Reinforcement Learning (RL) has shown significant promise in developing autonomous navigation algorithms for complex environments. However, the direct application of RL policies trained in simulation to real-world scenarios often faces challenges due to the reality gap. This paper proposes a two-stage system incorporating a segmentation strategy and a bird’s-eye-view (BEV) representation to mitigate the domain gap between simulation and reality. In the first stage, the segmentation transforms sensor data into a simplified and interpretable representation of the surrounding area, facilitating transferability across different deployments. In the second stage, the agent navigates through the BEV map, which can be trained using a vectorized simulation environment---a setup that runs multiple parallel instances of the environment to provide a wide range of training scenarios. This vectorization enables rapid exposure to varied environmental conditions, thereby accelerating and diversifying the training of a deep RL agent to achieve optimal navigation behaviors while maintaining high-speed, in-bound trajectories. The segmentation is crucial because it supports generalization of the learned policy across different robotic platforms. The contribution of this paper lies in combining real-time semantic segmentation with a bird’s-eye-view navigation policy, resulting in a transferable and scalable framework for real-world deployment of RL-based navigation agents. Experimental results demonstrate that agents trained with this methodology exhibit robust navigation performance and adaptability in both simulated and real-world environments, validating the efficacy of combining vectorized simulation with real-world segmentation for practical robotic navigation.

We propose a meta-language-based approach enabling Large Language Models (LLMs) to reliably generate structured, machine-readable artifacts referred to as Meta-Languagedefined Structures (MLDS) adapted to domain requirements, without adhering strictly to standard formats like JSON or XML.By embedding explicit schema instructions within prompts, we evaluated the method across diverse use cases, including automated Virtual Reality environment generation and automotive security modeling.Our experiments demonstrate that the meta-language approach significantly improves LLM-generated structure compliance, with an 88% validation rate across 132 test scenarios.Compared to traditional methods using LangChain and Pydantic, our MLDS method reduces setup complexity by approximately 80%, despite a marginally higher error rate.Furthermore, the MLDS artifacts produced were easily editable, enabling rapid iterative refinement.This flexibility greatly alleviates the "blank page syndrome" by providing structured initial artifacts suitable for immediate use or further human enhancement, making our approach highly practical for rapid prototyping and integration into complex industrial workflows.

Rapid advances of connected and autonomous vehicle technology have led to an increase in cyber-attacks.This in turn has driven the development of the ISO 21434 standard aimed at supporting the management of cybersecurity risks in the automotive industry.There is, however, a disconnect between the standard and the currently applied model-based development approaches that are increasingly applied for systems and software development.In this paper, we present tool support created for model-based automotive cybersecurity engineering.This tool is built upon the existing automotive systems development language, EAST-ADL, with extensions to address security in accordance with the ISO 21434 standard covering modeling support, calculation of security-related metrics such as impact, risk, and attack feasibility, and generation of ISO 21434 compliant security threat reports.Meeting the requirements of cybersecurity engineeering according to ISO 21434 are demonstrated with two examples.

In view of the advent of autonomous driving, the automotive industry is longing for adequately trained employees in a wide range of fields; these include not so much the classic automotive engineering and embedded systems topics, but rather software development, robotics, machine learning, statistics and design. As a particularly specific, industry-oriented discipline, automotive software engineering is hardly represented in academic teaching, except for a few AUTOSAR courses. But as a beacon project of digitization, autonomous driving can arouse broad interest among students who are interested in how diverse disciplines can be profitably combined to realize an impressive project. This interest is an excellent chance for both universities and industry to engage in constructive dialogue, to carry out exciting multidisciplinary projects at universities and to meet the needs of industry with graduates who have a relevant and versatile education. This workshop provides an opportunity for both sides to meet, share requirements and experiences and develop a best practice course according to industry requirements and academic feasibility.

The complexity of embedded automotive systems calls for a more rigorous approach to system development compared to current state of practice. A critical issue is the management of the engineering information that defines the embedded system. Development time, cost efficiency, quality and dependability all benefit from appropriate information management. System modeling based on an architecture description language is a way to keep the engineering information within one information structure. The EAST-ADL was developed in the EAST-EEA project (www.easteea.net) and is an architecture description language for automotive embedded systems. It is currently refined in the ATESSTproject (www.atesst.org). This paper gives an overview of the EAST-ADL and accounts for some recent refinements as developed in the ATESST project. Areas covered include the relation to other standardization initiatives such as UML2.0, AADL, AUTOSAR, SysML, Marte profile, requirements management and variability.

A software product line oriented approach to developing systems has an impact on the development process as a whole. Although the basic idea of product lines is simple, systematic implementation of the approach is a challenging task. In fact, today's software product lines have such complex variability that their handling must be supported by tools, otherwise a systematic approach would not be possible. The same holds for requirements management of product lines. On the basis of specific industrial scenarios the paper derives important requirements that have to be observed if requirements management tools are to be usefully applied to product lines. Current requirements management tools are evaluated on the basis of these requirements in their daily industrial use. The presented requirements can indicate the future direction of tool development and method research.