Werner Huber

Technische Hochschule Ingolstadt · Department of Electrical Engineering

Evaluating traffic safety using simulation is a huge challenge. The proportion of slower-than-average responses is particularly important, as these greatly influence the likelihood of accidents or injuries in dangerous circumstances. Developing accurate models that account for variations in individual response processes is fundamental for reliable...

Crashes involving vulnerable road users (VRUs) account for nearly 70% of all traffic fatalities in urban areas. To evaluate the effectiveness of measures to improve VRU safety, the causes of accidents attributable to human behavior require investigation, which remains a challenge to date. Experiments for this purpose are often conducted in a contro...

The main approaches for simulating FMCW radar are based on ray tracing, which is usually computationally intensive and do not account for background noise. This work proposes a faster method for FMCW radar simulation capable of generating synthetic raw radar data using generative adversarial networks (GAN). The code and pre-trained weights are open...

Background: Driving in urban traffic requires ad-vanced cognitive skills: perceiving all relevant traffic participants,anticipating their likely trajectories, deciding which action totake, and controlling the vehicle. The underlying perceptual andcognitive processes are subject to occasional failures, which candepend in a complex way on learned heu...

Micromobility, and e-scooters in particular, are now present in large numbers in many cities, and projections predict strong demand growth in the post-pandemic period, but e-scooter riders have a high risk of accident/injury. We want to represent human behavior in simulations in a way that can be used to assess proposed infrastructure-based safety...

Testing automated driving systems is challenging due to the numerous and unexpected scenarios these can en- counter in road traffic. In order to reduce the effort and costs of real test drives, different simulation-based test methods for environment sensors have been developed. The purpose is to enable the hardware integration of sensors in the ear...

Accurate environment perception can be achieved with multiple sensors with different measuring principles -- such as camera, lidar and radar sensors. In automated driving applications, this diversity aims, for example, to reduce the susceptibility of sensors to inclement weather. Fusion combines data from sensors and creates a generic representatio...

Safely traveling through urban traffic, for exampleperforming a right turn at an intersection, is a complextask for human drivers. Multiple stimuli such as leadingvehicles, cyclists or spontaneously crossing pedestrians competefor attention. Limited field of view and sampling capabilitiesof humans make a parsimonious and sometime error-proneselecti...

In automated driving functions (ADF) testing, novel methods have been developed to allow the combination of hardware and simulation to ensure safety in usage even at an early stage of development. This article proposes an architecture to integrate an entire test vehicle—denominated Dynamic Vehicle-in-the-Loop (DynViL)—in a virtual environment. This...

Scenario-based proving ground testing has been established as the standard test environment for the homologation of driver assistance systems. These test procedures are described, for example, in the New Car Assessment Programme test catalog, which only considers a limited number of possible scenarios. Furthermore, pedestrian targets are, among oth...

Micro-mobility modes such as e scooters are gaining increasing popularity, but e-scooter riders have high crash/injury risks. Virtual assessment of traffic safety measures, such as automated driving functions, requires valid models of all road users, including their interactions and responses to threats. This paper focuses on process models of thre...

Camera systems capture images from the surrounding environment and process these datastreams to detect and classify objects. However, these systems are prone to errors, often caused by adverse weather conditions such as fog. It is well known that fog has a negative effect on the camera’s view and thus degrades sensor performance. This is caused by...

The validation of automated driving requires billions of kilometers of test drives to be performed so that safety-in-use is assured. It is difficult to validate it only making use of data acquired on field tests in public roads due to the lack of controllability, e.g. over environment conditions. Therefore, the automotive industry relies on test dr...

Camera systems capture images from the surroundings and process these data for detecting and classifying objects. One particular category responsible for faults and failures is adverse weather conditions. In this case, it is known that rain, for example, degrades a sensor's performance due to absorption and scattering on falling raindrops. In addit...

New functions of modern vehicles (e.g., autonomous driving, early airbag ignition) make heavy use of internal and external communication. The increased usage of communication for the realization of safety-critical functions leads to new challenges for security and safety. In order to meet current as well as future requirements regarding the validit...

In order to correctly perceive its surroundings, advanced driver-assistance systems (ADAS) rely on the data quality of environment sensors, such as cameras, and on the data processing to distinguish multiple classes of traffic participants. Real test drives are important for their testing and validation, but certain test scenarios are difficult to...

For the system test of automotive safety systems, thousands of kilometers need to be driven on real roads. In the future, that number will increase significantly through higher complexity of the functions. To reduce that number and guarantee the controllability, reproducibility and increase the flexibility, a high amount of virtual driving kilomete...

Safety systems in automated vehicles use surround sensors to perceive their local environment. In contrast to radar sensors, laser scanners provide precise spatial information, which can be used to identify critical traffic situations and trigger reversible or irreversible safety systems. As a consequence , already small errors in sensor data measu...

The BASt-project group “Legal consequences of an increase in vehicle automation” has identified, defined and consequently compiled different automation degrees beyond Driver Assistance Systems. These are partial-, high- and full automation. According to German regulatory law, i.e. the German Road Traffic Code, it has been identified that the disti...

Advanced Driver Assistance systems support the driver in his driving tasks. They can be designed to enhance the driver's performance and/or to take over unpleasant tasks from the driver. An important optimization goal is to maintain the driver's activation at a moderate level, avoiding both stress and boredom. Functions requiring a situational inte...

"FGV-TUM." Originally presented as the author's Thesis (doctoral)--Technische Universität München. Includes bibliographical references (p. 195-201).