奥迪

In contemporary virtual vehicle development based on systems engineering and the V-Model methodology, two primary approaches are used for simulating longitudinal dynamics: quasi-static backward simulation models and dynamic forward simulation models. Each approach offers distinct advantages and disadvantages. The main benefit of quasi-static backward simulation models is their computational efficiency. However, this type of model does not capture vehicle dynamics, which is a strength of forward simulation models. Additionally, forward simulation models inherently require longer computation times, which significantly increases the overall simulation effort, particularly when combined with optimization across multiple iterations. Nevertheless, in the context of requirement-based simulation, backward simulation models are generally more suitable than forward simulation models. Therefore, an obvious solution is to include dynamics in a backward simulation model.This publication presents a new time-efficient backward simulation approach that incorporates vehicle dynamics, with a particular focus on the acceleration of battery-electric vehicles (BEVs). The model is constructed using basic component representations, which can be replaced by more detailed models in future work, in line with systems engineering principles. For validation, the outputs of the proposed model are first compared against a quasi-static backward simulation model, a forward simulation reference model and vehicle measurement data. Secondly, a parameter analysis is conducted using a forward simulation model to analyze the chosen parameters of the backward simulation model.

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, which represent a new generation of pre-trained, general-purpose AI models, developers can process heterogeneous inputs (e.g., natural language, sensor data, HD maps, and control actions), enabling the synthesis and interpretation of complex driving scenarios. In this paper, we conduct a survey about the application of foundation models for scenario generation and scenario analysis in autonomous driving (as of May 2025). Our survey presents a unified taxonomy that includes large language models, vision-language models, multimodal large language models, diffusion models, and world models for the generation and analysis of autonomous driving scenarios. In addition, we review the methodologies, open-source datasets, simulation platforms, and benchmark challenges, and we examine the evaluation metrics tailored explicitly to scenario generation and analysis. Finally, the survey concludes by highlighting the open challenges and research questions, and outlining promising future research directions. All reviewed papers are listed in a continuously maintained repository, which contains supplementary materials and is available at https://github.com/TUM-AVS/FM-for-Scenario-Generation-Analysis.

Automated vehicles (AVs) promise to enhance transportation safety and efficiency. However, ensuring their reliability in real-world conditions remains challenging, particularly due to rare and unexpected situations known as edge cases. While numerous approaches exist for detecting edge cases, a comprehensive survey reviewing these techniques is lacking. This paper bridges this gap by presenting a hierarchical review and systematic classification of edge case detection and assessment methodologies. Our classification is structured on two levels: first, by AV modules, including perception and trajectory-related (encompassing prediction, planning, and control) subsystems; and second, by underlying methodologies and theories guiding these techniques. Furthermore, we introduce "knowledge-driven" approaches, which complement data-driven methods by leveraging expert insights and domain knowledge to identify cases absent in training datasets. We then examine techniques and metrics for evaluating edge case detection methods, including detection performance, practical deployment (e.g., computational overhead), and domain-specific measures (e.g., crash rates and severity analysis). We conclude by highlighting key challenges for edge case detection, including data availability and quality issues, validation and interpretability limitations, the simulation-to-real gap, and computational constraints. The hierarchical classification and review of methods and assessment techniques in this survey enable modular and targeted testing frameworks by guiding the selection of detection methods for specific AV subsystems while considering methodological principles. It also supports practical testing by facilitating scenario generation in simulation and focused subsystem validation in the real world.

Where do the economic, environmental and social responsibilities of a car company begin and end? This is a question that often prompts discussion. For Audi, the focus of corporate responsibility is primarily on its products—and always considers the entire life cycle of a vehicle, from its production and use to the end of its life span: recycling. To lay the groundwork today for the future, the premium carmaker has to consider a wide range of issues: supplier management, protection of the environment, the research and development of innovative technologies like electrical mobility and synthetic fuels, and the challenge of recycling as much as possible of the materials used in cars. In doing so, Audi always considers how people will be living a few years from now, since creating an intelligent design for future individual mobility also depends on that. Audi bases all corporate decisions and activities on the sustainability of its products and processes. "We live responsibility" is the basic philosophy that runs like a common thread throughout the company.

Model-Based Systems Engineering (MBSE) promises structured, traceable development of complex systems, but high modeling effort remains a key adoption barrier. The textual notation of SysML v2 turns model construction into a text-to-text generation problem, opening new avenues for large language model (LLM) automation. This paper presents AMADEUS (Agentic Model-Aided Development Engineering Utilizing SysML), a conceptual framework for integrating agentic AI into systems engineering workflows in automated driving. The AMADEUS framework comprises three contributions: (1) a work package concept that operationalizes a domain-specific Systems Engineering methodology into discrete units executable by agents and maps each section to orchestration patterns such as actor-critic validation and role-based routing, (2) two complementary architecture patterns, typed operations exposed by a dedicated model server and direct SysML v2 text editing in a Git-based workflow, with a comparative analysis, and (3) an empirical benchmark evaluating three late-2025 frontier AI agents (OpenAI Codex, Google Gemini 3 Pro, Anthropic Claude Sonnet 4.5) against a human expert reference on seven SysML v2 modeling tasks of varying complexity. The evaluation provides initial evidence that AI agents achieve comparable quality (average score 3.69 vs. 3.86 on a 0–4 scale) while reducing modeling time by a factor of approximately 12 and per-task execution cost by a factor of 3,500. Transformation tasks achieve average S_total≥ 3.6 out of 4, while deduction-heavy tasks reveal remaining gaps, suggesting that the engineer’s role shifts from model creator to model reviewer.