Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a methodology examining the adaptability and performance evaluation of the 3D object detection methods on a LiDAR point cloud dataset generated by simulating a SOTIF-related Use Case.
This dataset provides the data collected in the scope of a Systematic Literature Review (SLR) study that focuses on systematically gather and analyse the existing literature on SOTIF published during 2018-2023. By performing a SLR on SOTIF, we have determine the factors associated with the successful implementation of SOTIF measures, the challenges arise when ensuring SOTIF for ADSs, and research gaps from the SLR of existing literature on SOTIF. The dataset can be useful for the researchers and practitioners.