Hochschule Ruhr West
Not a member yet
812 research outputs found
Sort by
Analyse der Sensorabhängigkeit einer LiDAR-basierten Objekterkennung mit neuronalen Netzen
Get PDFThe task of object detection in the automotive sector can be performed by evaluating various
sensor data. The evaluation of LiDAR data for the detection of objects is a special challenge for
which systems with neural networks can be used. These neural networks are trained by means of a
data set. If you want to use the net with your own recordings or another data set, it is important
to know how well these systems work in combination with data from another sensor. This allows
the results to be estimated in advance and compared with the results of previous experiments.
In this work the sensor dependence of a LiDAR based object recognition with neural networks
will be analysed. The detector used in this work is PointRCNN [1], which was designed for the
KITTI dataset [2]. To check the sensor dependency, the ’AEV Autonomous Driving Dataset’
(A2D2) dataset [3] was selected as a further dataset. After an introduction to PointRCNN and its
functionality, the data of both datasets are analysed. Then the data of the second dataset will be
ported into the format of the KITTI dataset so that they can be used with PointRCNN. Through
experiments with varying combinations of training and validation data it shall be investigated to
what extent trained models can be transferred to other sensor data or datasets. Therefore, it shall
be investigated how strong the dependence of the detector (PointRCNN) on the used sensors is.
The results show that PointRCNN can be evaluated with a different dataset than the training
dataset while still being able to detect objects. The point density of the datasets plays a decisive
role for the quality of the detection. Therefore it can be said that PointRCNN has a sensor
dependency that varies with the nature of the point cloud and its density.
Keywords: LiDAR data, 3D object recognition, laser scanner, sensor dependency, PointRCNN,
PointNet++, PointNet, KITTI Dataset, AEV Autonomous Driving Dataset, A2D2 Datase
Maneuver-based Control Interventions During Automated Driving: Comparing Touch, Voice, and Mid-Air Gestures as Input Modalities
No full textSelf-driving cars will relief the human from the driving task. Nevertheless, the human might want to intervene in the driving process and thus needs the possibility to control the car. Switching back to fully manual controls is uncomfortable once being passive and engaging in non-driving-related activities. A more comfortable way is controlling the car with elemental maneuvers (e.g., "turn left" or "stop"). Whereas touch interaction concepts exist, contactless interaction through voice and mid-air gestures has not yet been explored for maneuver-based car control. In this paper, we, therefore, compare the general eligibility of voice and mid-air gesture with touch interaction as the primary maneuver selection mechanism in a driving simulator study. Our results show high usability for all modalities. Contactless interaction leads to a more positive emotional perception of the interaction, yet mid-air gestures lead to higher task load. Overall, voice and touch control are preferred over mid-air gestures by most users
Teaching Problem Solving Skills By Strategy Trainings In Physics
Get PDFNowadays the expectations and requirements for engineers keep changing and involve besides technical, interdisciplinary and project management competencies, in particular problem solving skills (Lehmann et al., 2008). It has been shown that implicit teaching of problem solving strategies fails. The results are missing approaches, no linkage to the existing knowledge and the failure of a solution. (Woitkowski, 2018) However, there is a very well evaluated state of research how novices and experts solve physics problems. Experts use problem schemes, which include heuristics and exemplary problems that ease the process of generating proper solutions and make the process much less error-prone. (Friege, 2001) Therefore, the aim of this study is to develop a strategy training, which contains a strategy exercise and adjusted learning material to promote the problem solving competence of first year engineering students. To implement such a strategy training in the regular physics exercise, a manual concerning different task characteristics has been developed. The resulting categories have been used to create a compilation of tasks, which are suitable for analysing the fitting heuristics. To measure the effect of the new learning material and the strategy training a 2x2-design was chosen to examine the influence of either one of those variables. The pre-post-evaluation will focus on questionnaires considering the stages of the problem solving process
Design Principles of Collaborative Learning Space Connecting Teachers and Refugee Children - a Design Science Research Study
Get PDFLearning the German language is one of the most critical challenges for refugee children in Germany. It is a prerequisite to allow communication and integration into the educational system. To solve the underlying problem, we conceptualized a set of principles for the design of language learning systems to support collaboration between teachers and refugee children, using a Design Science Research approach. The proposed design principles offer functional and non-functional requirements of systems, including the integration of open educational resources, different media types to develop visual and audio narratives that can be linked to the cultural and social background. This study also illustrates the use of the proposed design principles by providing a working prototype of a learning system. In this, refugee children can learn the language collaboratively and with freely accessible learning resources. Furthermore, we discuss the proposed design principles with various socio-technical aspects of the well-being determinants to promote a positive system design for different cultural and generational settings. Overall, despite some limitations, the implemented design principles can optimize the potential of open educational resources for the research context and derive further recommendations for further research
ERC-20-based smart contracts for high performance GPU-Computation-on Whole-Genome Human Metabolic Simulations
No full textEntwicklung und Evaluation einer generischen Dialogstruktur für Voicebots zur Vereinbarung von Terminen in der Kundenbetreuung
No full text
How to Increase Automated Vehicles’ Acceptance through In-Vehicle Interaction Design: A Review
No full textAutomated vehicles (AVs) are on the edge of being available on the mass market. Research often focuses on technical aspects of automation, such as computer vision, sensing, or artificial intelligence. Nevertheless, researchers also identified several challenges from a human perspective that need to be considered for a successful introduction of these technologies. In this paper, we first analyze human needs and system acceptance in the context of AVs. Then, based on a literature review, we provide a summary of current research on in-car driver-vehicle interaction and related human factor issues. This work helps researchers, designers, and practitioners to get an overview of the current state of the art
