Refine
H-BRS Bibliography
- yes (80)
Departments, institutes and facilities
- Fachbereich Informatik (80) (remove)
Document Type
- Conference Object (38)
- Article (19)
- Preprint (7)
- Doctoral Thesis (4)
- Part of a Book (3)
- Research Data (3)
- Report (3)
- Book (monograph, edited volume) (1)
- Conference Proceedings (1)
- Contribution to a Periodical (1)
Year of publication
- 2021 (80) (remove)
Keywords
- Usable Security (4)
- Big Data Analysis (3)
- Machine Learning (3)
- AML (2)
- Augmented Reality (2)
- Authentication features (2)
- Cognitive robot control (2)
- Explainable robotics (2)
- Generative Models (2)
- HSP90 (2)
- Human-Computer Interaction (2)
- Learning from experience (2)
- LoRa (2)
- LoRaWAN (2)
- Low-Power Wide Area Network (LP-WAN) (2)
- Measurement (2)
- Path Loss (2)
- Quality diversity (2)
- Risk-based Authentication (RBA) (2)
- Robotics (2)
- Urban (2)
- 3D navigation (1)
- AD (1)
- AES (1)
- API Documentation (1)
- API Gebrauchstauglichkeit (1)
- API usability (1)
- Adaptive Control (1)
- Artificial Intelligence (1)
- Assistive robots (1)
- Auditory Cueing (1)
- BPMS (1)
- Benchmarking (1)
- Bioinformatics (1)
- Block cipher (1)
- Bond Graph Modelling (1)
- Branch and cut (1)
- CC (1)
- CEHL (1)
- Cache line fingerprinting (1)
- Classifiers (1)
- Clustering (1)
- Co-creative processes (1)
- Cognitive informatics (1)
- Cognitive robotics (1)
- Compliant fingers (1)
- Computational creativity (1)
- Computing methodologies (1)
- Content Security Policies (1)
- Continual robot learning (1)
- Correlative Microscopy (1)
- Cortex-M3 (1)
- Creative Commons (1)
- DPA (1)
- Datenbanksysteme (1)
- Developer Centered Security (1)
- Differential analysis (1)
- Digitale Lehre (1)
- Dimensionality reduction (1)
- Divergent optimization (1)
- Drug (1)
- E-Health (1)
- ELM (1)
- Earth Observation (1)
- Employee data protection (1)
- Evolutionary optimization (1)
- Explainable Machine Learning (1)
- Failure Prognosis (1)
- Fault Detection & Diagnosis (1)
- Fault Diagnosis (1)
- Feature extraction (1)
- Fluency (1)
- Foveated rendering (1)
- GDPR (1)
- GLI (1)
- Gabor filter (1)
- Global illumination (1)
- HSP70 (1)
- HTTP (1)
- Head-mounted Display (1)
- Header whitelisting (1)
- Heat Shock Protein (1)
- Hochleistungssport (1)
- Hochschullehre (1)
- Human centered computing (1)
- Human computer interaction (1)
- Human factors (1)
- Hybrid Failure Prognosis (1)
- Hybrid Systems (1)
- Hyperspectral image (1)
- Inductive Logic Programming (1)
- Informationsflüsse (1)
- Informationsgewinnung (1)
- Informationsverarbeitung (1)
- Integer programming (1)
- Intelligent Autonomous Systems (1)
- Intermediaries (1)
- Knowledge Graphs (1)
- Künstliche Intelligenz (1)
- Language learning (1)
- Large high-resolution displays (1)
- Leistungsdiagnostik (1)
- Leistungssport (1)
- Leukemia (1)
- MBZ (1)
- Machine-learning (1)
- Mebendazole (1)
- Memory-Constrained Devices (1)
- Methodik (1)
- Microarchitectural Data Sampling (MDS) (1)
- Mixed (1)
- Model-based Fault Diagnosis (1)
- Modelling (1)
- Molecular dynamics (1)
- Multimodal Microspectroscopy (1)
- NISTPQC (1)
- Natural Language Processing (1)
- OER (1)
- Object detection (1)
- Ontology (1)
- Open Educational Ressources (1)
- Out-of-view Objects (1)
- PDSTSP (1)
- PHR (1)
- Parallel drone scheduling traveling salesman problem (1)
- Password (1)
- Personal Health Record (1)
- Post-Quantum Signatures (1)
- Privacy engineering (1)
- Process Models (1)
- Process views (1)
- Pronunciation (1)
- QoS (1)
- Quality control (1)
- Quantum mechanics (1)
- Radiance caching (1)
- Reflectance modeling (1)
- Registration Refinement (1)
- Risk-based Authentication (1)
- Robot failure diagnosis (1)
- Robot learning (1)
- Robot software (1)
- Robotics competitions (1)
- Robust grasping (1)
- SAML (1)
- SOAP (1)
- SVM (1)
- Secure Coding Practices (1)
- Semantic gap (1)
- Separation algorithm (1)
- Sicherheits-APIs (1)
- Side channel attack (1)
- Signature Verification (1)
- Slippage detection (1)
- Smartphone (1)
- Softwareentwicklung (1)
- Spielanalyse (1)
- Streaming (1)
- Support Vector Machine (1)
- Surrogate-assistance (1)
- Synergetik (1)
- Tautomers (1)
- Touchscreens (1)
- Trainingssteuerung (1)
- Transformers (1)
- Unidirectional thermoplastic composites (1)
- Usable Privacy (1)
- Usable Security and Privacy (1)
- User interface (1)
- Variational Autoencoder (1)
- Virtual Reality (1)
- Virtual reality (1)
- Visual Cueing (1)
- Visual Discrimination (1)
- Visualization design and evaluation methods (1)
- Visualization systems and tools (1)
- Web (1)
- Wettkampfanalyse (1)
- XML Signature (1)
- XML Signature Wrapping (1)
- YAWL (1)
- ZombieLoad (1)
- architectural distortion (1)
- breast cancer (1)
- component based (1)
- convolutional neural networks (1)
- developer centered security (1)
- domain adaptation (1)
- entwicklerzentrierte Sicherheit (1)
- extreme learning machine (1)
- indicators calculation (1)
- information flows (1)
- informational self-determination (1)
- leaning-based interfaces (1)
- learning traces (1)
- locomotion interface (1)
- mebendazole (1)
- mental models (1)
- multi robot systems (1)
- navigational search (1)
- privacy at work (1)
- property-based testing for robots (1)
- reuse of indicators (1)
- security (1)
- security APIs (1)
- simulation-based robot testing (1)
- software development (1)
- spatial orientation (1)
- spatial updating (1)
- trace model (1)
- trace-based system (1)
- transfer learning (1)
- unsupervised learning (1)
- usable privacy controls (1)
- verification and validation of robot action execution (1)
- virtual reality (1)
Auch die mittlerweile siebte Ausgabe des wissenschaftlichen Workshops “Usable Security und Privacy” auf der Mensch und Computer 2021 wird aktuelle Forschungs- und Praxisbeiträge präsentiert und anschließend mit allen Teilnehmer:innen diskutiert. Zwei Beiträge befassen sich dieses Jahr mit dem Thema Privatsphäre, zwei mit dem Thema Sicherheit. Mit dem Workshop wird ein etabliertes Forum fortgeführt und weiterentwickelt, in dem sich Expert:innen aus unterschiedlichen Domänen, z. B. dem Usability- und Security- Engineering, transdisziplinär austauschen können.
Künstliche Intelligenz (KI) ist aus der heutigen Gesellschaft kaum noch wegzudenken. Auch im Sport haben Methoden der KI in den letzten Jahren mehr und mehr Einzug gehalten. Ob und inwieweit dabei allerdings die derzeitigen Potenziale der KI tatsächlich ausgeschöpft werden, ist bislang nicht untersucht worden. Der Nutzen von Methoden der KI im Sport ist unbestritten, jedoch treten bei der Umsetzung in die Praxis gravierende Probleme auf, was den Zugang zu Ressourcen, die Verfügbarkeit von Experten und den Umgang mit den Methoden und Daten betrifft. Die Ursache für die, verglichen mit anderen Anwendungsgebieten, langsame An- bzw. Übernahme von Methoden der KI in den Spitzensport ist nach Hypothese des Autorenteams auf mehrere Mismatches zwischen dem Anwendungsfeld und den KI-Methoden zurückzuführen. Diese Mismatches sind methodischer, struktureller und auch kommunikativer Art. In der vorliegenden Expertise werden Vorschläge abgeleitet, die zur Auflösung der Mismatches führen können und zugleich neue Transfer- und Synergiemöglichkeiten aufzeigen. Außerdem wurden drei Use Cases zu Trainingssteuerung, Leistungsdiagnostik und Wettkampfdiagnostik exemplarisch umgesetzt. Dies erfolgte in Form entsprechender Projektbeschreibungen. Dabei zeigt die Ausarbeitung, auf welche Art und Weise Probleme, die heute noch bei der Verbindung zwischen KI und Sport bestehen, möglichst ausgeräumt werden können. Eine empirische Umsetzung des Use Case Trainingssteuerung erfolgte im Radsport, weshalb dieser ausführlicher dargestellt wird.
Short summary
Accompanying dataset for our paper
A. Mitrevski, P. G. Plöger, and G. Lakemeyer, "Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models," in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2021.
Contents
The dataset includes a single zip archive, containing data from the experiment described in the paper (conducted with a Toyota HSR). The zip archive contains three subdirectories:
handle_grasping_failure_database: A dump of a MongoDB database containing data from the handle grasping experiment, including ground-truth grasping failure annotations
pre_arm_motion_images: Images collected from the robot's hand camera before moving the robot's hand towards the handle
pregrasp_images: Images collected from the robot's hand camera just before closing the gripper for grasping
The image names include the time stamp at which the images were taken; this allows matching each image with the execution data in the database.
Database usage
After unzipping the archive, the database can be restored with the command
mongorestore handle_grasping_failure_database
This will create a MongoDB database with the name drawer_handle_grasping_failures.
Code for processing the data and failure analysis can be found in our <a href="https://github.com/alex-mitrevski/explainable-robot-execution-models">GitHub repository.
The dataset contains the following data from successful and failed executions of the Toyota HSR robot placing a book on a shelf.
RGB images from the robot's head camera
Depth images from the robot's head camera
Rendered images of the robot's 3D model from the point of view of the robot's head camera
Force-torque readings from a wrist-mounted force-torque sensor
Joint efforts, velocities and positions
extrinsic and intrinsic camera calibration parameters
frame-level anomaly annotations
The anomalies that occur during execution include:
the manipulated book falling down
books on the shelf being disturbed significantly
camera occlusions
robot being disturbed by an external collision
The dataset is split into a train, validation and test set with the following number of trials:
Train: 48 successful trials
Validation: 6 successful trials
Test: 60 anomalous trials and 7 successful trials
Contents
There are two zip archives included (grasping.zip and throwing.zip), corresponding to two experiments (grasping objects and throwing them in a drawer), both performed with a Toyota HSR. Each archive contains two directories - learning and generalisation - with object-specific learning and generalisation data. For each object, we provide a dump of a MongoDB database, which contains data sufficient for learning the models used in our experiments.
Usage
After unzipping the archives, each database can be restored with the command
mongorestore [data_directory_name]
This will create a MongoDB database with the name of the directory. Code for processing the data and model learning can be found in our <a href="https://github.com/alex-mitrevski/explainable-robot-execution-models">GitHub repository.
In Robot-Assisted Therapy for children with Autism Spectrum Disorder, the therapists’ workload is increased due to the necessity of controlling the robot manually. The solution for this problem is to increase the level of autonomy of the system, namely the robot should interpret and adapt to the behaviour of the child under therapy. The problem that we are adressing is to develop a behaviour model that will be used for the robot decision-making process, which will learn how to adequately react to certain child reactions. We propose the use of the reinforcement learning technique for this task, where feedback for learning is obtained from the therapist’s evaluation of a robot’s behaviour.
In this thesis it is posed that the central object of preference discovery is a co-creative process in which the Other can be represented by a machine. It explores efficient methods to enhance introverted intuition using extraverted intuition's communication lines. Possible implementations of such processes are presented using novel algorithms that perform divergent search to feed the users' intuition with many examples of high quality solutions, allowing them to take influence interactively. The machine feeds and reflects upon human intuition, combining both what is possible and preferred. The machine model and the divergent optimization algorithms are the motor behind this co-creative process, in which machine and users co-create and interactively choose branches of an ad hoc hierarchical decomposition of the solution space.
The proposed co-creative process consists of several elements: a formal model for interactive co-creative processes, evolutionary divergent search, diversity and similarity, data-driven methods to discover diversity, limitations of artificial creative agents, matters of efficiency in behavioral and morphological modeling, visualization, a connection to prototype theory, and methods to allow users to influence artificial creative agents. This thesis helps putting the human back into the design loop in generative AI and optimization.
Object-Based Trace Model for Automatic Indicator Computation in the Human Learning Environments
(2021)
This paper proposes a traces model in the form of an object or class model (in the UML sense) which allows the automatic calculation of indicators of various kinds and independently of the computer environment for human learning (CEHL). The model is based on the establishment of a trace-based system that encompasses all the logic of traces collecting and indicators calculation. It is im-plemented in the form of a trace database. It is an important contribution in the field of the exploitation of the traces of apprenticeship in a CEHL because it pro-vides a general formalism for modeling the traces and allowing the calculation of several indicators at the same time. Also, with the inclusion of calculated indica-tors as potential learning traces, our model provides a formalism for classifying the various indicators in the form of inheritance relationships, which promotes the reuse of indicators already calculated. Economically, the model can allow organi-zations with different learning platforms to invest only in one traces Management System. At the social level, it can allow a better sharing of trace databases be-tween the various research institutions in the field of CEHL.
Die Blockchain-Technologie ist einer der großen Innovationstreiber der letzten Jahre. Mit einer zugrundeliegenden Blockchain-Technologie ist auch der Betrieb von verteilten Anwendungen, sogenannter Decentralized Applications (DApps), bereits technisch umsetzbar. Dieser Beitrag verfolgt das Ziel, Gestaltungsmöglichkeiten der digitalen Verbraucherteilhabe an Blockchain-Anwendungen zu untersuchen. Hierzu enthält der Beitrag eine Einführung in die digitale Verbraucherteilhabe und die technischen Grundlagen und Eigenschaften der Blockchain-Technologie, einschließlich darauf basierender DApps. Abschließend werden technische, ethisch-organisatorische, rechtliche und sonstige Anforderungsbereiche für die Umsetzung von digitaler Verbraucherteilhabe in Blockchain-Anwendungen adressiert.
Risk-based authentication (RBA) aims to strengthen password-based authentication rather than replacing it. RBA does this by monitoring and recording additional features during the login process. If feature values at login time differ significantly from those observed before, RBA requests an additional proof of identification. Although RBA is recommended in the NIST digital identity guidelines, it has so far been used almost exclusively by major online services. This is partly due to a lack of open knowledge and implementations that would allow any service provider to roll out RBA protection to its users. To close this gap, we provide a first in-depth analysis of RBA characteristics in a practical deployment. We observed N=780 users with 247 unique features on a real-world online service for over 1.8 years. Based on our collected data set, we provide (i) a behavior analysis of two RBA implementations that were apparently used by major online services in the wild, (ii) a benchmark of the features to extract a subset that is most suitable for RBA use, (iii) a new feature that has not been used in RBA before, and (iv) factors which have a significant effect on RBA performance. Our results show that RBA needs to be carefully tailored to each online service, as even small configuration adjustments can greatly impact RBA's security and usability properties. We provide insights on the selection of features, their weightings, and the risk classification in order to benefit from RBA after a minimum number of login attempts.
Low-Cost In-Hand Slippage Detection and Avoidance for Robust Robotic Grasping with Compliant Fingers
(2021)
Mebendazole Mediates Proteasomal Degradation of GLI Transcription Factors in Acute Myeloid Leukemia
(2021)
The prognosis of elderly AML patients is still poor due to chemotherapy resistance. The Hedgehog (HH) pathway is important for leukemic transformation because of aberrant activation of GLI transcription factors. MBZ is a well-tolerated anthelmintic that exhibits strong antitumor effects. Herein, we show that MBZ induced strong, dose-dependent anti-leukemic effects on AML cells, including the sensitization of AML cells to chemotherapy with cytarabine. MBZ strongly reduced intracellular protein levels of GLI1/GLI2 transcription factors. Consequently, MBZ reduced the GLI promoter activity as observed in luciferase-based reporter assays in AML cell lines. Further analysis revealed that MBZ mediates its anti-leukemic effects by promoting the proteasomal degradation of GLI transcription factors via inhibition of HSP70/90 chaperone activity. Extensive molecular dynamics simulations were performed on the MBZ-HSP90 complex, showing a stable binding interaction at the ATP binding site. Importantly, two patients with refractory AML were treated with MBZ in an off-label setting and MBZ effectively reduced the GLI signaling activity in a modified plasma inhibitory assay, resulting in a decrease in peripheral blood blast counts in one patient. Our data prove that MBZ is an effective GLI inhibitor that should be evaluated in combination to conventional chemotherapy in the clinical setting.
It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link to the github repository of this report can be found here: https://github.com/agrija9/Deep-Unsupervised-Domain-Adaptation.
Recent experimental evidence suggest that mebendazole, a popular antiparasitic drug, binds to heat shock protein 90 (Hsp90) and inhibit acute myeloid leukemia cell growth. In this study we use quantum mechanics (QM), molecular similarity and molecular dynamics (MD) calculations to predict possible binding poses of mebendazole to the adenosine triphosphate (ATP) binding site of Hsp90. Extensive conformational searches and minimization of the five tautomers of mebendazole using MP2/aug-cc-pVTZ theory level resulting in 152 minima being identified. Mebendazole-Hsp90 complex models were created using the QM optimized conformations and protein coordinates obtained from experimental crystal structures that were chosen through similarity calculations. Nine different poses were identified from a total of 600 ns of explicit solvent, all-atom MD simulations using two different force fields. All simulations support the hypothesis that mebendazole is able to bind to the ATP binding site of Hsp90.
When users in virtual reality cannot physically walk and self-motions are instead only visually simulated, spatial updating is often impaired. In this paper, we report on a study that investigated if HeadJoystick, an embodied leaning-based flying interface, could improve performance in a 3D navigational search task that relies on maintaining situational awareness and spatial updating in VR. We compared it to Gamepad, a standard flying interface. For both interfaces, participants were seated on a swivel chair and controlled simulated rotations by physically rotating. They either leaned (forward/backward, right/left, up/down) or used the Gamepad thumbsticks for simulated translation. In a gamified 3D navigational search task, participants had to find eight balls within 5 min. Those balls were hidden amongst 16 randomly positioned boxes in a dark environment devoid of any landmarks. Compared to the Gamepad, participants collected more balls using the HeadJoystick. It also minimized the distance travelled, motion sickness, and mental task demand. Moreover, the HeadJoystick was rated better in terms of ease of use, controllability, learnability, overall usability, and self-motion perception. However, participants rated HeadJoystick could be more physically fatiguing after a long use. Overall, participants felt more engaged with HeadJoystick, enjoyed it more, and preferred it. Together, this provides evidence that leaning-based interfaces like HeadJoystick can provide an affordable and effective alternative for flying in VR and potentially telepresence drones.
Urban LoRa networks promise to provide a cost-efficient and scalable communication backbone for smart cities. One core challenge in rolling out and operating these networks is radio network planning, i.e., precise predictions about possible new locations and their impact on network coverage. Path loss models aid in this task, but evaluating and comparing different models requires a sufficiently large set of high-quality received packet power samples. In this paper, we report on a corresponding large-scale measurement study covering an urban area of 200km2 over a period of 230 days using sensors deployed on garbage trucks, resulting in more than 112 thousand high-quality samples for received packet power. Using this data, we compare eleven previously proposed path loss models and additionally provide new coefficients for the Log-distance model. Our results reveal that the Log-distance model and other well-known empirical models such as Okumura or Winner+ provide reasonable estimations in an urban environment, and terrain based models such as ITM or ITWOM have no advantages. In addition, we derive estimations for the needed sample size in similar measurement campaigns. To stimulate further research in this direction, we make all our data publicly available.
Designs for decorative surfaces, such as flooring, must cover several square meters to avoid visible repeats. While the use of desktop systems is feasible to support the designer, it is challenging for a non-domain expert to get the right impression of the appearances of surfaces due to limited display sizes and a potentially unnatural interaction with digital designs. At the same time, large-format editing of structure and gloss is becoming increasingly important. Advances in the printing industry allow for more faithful reproduction of such surface details. Unfortunately, existing systems for visualizing surface designs cannot adequately account for gloss, especially for non-domain experts. Here, the complex interaction of light sources and the camera position must be controlled using software controls. As a result, only small parts of the data set can be properly inspected at a time. Also, real-world lighting is not considered here. This work presents a system for the processing and realistic visualization of large decorative surface designs. To this end, we present a tabletop solution that is coupled to a live 360° video feed and a spatial tracking system. This allows for reproducing natural view-dependent effects like real-world reflections, live image-based lighting, and the interaction with the design using virtual light sources employing natural interaction techniques that allow for a more accurate inspection even for non-domain experts.
Risk-based authentication (RBA) extends authentication mechanisms to make them more robust against account takeover attacks, such as those using stolen passwords. RBA is recommended by NIST and NCSC to strengthen password-based authentication, and is already used by major online services. Also, users consider RBA to be more usable than two-factor authentication and just as secure. However, users currently obtain RBA's high security and usability benefits at the cost of exposing potentially sensitive personal data (e.g., IP address or browser information). This conflicts with user privacy and requires to consider user rights regarding the processing of personal data. We outline potential privacy challenges regarding different attacker models and propose improvements to balance privacy in RBA systems. To estimate the properties of the privacy-preserving RBA enhancements in practical environments, we evaluated a subset of them with long-term data from 780 users of a real-world online service. Our results show the potential to increase privacy in RBA solutions. However, it is limited to certain parameters that should guide RBA design to protect privacy. We outline research directions that need to be considered to achieve a widespread adoption of privacy preserving RBA with high user acceptance.
Components and Architecture for the Implementation of Technology-Driven Employee Data Protection
(2021)
In the field of service robots, dealing with faults is crucial to promote user acceptance. In this context, this work focuses on some specific faults which arise from the interaction of a robot with its real world environment due to insufficient knowledge for action execution. In our previous work [1], we have shown that such missing knowledge can be obtained through learning by experimentation. The combination of symbolic and geometric models allows us to represent action execution knowledge effectively. However we did not propose a suitable representation of the symbolic model. In this work we investigate such symbolic representation and evaluate its learning capability. The experimental analysis is performed on four use cases using four different learning paradigms. As a result, the symbolic representation together with the most suitable learning paradigm are identified.
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited. To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs. This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against two baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.083. Additionally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications. Finally, the source code and pre-trained STonKGs models are available at https://github.com/stonkgs/stonkgs and https://huggingface.co/stonkgs/stonkgs-150k.
Application of underwater robots are on the rise, most of them are dependent on sonar for underwater vision, but the lack of strong perception capabilities limits them in this task. An important issue in sonar perception is matching image patches, which can enable other techniques like localization, change detection, and mapping. There is a rich literature for this problem in color images, but for acoustic images, it is lacking, due to the physics that produce these images. In this paper we improve on our previous results for this problem (Valdenegro-Toro et al, 2017), instead of modeling features manually, a Convolutional Neural Network (CNN) learns a similarity function and predicts if two input sonar images are similar or not. With the objective of improving the sonar image matching problem further, three state of the art CNN architectures are evaluated on the Marine Debris dataset, namely DenseNet, and VGG, with a siamese or two-channel architecture, and contrastive loss. To ensure a fair evaluation of each network, thorough hyper-parameter optimization is executed. We find that the best performing models are DenseNet Two-Channel network with 0.955 AUC, VGG-Siamese with contrastive loss at 0.949 AUC and DenseNet Siamese with 0.921 AUC. By ensembling the top performing DenseNet two-channel and DenseNet-Siamese models overall highest prediction accuracy obtained is 0.978 AUC, showing a large improvement over the 0.91 AUC in the state of the art.
Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. Assuming a priori knowledge of the target domain, such grammars can be exploited to enforce syntactical constraints when predicting logical forms. To that end, we assess how syntactical parsers can be integrated into modern encoder-decoder frameworks. Specifically, we implement an attentional SEQ2SEQ model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. Compared to other approaches to grammar-guided decoding that modify the underlying neural network architecture or attempt to derive full parse trees, our approach is conceptually simpler, adds less computational overhead during inference and integrates seamlessly with current SEQ2SEQ frameworks. We present preliminary evaluation results against a recurrent SEQ2SEQ baseline on GEOQUERY and ATIS and demonstrate improved performance while enforcing grammatical constraints.
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.
A qualitative study of Machine Learning practices and engineering challenges in Earth Observation
(2021)
Machine Learning (ML) is ubiquitously on the advance. Like many domains, Earth Observation (EO) also increasingly relies on ML applications, where ML methods are applied to process vast amounts of heterogeneous and continuous data streams to answer socially and environmentally relevant questions. However, developing such ML- based EO systems remains challenging: Development processes and employed workflows are often barely structured and poorly reported. The application of ML methods and techniques is considered to be opaque and the lack of transparency is contradictory to the responsible development of ML-based EO applications. To improve this situation a better understanding of the current practices and engineering-related challenges in developing ML-based EO applications is required. In this paper, we report observations from an exploratory study where five experts shared their view on ML engineering in semi-structured interviews. We analysed these interviews with coding techniques as often applied in the domain of empirical software engineering. The interviews provide informative insights into the practical development of ML applications and reveal several engineering challenges. In addition, interviewees participated in a novel workflow sketching task, which provided a tangible reflection of implicit processes. Overall, the results confirm a gap between theoretical conceptions and real practices in ML development even though workflows were sketched abstractly as textbook-like. The results pave the way for a large-scale investigation on requirements for ML engineering in EO.
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.
Software developers build complex systems using plenty of third-party libraries. Documentation is key to understand and use the functionality provided via the libraries’ APIs. Therefore, functionality is the main focus of contemporary API documentation, while cross-cutting concerns such as security are almost never considered at all, especially when the API itself does not provide security features. Documentations of JavaScript libraries for use in web applications, e.g., do not specify how to add or adapt a Content Security Policy (CSP) to mitigate content injection attacks like Cross-Site Scripting (XSS). This is unfortunate, as security-relevant API documentation might have an influence on secure coding practices and prevailing major vulnerabilities such as XSS. For the first time, we study the effects of integrating security-relevant information in non-security API documentation. For this purpose, we took CSP as an exemplary study object and extended the official Google Maps JavaScript API documentation with security-relevant CSP information in three distinct manners. Then, we evaluated the usage of these variations in a between-group eye-tracking lab study involving N=49 participants. Our observations suggest: (1) Developers are focused on elements with code examples. They mostly skim the documentation while searching for a quick solution to their programming task. This finding gives further evidence to results of related studies. (2) The location where CSP-related code examples are placed in non-security API documentation significantly impacts the time it takes to find this security-relevant information. In particular, the study results showed that the proximity to functional-related code examples in documentation is a decisive factor. (3) Examples significantly help to produce secure CSP solutions. (4) Developers have additional information needs that our approach cannot meet.
Overall, our study contributes to a first understanding of the impact of security-relevant information in non-security API documentation on CSP implementation. Although further research is required, our findings emphasize that API producers should take responsibility for adequately documenting security aspects and thus supporting the sensibility and training of developers to implement secure systems. This responsibility also holds in seemingly non-security relevant contexts.
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.
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.