As automated driving technologies become more mature, there is an increasing reliance on digital maps to support safe and efficient driving. Sensors like cameras and radars can be limited by occlusions, lighting conditions, or weather, and often fall short. High-definition (HD) maps offer excellent accuracy, but they are expensive to produce. These limitations make these techniques impractical for large-scale deployment. What makes our approach particularly attractive is its hardware simplicity: the entire process requires only a precise GNSS receiver and a commonly available lane detection camera, eliminating the need for expensive sensors like LiDAR or complex multi-vehicle fleets. We rigorously evaluated our method in a highway environment, where a vehicle equipped with our generated maps successfully executed autonomous lane following and adapted its speed based on detected speed limit signs. The positional deviation of the resulting maps was consistently under 5 cm.

Automated Driving functions have widely spread in last years, not only in research, but also in the automotive industry. Many car manufacturers and their suppliers have funded different software systems to fulfill the driving requirements. By the growing number of innovations, the rapidly changing technology and newer players in the automotive industry requires academy and industry to collaborate on their automated software developments. To do so, a common research and development framework is needed which inherently provides smooth transition of new solutions from one world to the other. Even though there are many open source research framework for rapid prototyping of automated driving functions, these solutions are often concentrated on low speed maneuvering, especially for the higher automation levels, such as robo-taxis. However, major automotive companies require developments of up to SAE (Society of Automotive Engineers) level 2 and 3. Therefore, a new prototypical, open source software architecture¹ is proposed, that uses well-known tools and technology as basis, such as Robot Operating System or Autoware Universe, but also being closely in compliance with industrial architecture aspects. It is proven that the proposed architecture, along with its abstraction layers and interfaces provide modularity, and interchangeability of basic components, while the hardware and vehicle dependencies are well separated from the application software layer. Via few exemplary functions the usability of the system is demonstrated, and fellow researchers are highly encouraged to advise on the generalization of the system.¹https://github.com/jkk-research/CooperativeResearchPlatform/tree/release