Master / Bachelor - Survey of Vehicle AD - Software Architectures - Entwicklung, Forschung, IT

You will work with our team on a systematic survey of software architectures for automated driving, focusing on end-to-end approaches, modular pipelines, and agentic AD systems (LLM-based, tool-using agents and orchestration). You will develop a taxonomy of the different architectures, analyze relevant open-source stacks (e.g., Autoware, Baidu Apollo, potentially S-Core/Red Hat ecosystems) based on documentation, releases, and repositories, and derive technological trends, gaps, and actionable recommendations.

Your tasks

• refine the topic and formulate precise research questions.
• conduct a systematic literature search (IEEE, ACM, arXiv, Google Scholar), screen the studies, and extract relevant data.
• develop a taxonomy of architectures: end-to-end vs. modular vs. agentic (roles, orchestration, tool use, safety/runtime aspects).
• compare open-source AD stacks, analyzing architecture layers, middleware (e.g., ROS 2/CyberRT), APIs, roadmaps, releases, licensing/governance, community metrics, and maturity levels.
• map agentic AD concepts, including agent roles (planner, safety critic/verifier, perception narrator, controller designer), communication patterns, knowledge integration (e.g., RAG), and integration points within existing stacks.
• compile the landscape of relevant benchmarks and datasets, especially for scenarios such as parking or docking.
• create evidence syntheses, comparison tables, and visualizations, deriving guidelines and research gaps.
• contribute to scientific writing (DE/EN) and prepare the final presentation.

• Academic studies in a relevant technical or engineering field such as Industrial Engineering, Mechanical Engineering, Automotive Engineering, Computer Science, Robotics, Electrical Engineering, Mechatronics, Control Engineering, Aerospace Engineering, or Technical Business Administration or similar
• Interest in automated driving, software architectures, and agentic AD/LLM-based concepts.
• Basic knowledge of literature research and academic referencing (e.g., BibTeX, Zotero, systematic screening).
• Structured, analytical working style with precise documentation (EN/DE).
• Beneficial: Basic skills in programming (e.g., Python/C++) and experience in open-source communities.
• Remuneration is according to the German TVöD 05.