A5085225726- Traffic and Road Safety
- Autonomous Vehicle Technology and Safety
- Traffic Prediction and Management Techniques
- Traffic control and management
- Human-Automation Interaction and Safety
- Real-time simulation and control systems
- Risk and Safety Analysis
- Simulation Techniques and Applications
- Bayesian Modeling and Causal Inference
- Safety Systems Engineering in Autonomy
- Vehicle emissions and performance
- Data Quality and Management
- Anomaly Detection Techniques and Applications
- Vehicle Dynamics and Control Systems
- German Security and Defense Policies
- Safety Warnings and Signage
- Myofascial pain diagnosis and treatment
- Biomedical Text Mining and Ontologies
- Musculoskeletal pain and rehabilitation
- Urban Transport and Accessibility
- Vehicular Ad Hoc Networks (VANETs)
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Fault Detection and Control Systems
- Data-Driven Disease Surveillance
- Transportation Planning and Optimization
TU Dresden
2019-2024
Kraftanlagen (Germany)
2023
Scenario based methods for testing and validation of automated driving systems in virtual test environments are gaining importance becoming an important component verification processes systems. The high system complexity such the costs lead to exponential increase efforts real world testing. Recent research works have shown that it is necessary drive billions kilometers ensure safety reliability This amount far from possible achievable any procedure regarding time costs. Using different...
With the rise of Advanced Driver Assistant Systems (ADAS) and introduction Highly Automated Driving (HAD), understanding predicting road traffic accidents becomes increasingly important. Especially for assessment HAD/ADAS systems safety, precise prediction system's impact on occurrence is essential. Traffic simulations, as one option virtual assessment, enable safety in test fields. By modelling human driver, it possible to simulate predict future accident constellations severities. In...
Automated driving systems should be able to avoid road traffic accidents and drive more safely than human drivers do. Test scenarios derived from real-world data such as police accident can help assess the safety performance of automated systems. In many countries, collect information about nearly every accident, resulting in a representative sample. However, collected often do not contain exact conflicts that cause an accident. Therefore, we estimated globally known three-digit type for...
This survey aims to provide an overview of various methods for generating data-driven test scenarios assessing automated driving systems (ADS). The updates the overall process scenario generation and categorizes current using a systematic literature reviewof 64 studies identified between 2017 01/2023. Overall, we demonstrate that should be updated by another step, fusion, leading seven steps: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Scenario-based testing will help validate automated driving systems (ADS) and establish safer road traffic. To date, most data-driven test scenario generation methods rely primarily on one data source such as police accident (PD), naturalistic studies, or video-based traffic observations (VOs). However, none of these sources perfectly satisfies all layers the six-layer model for description scenarios. Moreover, not available cover same location period. Therefore, we fused information from...
Scenario-based testing is a major pillar in the development and effectiveness assessment of automated driving systems. Thereby, test scenarios address different information layers situations (normal driving, critical accidents) by using databases. However, systematic combination accident / or normal databases into new synthetic can help to obtain that are as realistic possible. This paper shows how statistical matching (SM) be applied fuse categorial traffic observation Hereby, fusion...
Automated driving systems (ADS) should be able to avoid road traffic accidents and drive safer than human drivers. Test scenarios derived from real-world data – e.g. police accident can help assess the safety performance of ADS.In many countries, collect information about nearly every accident, thus resulting in a representative sample. However, collected often does not contain exact conflict which caused accident. Therefore, we have estimated three-digit type, describing accident-causing...
Motorcyclists are among the most vulnerable road users in traffic. Often, cause of accidents is a loss control on rural roads which could be averted by making use physical potential terms larger lean angles. At same time, reality driven angles over group riders and longer route unknown mainly due to special measuring technology required. The focus therefore development low-cost measurement method for motorcycles. Smartphones usually characterized integrated inertial sensors, suitable...