Stefan de Vries, Project Manager & Business Developer, Connected and Automated Vehicles, Applus IDIADA

Abstract: Safety of the intended functionality (SOTIF) is about ensuring the absence of unreasonable risk due to performance limitations, function insufficiencies and foreseeable misuse. Whereas SOTIF verificationfocusses on reduction of the known unsafe scenarios in controlled environments, SOTIF validation aims to disclose unknown unsafe scenarios by virtual simulation and driving on public roads. To reduce the large driving effort required to validate the safety of automated vehicle functions, Applus IDIADA developed a route selection method designed to identify routes with an above-average probability of encountering challenging elements. And to statistically demonstrate reliability, Applus IDIADA developed a method to calculate a target mileage taking human performance as a benchmark.

The field of artificial intelligence (AI) has made significant progress in recent years, with applications ranging from natural language processing to computer vision. In the last years, Applus IDIADA Brakes department has presented several studies about artificial intelligence application for detection of brake noises. In this paper, Applus IDIADA present the research done in this area but focus on the development of an AI model for predicting subjective ratings for squeal brake noises based on objective measurements collected through the instrumentation in a typical brake noise durability. Subjective ratings are based on human opinions and can be challenging to quantify. Objective measurements, on the other hand, can be objectively quantified and provide a more reliable basis for prediction Brake noise is a critical aspect of vehicle performance and can impact the overall customer experience. Currently, subjective assessments of brake noise are made by human drivers evaluators, which can be time-consuming to be trained and high skilled, while results are still based in a subjective. By using the AI model to predict subjective ratings based on objective measurements, this process can be automated and made more consistent. In addition, the use of this tools has the potential to be used in the field of autonomous vehicles. In the near-middle future, there will be no necessity to have a human driver. This also will affect to provide a subjective assessment in the testing area, while squeal brake noises will continue to be an important issue point. In that case, the application of this models will be able to provide these assessments but also ensure that the assessments are consistent with previous historic data and based objective measurements. The study utilized a comprehensive dataset collected during several years of testing of Applus IDIADA. Subjective ratings come from high skilled drivers and, corresponding objective measurements from recorded data through typical brake durability instrumentation. Exploratory data analysis (EDA) was performed to examine the correlation between various variables and to identify any patterns in the data. The EDA showed that there was some correlation between certain objective measurements and subjective ratings. Based on these findings, the most relevant variables were selected to be used in the model. The algorithm was trained on the selected objective measurements and corresponding subjective ratings to learn the relationship between the two. The model was evaluated using several metrics, including accuracy, to determine its performance in predicting subjective ratings based on objective measurements. The results of the study were promising, with the model achieving an important level of accuracy in predicting subjective ratings based on objective measurements, indicating that the model's predictions were close to the actual subjective ratings. This demonstrates the effectiveness of the model in accurately predicting subjective ratings based on objective measurements. In conclusion, the development of an AI model for predicting subjective ratings based on objective measurements is an important step towards the understanding of subjective ratings and objective measurements for brake squeal noise. In addition, the results of this study demonstrate the potential of AI models to be implemented in the near-middle future on autonomous vehicles providing more accurate subjective rating based on objective data. Future work in this area could involve expanding the model to include additional variables or incorporating other machine learning techniques to further improve performance.