Refine
Department, Institute
- Fachbereich Informatik (889) (remove)
Document Type
- Conference Object (507)
- Article (184)
- Report (70)
- Part of a Book (42)
- Book (27)
- Preprint (22)
- Conference Proceedings (15)
- Doctoral Thesis (8)
- Master's Thesis (5)
- Research Dataset (3)
Year of publication
Language
- English (750)
- German (134)
- Multiple languages (4)
- No linguistic content (1)
Keywords
- Virtual Reality (9)
- Robotics (7)
- Lehrbuch (6)
- Navigation (6)
- Robotik (6)
- Virtual reality (6)
- 3D user interface (5)
- robotics (5)
- virtual reality (5)
- ARRs (4)
An internal model of self-motion provides a fundamental basis for action in our daily lives, yet little is known about its development. The ability to control self-motion develops in youth and often deteriorates with advanced age. Self-motion generates relative motion between the viewer and the environment. Thus, the smoothness of the visual motion created will vary as control improves. Here, we study the influence of the smoothness of visually simulated self-motion on an observer's ability to judge how far they have travelled over a wide range of ages. Previous studies were typically highly controlled and concentrated on university students. But are such populations representative of the general public? And are there developmental and sex effects? Here, estimates of distance travelled (visual odometry) during visually induced self-motion were obtained from 466 participants drawn from visitors to a public science museum. Participants were presented with visual motion that simulated forward linear self-motion through a field of lollipops using a head-mounted virtual reality display. They judged the distance of their simulated motion by indicating when they had reached the position of a previously presented target. The simulated visual motion was presented with or without horizontal or vertical sinusoidal jitter. Participants' responses indicated that they felt they travelled further in the presence of vertical jitter. The effectiveness of the display increased with age over all jitter conditions. The estimated time for participants to feel that they had started to move also increased slightly with age. There were no differences between the sexes. These results suggest that age should be taken into account when generating motion in a virtual reality environment. Citizen science studies like this can provide a unique and valuable insight into perceptual processes in a truly representative sample of people.
OSC data
(2020)
Optimization plays an essential role in industrial design, but is not limited to minimization of a simple function, such as cost or strength. These tools are also used in conceptual phases, to better understand what is possible. To support this exploration we focus on Quality Diversity (QD) algorithms, which produce sets of varied, high performing solutions. These techniques often require the evaluation of millions of solutions -- making them impractical in design cases. In this thesis we propose methods to radically improve the data-efficiency of QD with machine learning, enabling its application to design. In our first contribution, we develop a method of modeling the performance of evolved neural networks used for control and design. The structures of these networks grow and change, making them difficult to model -- but with a new method we are able to estimate their performance based on their heredity, improving data-efficiency by several times. In our second contribution we combine model-based optimization with MAP-Elites, a QD algorithm. A model of performance is created from known designs, and MAP-Elites creates a new set of designs using this approximation. A subset of these designs are the evaluated to improve the model, and the process repeats. We show that this approach improves the efficiency of MAP-Elites by orders of magnitude. Our third contribution integrates generative models into MAP-Elites to learn domain specific encodings. A variational autoencoder is trained on the solutions produced by MAP-Elites, capturing the common “recipe” for high performance. This learned encoding can then be reused by other algorithms for rapid optimization, including MAP-Elites. Throughout this thesis, though the focus of our vision is design, we examine applications in other fields, such as robotics. These advances are not exclusive to design, but serve as foundational work on the integration of QD and machine learning.
Risk-based Authentication (RBA) is an adaptive security measure to strengthen password-based authentication. RBA monitors additional features during login, and when observed feature values differ significantly from previously seen ones, users have to provide additional authentication factors such as a verification code. RBA has the potential to offer more usable authentication, but the usability and the security perceptions of RBA are not studied well.
We present the results of a between-group lab study (n=65) to evaluate usability and security perceptions of two RBA variants, one 2FA variant, and password-only authentication. Our study shows with significant results that RBA is considered to be more usable than the studied 2FA variants, while it is perceived as more secure than password-only authentication in general and comparably secure to 2FA in a variety of application types. We also observed RBA usability problems and provide recommendations for mitigation. Our contribution provides a first deeper understanding of the users' perception of RBA and helps to improve RBA implementations for a broader user acceptance.
When a robotic agent experiences a failure while acting in the world, it should be possible to discover why that failure has occurred, namely to diagnose the failure. In this paper, we argue that the diagnosability of robot actions, at least in a classical sense, is a feature that cannot be taken for granted since it strongly depends on the underlying action representation. We specifically define criteria that determine the diagnosability of robot actions. The diagnosability question is then analysed in the context of a handle manipulation action, such that we discuss two different representations of the action – a composite policy with a learned success model for the action parameters, and a neural network-based monolithic policy – both of which exist on different sides of the diagnosability spectrum. Through this comparison, we conclude that composite actions are more suited to explicit diagnosis, but representations with less prior knowledge are more flexible. This suggests that model learning may provide balance between flexibility and diagnosability; however, data-driven diagnosis methods also need to be enhanced in order to deal with the complexity of modern robots.
Comparing Non-Visual and Visual Guidance Methods for Narrow Field of View Augmented Reality Displays
(2020)
Current augmented reality displays still have a very limited field of view compared to the human vision. In order to localize out-of-view objects, researchers have predominantly explored visual guidance approaches to visualize information in the limited (in-view) screen space. Unfortunately, visual conflicts like cluttering or occlusion of information often arise, which can lead to search performance issues and a decreased awareness about the physical environment. In this paper, we compare an innovative non-visual guidance approach based on audio-tactile cues with the state-of-the-art visual guidance technique EyeSee360 for localizing out-of-view objects in augmented reality displays with limited field of view. In our user study, we evaluate both guidance methods in terms of search performance and situation awareness. We show that although audio-tactile guidance is generally slower than the well-performing EyeSee360 in terms of search times, it is on a par regarding the hit rate. Even more so, the audio-tactile method provides a significant improvement in situation awareness compared to the visual approach.
Flying in virtual reality (VR) using standard handheld controllers can be cumbersome and contribute to unwanted side effects such as motion sickness and disorientation. This paper investigates a novel hands-free flying interface - HeadJoystick, where the user moves their head similar to a joystick handle toward the target direction to control virtual translation velocity. The user sits on a regular office swivel chair and rotates it physically to control virtual rotation using 1:1 mapping. We evaluated short-term (Study 1) and extended usage effects through repeated usage (Study 2) of the HeadJoystick versus handheld interfaces in two within-subject studies, where participants flew through a sequence of increasingly difficult tunnels in the sky. Using the HeadJoystick instead of handheld interfaces improved both user experience and performance, in terms of accuracy, precision, ease of learning, ease of use, usability, long-term use, presence, immersion, sensation of self-motion, workload, and enjoyment in both studies. These findings demonstrate the benefits of using leaning-based interfaces for VR flying and potentially similar telepresence applications such as remote flight with quadcopter drones. From a theoretical perspective, we also show how leaning-based motion cueing interacts with full physical rotation to improve user experience and performance compared to the gamepad.
Gone But Not Forgotten: Evaluating Performance and Scalability of Real-Time Mesoscopic Agents
(2020)
Telepresence robots allow people to participate in remote spaces, yet they can be difficult to manoeuvre with people and obstacles around. We designed a haptic-feedback system called “FeetBack," which users place their feet in when driving a telepresence robot. When the robot approaches people or obstacles, haptic proximity and collision feedback are provided on the respective sides of the feet, helping inform users about events that are hard to notice through the robot’s camera views. We conducted two studies: one to explore the usage of FeetBack in virtual environments, another focused on real environments.We found that FeetBack can increase spatial presence in simple virtual environments. Users valued the feedback to adjust their behaviour in both types of environments, though it was sometimes too frequent or unneeded for certain situations after a period of time. These results point to the value of foot-based haptic feedback for telepresence robot systems, while also the need to design context-sensitive haptic feedback.
Navigation of Unmanned Ground Vehicles (UGV) in unknown environments is an active area of research for mobile robotics. A main hindering factor for UGV navigation is the limited range of the on-board sensors that process only restricted areas of the environment at a time. In addition, most existing approaches process sensor information under the assumption of a static environment. This restrains the exploration capability of the UGV especially in time-critical applications such as search and rescue. The cooperation with an Unmanned Aerial Vehicle (UAV) can provide the UGV with an extended perspective of the environment which enables a better-suited path planning solution that can be adjusted on demand. In this work, we propose a UAV-UGV cooperative path planning approach for dynamic environments by performing semantic segmentation on images acquired from the UAV's view via a deep neural network. The approach is evaluated in a car park scenario, with the goal of providing a path plan to an empty parking space for a ground-based vehicle. The experiments were performed on a created dataset of real-world car park images located in Croatia and Germany, in addition to images from a simulated environment. The segmentation results demonstrate the viability of the proposed approach in producing maps of the dynamic environment on demand and accordingly generating path plans for ground-based vehicles.
Damage to grasslands is mainly caused by wild boar during foraging. Farmers in Germany thereby register yield losses and expenses for damage repair. This contribution analyzes the acquisition and processing of aerial images to orthomosaics and image segmentation to perform spatial measurements of damaged patches in grasslands. A sample set of manually annotated orthomosaics is analyzed. Preliminary classification results applying a convolutional neural network approach to segment damaged patches are presented. First results show the applicability of the applied methods in the detection of damage caused by wild boar and suggest that other damage causes (e.g., mole damage) should be considered to improve results.
This paper utilizes machine learning to investigate the classification of encryption applied to network traffic and the underlying activities. It is firstly motivated by the difficulty of traditional traffic classification caused by additional encryption as ports and headers are hidden. Secondly, the results also present the effectiveness of currently available privacy-enhancing technologies. A new dataset is created, containing Pure (without additional encryption), Tor, Tor with obfuscation, VPN and VPN+Tor network traffic. Additionally, there are five different activities performed during each kind of traffic recording, namely audio streaming, browsing, P2P/SFTP file transfers and video conferencing. The traffic is classified by extracting features based on flows calculated by ARGUS and CICFlowMeter, combining three classifiers with seven feature selection algorithms. The results for the classification of the encryption clearly indicate the possibility of using this detection system in a modified fashion within a practical application. For the detection of activities inside encrypted network traffic, the results show that the disguise is ineffective. Overall, this reveals the need to improve the resistance of commonly used techniques for the protection of network traffic against machine learning.
Graph drawing with spring embedders employs a V ×V computation phase over the graph’s vertex set to compute repulsive forces. Here, the efficacy of forces diminishes with distance: a vertex can effectively only influence other vertices in a certain radius around its position. Therefore, the algorithm lends itself to an implementation using search data structures to reduce the runtime complexity. NVIDIA RT cores implement hierarchical tree traversal in hardware. We show how to map the problem of finding graph layouts with force-directed methods to a ray tracing problem that can subsequently be implemented with dedicated ray tracing hardware. With that, we observe speedups of 4× to 13× over a CUDA software implementation.
A Comparative Study of Uncertainty Estimation Methods in Deep Learning Based Classification Models
(2020)
Deep learning models produce overconfident predictions even for misclassified data. This work aims to improve the safety guarantees of software-intensive systems that use deep learning based classification models for decision making by performing comparative evaluation of different uncertainty estimation methods to identify possible misclassifications.
In this work, uncertainty estimation methods applicable to deep learning models are reviewed and those which can be seamlessly integrated to existing deployed deep learning architectures are selected for evaluation. The different uncertainty estimation methods, deep ensembles, test-time data augmentation and Monte Carlo dropout with its variants, are empirically evaluated on two standard datasets (CIFAR-10 and CIFAR-100) and two custom classification datasets (optical inspection and RoboCup@Work dataset). A relative ranking between the methods is provided by evaluating the deep learning classifiers on various aspects such as uncertainty quality, classifier performance and calibration. Standard metrics like entropy, cross-entropy, mutual information, and variance, combined with a rank histogram based method to identify uncertain predictions by thresholding on these metrics, are used to evaluate uncertainty quality.
The results indicate that Monte Carlo dropout combined with test-time data augmentation outperforms all other methods by identifying more than 95% of the misclassifications and representing uncertainty in the highest number of samples in the test set. It also yields a better classifier performance and calibration in terms of higher accuracy and lower Expected Calibration Error (ECE), respectively. A python based uncertainty estimation library for training and real-time uncertainty estimation of deep learning based classification models is also developed.
We have designed an inexpensive intelligent pedestrian counting system. The pedestrian counting system consists of several counters that can be connected together in a distributed fashion and communicate over the wireless channel. The motion pattern is recorded using a set of passive infrared (PIR) sensors. Each counter has one wireless sensor node that processes the PIR sensor data and transmits it to a base station. Then echo state network, a special kind of recurrent neural network, is used to predict the pedestrian count from the input pattern. The evaluation of the performance of such networks in a novel kind of application is one focus of this work. The counter gave a performance of 80.4% which is better than the commercially available low-priced pedestrian counters. The article reports the experiments we did for analyzing the counterperformance and lists the strengths and limitations of the current implementation. It will also report the preliminary test results obtained by substituting the PIR sensors with low-cost active IR distance sensors which can improve the counter performance further.
Human and robot tasks in household environments include actions such as carrying an object, cleaning a surface, etc. These tasks are performed by means of dexterous manipulation, and for humans, they are straightforward to accomplish. Moreover, humans perform these actions with reasonable accuracy and precision but with much less energy and stress on the actuators (muscles) than the robots do. The high agility in controlling their forces and motions is actually due to "laziness", i.e. humans exploit the existing natural forces and constraints to execute the tasks.
The above-mentioned properties of the human lazy strategy motivate us to relax the problem of controlling robot motions and forces, and solve it with the help of the environment. Therefore, in this work, we developed a lazy control strategy, i.e. task specification models and control architectures that relax several aspects of robot control by exploiting prior knowledge about the task and environment. The developed control strategy is realized in four different robotics use cases. In this work, the Popov-Vereshchagin hybrid dynamics solver is used as one of the building blocks in the proposed control architectures. An extension of the solver’s interface with the artificial Cartesian force and feed-forward joint torque task-drivers is proposed in this thesis.
To validate the proposed lazy control approach, an experimental evaluation was performed in a simulation environment and on a real robot platform.
Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading
(2020)
Automatic Short Answer Grading (ASAG) is the process of grading the student answers by computational approaches given a question and the desired answer. Previous works implemented the methods of concept mapping, facet mapping, and some used the conventional word embeddings for extracting semantic features. They extracted multiple features manually to train on the corresponding datasets. We use pretrained embeddings of the transfer learning models, ELMo, BERT, GPT, and GPT-2 to assess their efficiency on this task. We train with a single feature, cosine similarity, extracted from the embeddings of these models. We compare the RMSE scores and correlation measurements of the four models with previous works on Mohler dataset. Our work demonstrates that ELMo outperformed the other three models. We also, briefly describe the four transfer learning models and conclude with the possible causes of poor results of transfer learning models.
Graph drawing with spring embedders employs a V x V computation phase over the graph's vertex set to compute repulsive forces. Here, the efficacy of forces diminishes with distance: a vertex can effectively only influence other vertices in a certain radius around its position. Therefore, the algorithm lends itself to an implementation using search data structures to reduce the runtime complexity. NVIDIA RT cores implement hierarchical tree traversal in hardware. We show how to map the problem of finding graph layouts with force-directed methods to a ray tracing problem that can subsequently be implemented with dedicated ray tracing hardware. With that, we observe speedups of 4x to 13x over a CUDA software implementation.
Bei der sechsten Ausgabe des wissenschaftlichen Workshops ”Usable Security und Privacy” auf der Mensch und Computer 2020 werden wie in den vergangenen Jahren aktuelle Forschungs- und Praxisbeiträge präsentiert und anschließend mit allen Teilnehmenden diskutiert. Drei Beiträge befassen sich dieses Jahr mit dem Thema Privatsphäre, einer 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.
