Bibliographic Details
| Title: |
Personalized Active Camber Control for Path Following Assistance: a Non-interference Approach. |
| Authors: |
Chen, Zhengliang1 (AUTHOR), Wang, Wei2 (AUTHOR) wangwei@iis.u-tokyo.ac.jp, Raksincharonsak, Pongsathorn1 (AUTHOR) |
| Source: |
International Journal of Automotive Technology. Apr2026, Vol. 27 Issue 2, p459-473. 15p. |
| Subjects: |
Driver assistance systems, Alignment of automobile wheels, Machine learning |
| Abstract: |
− With the advancement of intelligent vehicle technologies, the development of advanced driver assistance systems (ADAS) is extending beyond conventional active safety functions such as emergency braking and lane keeping, aiming at achieving human-vehicle shared control under more general driving scenarios. However, traditional ADAS technologies, such as steer-by-wire systems, may affect steering torque feedback and consequently influence the driver's haptic perception, thereby complicating the design process due to potential interference issues. This study proposes and investigates a non-interference steering assist ADAS design based on tire alignment adjustments for the path following purpose, with special focus on the tire camber angle control. Based on feed-forward control laws, theoretical analysis and test verification reveal that increasing the response in yaw motion potentially enhances the driver-vehicle cooperation and therefore improves the path following performances. As to further adjust the control gain in an adaptive manner considering individual differences of drivers, an attention mechanism-based multi-layer perception (AM-MLP) is designed and trained using the collected driving data of novice drivers. Verification tests through driving simulator highlight the effects of personalized non-interference steering assist ADAS method on improving the human-vehicle closed-loop performances without increasing the driving stress. [ABSTRACT FROM AUTHOR] |
|
Copyright of International Journal of Automotive Technology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |