Anomaly detection and Quality Indicators for Digital maps used in ADAS applications

With the evolution of ADAS and AD technology, digital maps have become one of the critical sources along with other ADAS sensors. Up-to-date map data is crucial for proper functioning of ADAS functions. The need for map update is driven by (i) ADAS technology progressively using map attributes in risk of getting outdated, and (ii) by rapid changes in road infrastructure. This demands the need to evaluate the correctness and quality of the map data on a regular basis and in an efficient way. In this work, we propose a framework to quantify the map data quantity and quality in a systematic way. The framework algorithmically detects error locations in a map database and then derives KPIs from these error locations. This helps in identifying issues in the map data related to the internal data consistency or heuristic rules. The framework consists of a process automation written in Python and map database checks written in SQL. The proposed framework defines validation methodology that achieves goals like: (1) KPIs for map data reliability (2) systematic error identification. The framework was evaluated with maps from different sources. The framework yields results quickly and efficiently so that it can be regularly executed well before vehicle testing. In addition, the efficient KPI calculation permits to control relevant map properties over subsequent map releases.