Abstract
The presence of adverse road conditions like water, snow, and ice is known to largely increase the chances of road vehicle crashes due to reduced vehicle performance. Providing useful information about future tire-road friction characteristics that will influence vehicle traction and braking capability are essential for safe operation under such weather conditions. This paper describes an approach for using a low-cost camera, vehicle GPS and other basic vehicle sensors on a scaled autonomous vehicle to build a Neural Network for slip-slope prediction. A Recursive Least Squares Filter is used to estimate the longitudinal friction slip-slope. As an alternative to surface classification which requires a labelled data set, this method uses an easily obtained slip-slope to infer tire-road friction levels. A preliminary experiment is conducted which indicates the neural networks effectiveness to distinguish slip-slope values based on previewed road images captured by the vehicle camera.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
