder unbewusst – in eine umfassende Verarbeitung ihrer personenbezogenen Daten ein. Warum tun Menschen dies? Es werden verschiedene Ursachen diskutiert (beispielsweise in [79]), hierzu gehören Uninformiertheit, mangelnde Sensibilität, das Gefühl der Hilflosigkeit, mangelnde Zahlungsbereitschaft und mangelnde Alternativen. Auch wenn dies in Einzelfällen zutrifft, so gibt es oft sehr wohl datenschutzfreundliche Alternativen. Beispielsweise existiert zu WhatsApp (als Instant Messaging App) die Alternative Threema. Threema gilt als EU-DS-GVO-konform und funktional durchaus mit WhatsApp vergleichbar [62]. Allerdings ist inzwischen die aktuelle Netzwerkgröße ein entscheidendes Auswahlkriterium: Im Januar 2018 hatte Threema 4,5 Millionen Nutzer [172], WhatsApp dagegen 1,5 Milliarden [171]. Dies ist ein Indiz dafür, dass WhatsApp sich quasi zum De-facto-Standard entwickelt hat und es für die einzelne Person nur schwer möglich ist, viele andere “zum Wechsel auf ein anderes Produkt zu bewegen. [. . . ] Bei Diensten mit Nutzerzahlen im Milliardenbereich kann von ’Freiwilligkeit’ nur noch bedingt gesprochen werden.“ [9]
Experience made with free and open source software (FOSS) in the public research is shared with the community. The motivation for using and publishing FOSS is to increase visibility, transparancy and feedback quality while at the same time lowering software licensing costs. Also, the idea of giving back and returning a value plays a role. The most frequently given counter arguments are discussed. In the end, it’s important to embed FOSS publishing into the company’s strategy for the exploitation of scientific research results. To help with this, a checklist of criteria to indicate FOSS publishing is suggested. On the backround of wireless sensor networks, some case studies of FOSS contribution are detailed. The emphasis is on checking the original motivation and the spirit of FOSS back with the reality. Finally, further potential of publishing FOSS in the context of scientific research is identified.
Cancer is one of the leading causes of death worldwide [183], with lung tumors being the most frequent cause of cancer deaths in men as well as one of the most common cancers diagnosed in woman [40]. As symptoms often arise in advanced stages, an early diagnosis is especially important to ensure the best and earliest possible treatment. In order to achieve this, Computed Tomography (CT) scans are frequently used for tumor detection and diagnosis. We will present examples of publicly available CT image data of lung cancer patients and discuss possible methods to realize an automatic system for automated cancer diagnosis. We will also look at the recent SPIE-AAPM Lung CT Challenge [10] data set in detail and describe possible methods and challenges for image segmentation and classification based on this data set.
Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models
(2021)
When faced with an execution failure, an intelligent robot should be able to identify the likely reasons for the failure and adapt its execution policy accordingly. This paper addresses the question of how to utilise knowledge about the execution process, expressed in terms of learned constraints, in order to direct the diagnosis and experience acquisition process. In particular, we present two methods for creating a synergy between failure diagnosis and execution model learning. We first propose a method for diagnosing execution failures of parameterised action execution models, which searches for action parameters that violate a learned precondition model. We then develop a strategy that uses the results of the diagnosis process for generating synthetic data that are more likely to lead to successful execution, thereby increasing the set of available experiences to learn from. The diagnosis and experience correction methods are evaluated for the problem of handle grasping, such that we experimentally demonstrate the effectiveness of the diagnosis algorithm and show that corrected failed experiences can contribute towards improving the execution success of a robot.
When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional learning, as using incomplete or unsuitable policies can lead to execution failures. Generalisation is particularly relevant when a robot has to deal with a large variety of objects and in different contexts. In this paper, we propose and analyse a strategy for generalising parameterised execution models of manipulation actions over different objects based on an object ontology. In particular, a robot transfers a known execution model to objects of related classes according to the ontology, but only if there is no other evidence that the model may be unsuitable. This allows using ontological knowledge as prior information that is then refined by the robot’s own experiences. We verify our algorithm for two actions – grasping and stowing everyday objects – such that we show that the robot can deduce cases in which an existing policy can generalise to other objects and when additional execution knowledge has to be acquired.
Property-Based Testing in Simulation for Verifying Robot Action Execution in Tabletop Manipulation
(2021)
An important prerequisite for the reliability and robustness of a service robot is ensuring the robot’s correct behavior when it performs various tasks of interest. Extensive testing is one established approach for ensuring behavioural correctness; this becomes even more important with the integration of learning-based methods into robot software architectures, as there are often no theoretical guarantees about the performance of such methods in varying scenarios. In this paper, we aim towards evaluating the correctness of robot behaviors in tabletop manipulation through automatic generation of simulated test scenarios in which a robot assesses its performance using property-based testing. In particular, key properties of interest for various robot actions are encoded in an action ontology and are then verified and validated within a simulated environment. We evaluate our framework with a Toyota Human Support Robot (HSR) which is tested in a Gazebo simulation. We show that our framework can correctly and consistently identify various failed actions in a variety of randomised tabletop manipulation scenarios, in addition to providing deeper insights into the type and location of failures for each designed property.
Execution monitoring is essential for robots to detect and respond to failures. Since it is impossible to enumerate all failures for a given task, we learn from successful executions of the task to detect visual anomalies during runtime. Our method learns to predict the motions that occur during the nominal execution of a task, including camera and robot body motion. A probabilistic U-Net architecture is used to learn to predict optical flow, and the robot's kinematics and 3D model are used to model camera and body motion. The errors between the observed and predicted motion are used to calculate an anomaly score. We evaluate our method on a dataset of a robot placing a book on a shelf, which includes anomalies such as falling books, camera occlusions, and robot disturbances. We find that modeling camera and body motion, in addition to the learning-based optical flow prediction, results in an improvement of the area under the receiver operating characteristic curve from 0.752 to 0.804, and the area under the precision-recall curve from 0.467 to 0.549.
New cars are increasingly "connected" by default. Since not having a car is not an option for many people, understanding the privacy implications of driving connected cars and using their data-based services is an even more pressing issue than for expendable consumer products. While risk-based approaches to privacy are well established in law, they have only begun to gain traction in HCI. These approaches are understood not only to increase acceptance but also to help consumers make choices that meet their needs. To the best of our knowledge, perceived risks in the context of connected cars have not been studied before. To address this gap, our study reports on the analysis of a survey with 18 open-ended questions distributed to 1,000 households in a medium-sized German city. Our findings provide qualitative insights into existing attitudes and use cases of connected car features and, most importantly, a list of perceived risks themselves. Taking the perspective of consumers, we argue that these can help inform consumers about data use in connected cars in a user-friendly way. Finally, we show how these risks fit into and extend existing risk taxonomies from other contexts with a stronger social perspective on risks of data use.
Representation and Experience-Based Learning of Explainable Models for Robot Action Execution
(2021)
For robots acting in human-centered environments, the ability to improve based on experience is essential for reliable and adaptive operation; however, particularly in the context of robot failure analysis, experience-based improvement is only useful if robots are also able to reason about and explain the decisions they make during execution. In this paper, we describe and analyse a representation of execution-specific knowledge that combines (i) a relational model in the form of qualitative attributes that describe the conditions under which actions can be executed successfully and (ii) a continuous model in the form of a Gaussian process that can be used for generating parameters for action execution, but also for evaluating the expected execution success given a particular action parameterisation. The proposed representation is based on prior, modelled knowledge about actions and is combined with a learning process that is supervised by a teacher. We analyse the benefits of this representation in the context of two actions – grasping handles and pulling an object on a table – such that the experiments demonstrate that the joint relational-continuous model allows a robot to improve its execution based on experience, while reducing the severity of failures experienced during execution.
We consider multi-solution optimization and generative models for the generation of diverse artifacts and the discovery of novel solutions. In cases where the domain's factors of variation are unknown or too complex to encode manually, generative models can provide a learned latent space to approximate these factors. When used as a search space, however, the range and diversity of possible outputs are limited to the expressivity and generative capabilities of the learned model. We compare the output diversity of a quality diversity evolutionary search performed in two different search spaces: 1) a predefined parameterized space and 2) the latent space of a variational autoencoder model. We find that the search on an explicit parametric encoding creates more diverse artifact sets than searching the latent space. A learned model is better at interpolating between known data points than at extrapolating or expanding towards unseen examples. We recommend using a generative model's latent space primarily to measure similarity between artifacts rather than for search and generation. Whenever a parametric encoding is obtainable, it should be preferred over a learned representation as it produces a higher diversity of solutions.