Effective Evaluation of Automated Driving Systems 2017-01-0031
In the last years various advanced driver assistance systems (ADAS) have been introduced on the market. More highly advanced functions up to automated driving functions are currently under research. By means of these functions partly automated driving in specific situations is already or will be realized soon, e.g. traffic jam assist. Besides the technical challenges to develop such automated driving functions for complex situations, e.g. construction or intersection areas, new approaches for the evaluation of these functions under different driving conditions are necessary, in order to assess the benefits and identify potential weaknesses. Classical approaches for evaluation and market sign off will require an extensive testing, which results in high costs and time demands. Therefore the classical approaches are hardly feasible taking into account higher levels of support and automation.
Today the final sign-off requires a high amount of real world tests. This cannot be provided for all possible driving situations for higher degrees of vehicle automation due to the influencing factors such as environmental conditions, infrastructure and behavior of other traffic participants. The high amounts as well as the different combination of situations require thousands of test kilometers in order to cover all relevant driving situations. Furthermore evaluation of ADAS needs to consider the conflict of interest between acceptance, effectiveness and controllability as well as to ensure the fulfillment of the functional safety requirement defined in the ISO 26262. Taking this into account, this paper presents the systematic approach to evaluate a traffic jam assist feature. This feature supports the driver in traffic jam situations by means of longitudinal and lateral control support using a radar and a camera sensor. In this context, this paper describes a systematic approach to evaluate road vehicles with automated driving functions.