Publications Search Results
1 - 10 of 71
-
PublicationDesigning User Interfaces for Automated Driving: A Simulator Study on Individual Information Preferences( 2024)Automated Driving (AD) can free users from driving and create time for their disposal. However, since manufacturers increasingly target a wide customer range with AD, such systems and their User Interfaces (UI) must accommodate different user characteristics and preferences. This paper aims to analyze the effects of individual characteristics on the information preferences in UIs for surrounding road infrastructure (for instance, lane markings or traffic signs) and system limits describing hindering factors for AD (for instance, construction sites or unsuitable weather conditions). To do so, we performed a driving simulator study with 43 participants. Results show that users with a more positive attitude towards technology prefer more infrastructure information. Furthermore, users familiar with Automatic Cruise Control prefer less system limit information, while higher experience with Steering Assists relates to higher preference in this regard. These findings add concrete mechanisms to the theory of personalized AD UIs and inform product development on how to create more personalized user experiences. By this, we aim to address challenges regarding the acceptance, adoption, and usage of AD.
-
PublicationCybersecurity risk analysis of an automated driving system( 2023-10-25)
-
PublicationEvCenterNet: Uncertainty Estimation for Object Detection Using Evidential Learning( 2023)Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision making and path planning. In this work, we propose EvCenterNet, a novel uncertainty-aware 2D object detection framework using evidential learning to directly estimate both classification and regression uncertainties. To employ evidential learning for object detection, we devise a combination of evidential and focal loss functions for the sparse heatmap inputs. We introduce class-balanced weighting for regression and heatmap prediction to tackle the class imbalance encountered by evidential learning. Moreover, we propose a learning scheme to actively utilize the predicted heatmap uncertainties to improve the detection performance by focusing on the most uncertain points. We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets including BDD100K and nuImages. Our experiments demonstrate that our approach improves the precision and minimizes the execution time loss in relation to the base model.
-
PublicationAccelerated Real-Life (ARL) Testing and Characterization of Automotive LiDAR Sensors to facilitate the Development and Validation of Enhanced Sensor Models( 2023)In the realm of automated driving simulation and sensor modeling, the need for highly accurate sensor models is paramount for ensuring the reliability and safety of advanced driving assistance systems (ADAS). Hence, numerous works focus on the development of high-fidelity models of ADAS sensors, such as camera, Radar as well as modern LiDAR systems to simulate the sensor behavior in different driving scenarios, even under varying environmental conditions, considering for example adverse weather effects. However, aging effects of sensors, leading to suboptimal system performance, are mostly overlooked by current simulation techniques. This paper introduces a cutting-edge Hardware-in-the-Loop (HiL) test bench designed for the automated, accelerated aging and characterization of Automotive LiDAR sensors. The primary objective of this research is to address the aging effects of LiDAR sensors over the product life cycle, specifically focusing on aspects such as laser beam profile deterioration, output power reduction and intrinsic parameter drift, which are mostly neglected in current sensor models. By that, this proceeding research is intended to path the way, not only towards identifying and modeling respective degradation effects, but also to suggest quantitative model validation metrics.
-
PublicationhelyOS: A customized off-the-shelf solution for autonomous driving applications in delimited areas( 2023)Microservice Architectures (MSA), known to successfully handle complex software systems, are emerging as the new paradigm for automotive software. The design of an MSA requires correct subdivision of the software system and implementation of the communication between components. These tasks demand both software expertise and domain knowledge. In this context, we developed an MSA framework pre-tailored to meet the requirements of autonomous driving applications in delimited areas - the helyOS framework. The framework decomposes complex applications in predefined microservice domains and provides a communication backbone for event messages and data. This paper demonstrates how such a tailored MSA framework can accelerate the development by prompting a quick start for the integration of motion planning algorithms, device controllers, vehicles simulators and webbrowser interfaces.
-
PublicationFault Injection in Actuator Models for Testing of Automated Driving Functions( 2023)
-
PublicationThe Path to Safe Machine Learning for Automotive Applications(SAE International, 2023)Recent rapid advancement in machine learning (ML) technologies have unlocked the potential for realizing advanced vehicle functions that were previously not feasible using traditional approaches to software development. One prominent example is the area of automated driving. However, there is much discussion regarding whether ML-based vehicle functions can be engineered to be acceptably safe, with concerns related to the inherent difficulty and ambiguity of the tasks to which the technology is applied. This leads to challenges in defining adequately safe responses for all possible situations and an acceptable level of residual risk, which is then compounded by the reliance on training data. The Path to Safe Machine Learning for Automotive Applications discusses the challenges involved in the application of ML to safety-critical vehicle functions and provides a set of recommendations within the context of current and upcoming safety standards. In summary, the potential of ML will only be unlocked for safety-related functions if the inevitable uncertainties associated with both the specification and performance of the trained models can be sufficiently well understood and controlled within the application-specific context.
-
PublicationImplementing Remote Driving in 5G Standalone Campus Networks( 2023)While there have been enormous advances in automated driving functions in the recent years, there are still circumstances where automated driving is not feasible or not even desired. Teleoperation is one approach to keep the vehicle mobile in such situations, with remote driving being one mode of teleoperation. In this paper we describe a 5G remote driving environment based on a 5G Standalone campus network, explaining technological and hardware choices. The paper is completed with experiences from practical trials, showing that remote driving using the proposed environment is feasible on a closed area. The achieved velocities are similar to that of a direct human driver.
-
PublicationVerification and validation of automated driving systems utilizing probabilistic FMEA and simulation approachesOne of the main challenges for deploying highly automated driving is the need for a new strategy for verification and validation ensuring a safety and reliability in all traffic scenarios and conditions. In this context, the two projects of the German PEGASUS family VV Methoden and Set Level are focusing on this challenge addressing advanced methods for verification and validation as well as a holistic simulation environment for development and testing of automated driving functions. Within this paper, the overall concept of defining system and test requirements based on a probabilistic FMEA will be presented and discussed in view of applicability and limitations. The discussion will be complemented by outlining the closed-loop simulation approach and demonstration its potential by means of a first XiL test rig for a camera system applying a virtual traffic scenario.
-
PublicationClosing the gaps: Complexity and uncertainty in the safety assurance and regulation of automated driving( 2023)The increasing level of automation within an open context and use of artificial intelligence in cognitive cyber-physical Systems (CPS) is leading to emergent complexity and subsequently to uncertainties within the system assurance process. For example, in automated driving this is particularly true for the class of risks associated with the safety of the intended functionality (SOTIF) as described by the standard ISO 21448. In this report, we provide a definition of how complexity and uncertainty impacts the safety assurance of cognitive CPS. Based on this structured understanding of the problem, we propose an approach to managing the safety and regulating the deployment and operation of such systems in order to maintain an acceptable level of residual risk despite of, and with the intent of reducing, residual uncertainties. The approach includes criteria to guide decisions regarding the deployment and continuous assurance of the systems. The model used to structure these proposals includes a causal analysis of the factors impacting the complexity and resulting uncertainty (and, by extension, risk) that span the three layers of technical & human factors, management & operations and governance and regulation. These principles are generally applicable to a broad class of cognitive cyber-physical systems. However, in this report we focus on their application to automated driving systems.
