User-oriented evaluation of driver assistance systems

Abstract

The development of driver assistance systems must be accompanied by useroriented evaluation procedures in order to achieve high effectiveness and acceptance in everyday use while minimizing unwanted “side effects.” In addition to design recommendations such as the Response Code of Practice, user-oriented tests with both expert and nonexpert drivers have to be conducted in various phases of the development process. This chapter explains the suitability, planning, execution, and analysis of these user-oriented tests in a variety of test environments. It covers the whole range from driving simulator experiments, tests on proving grounds and in real traffic environments, up to and including field validation tests before final signoff. Recommendations are given for the experimental design, including the selection of test persons, sample size, test scenarios, and setups, as well as the choice of suitable assessment parameters and criteria. A special section is devoted to the execution and analysis of field validation tests. Practical examples for all test settings complete the chapter, including from the area of Functional Safety. The evaluation and validation of Mercedes-Benz safety systems for rear-end crash avoidance is a recurrent theme, supplemented by examples of other types of driver assistance system.