Control Model of Automated Driving Systems based on SOTIF Evaluation 2020-01-1214
In partially automated and conditionally automated vehicles, part of the work of human drivers is replaced by the system, and the main source of safety risks is no longer system failures, but non-failure risks caused by insufficient system function design. The absence of unreasonable risk due to hazards resulting from functional insufficiencies of the intended functionality or by reasonably foreseeable misuse by persons, is referred to as the Safety Of The Intended Functionality (SOTIF). Drivers have the responsibility to supervise the automated driving system. When they don't agree with the operation behavior of the system, they will interfere with the instructions. However, this may lead to potential risks. In order to discover the causes of human misuse, this paper takes the trust feeling between the driver and the automated driving system as the starting point, and based on the collected data of track test, establishes the evaluation index -- confidence degree to show the trust feeling between the driver and the automated system. Confidence degree is a comprehensive interpretation of the driver's physiological and psychological feelings. In the process of track test, we simultaneously collect the dynamics indicators of the vehicle and the feedback of the steering wheel to the driver, including the torque of the steering wheel and the change of steering wheel angle. After the test, the drivers' driving feeling was evaluated by questionnaire. Then, the relationship between objective index and subjective score was established by machine learning method, and the development of evaluation index was completed. Finally, this paper optimizes the automatic driving motion planning and control algorithm based on this index, and verifies the effectiveness of the algorithm through simulation and another track test.
Mengge Guo, Shiliang Shang, Cui Haifeng, Kaijiong Zhang, Weishun Deng, Xi Zhang, Fan Yu