The 10 most recently reported publications
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.
