The growth of the automobile Industry in the past 50 years is radical. The development of chassis control systems have grown drastically due to the demand for safer, faster and more comfortable vehicles. For example, the invention of Anti-lock Braking System (ABS) has resulted in saving more than a million lives since its adaptation while also allowing the vehicles to commute faster. As we move into the autonomous vehicles era, demand for additional information about tire-road interaction to improve the performance of the onboard chassis control systems, is high. This is due to the fact that the interaction between the tire and the road surface determines the stability boundary limits of the vehicles. In this research, a real-time system to classify the road surface into five major categories was developed. The five surfaces include Dry Asphalt, Wet Asphalt, Snow, and Ice and dry Concrete. tri-axial accelerometers were placed on the inner liner of the tires. An advanced signal processing technique was utilized along with a machine learning model to classify the road surfaces. The instrumented Volkswagen Jetta with intelligent tires was retrofitted with new instrumentation for collecting data and evaluating the performance of the developed real-time system. A comprehensive study on road surface classification was performed in order to determine the features of the classification algorithm. Performance of the real-time system is discussed in details and compared with offline results. / Master of Science / The automobile industry has been improving road transportation safety over the past 50 years. While we enter the autonomous vehicles era, the safety of the vehicle is of primary concern. In order to get the autonomous vehicles to production, we will have to improve the on board vehicle control systems to adapt to all surfaces. Gaining more accurate information about the tire and road interaction will help in improving the control systems. Tires have always been considered a passive element of the vehicle. However, more recently, the idea of “tire as a sensor” has surfaced and has become one of the major research thrusts in tire as well as vehicle companies. The intelligent tire research at the Center for Tire Research (CenTiRe) begun in 2010 and has been going strong. In this work, we have developed a classification algorithm to classify the road surfaces in real-time based on acceleration measured inside the tire. The information regarding the road surface would be highly beneficial for the developing new control strategies, automate service vehicles and aid surface prediction in autonomous vehicles.

Modern day cars are often equipped with a variety of sensors that collect information about the car and its surroundings. The stereo camera is an example of a sensor that in addition to regular images also provides distances to points in its environment. This information can, for example, be used for detecting approaching obstacles and warn the driver if a collision is imminent or even automatically brake the vehicle. Objects that constitute a potential danger are usually located on the road in front of the vehicle which makes the road surface a suitable reference level from which to measure the object's heights. This Master's thesis describes how an estimate of the road surface can be found to in order to make these height measurements. The thesis describes how the large amount of data generated by the stereo camera can be scaled down to a more effective representation in the form of an elevation map. The report discusses a method for relating data from different instances in time using information from the vehicle's motion sensors and shows how this method can be used for temporal filtering of the elevation map. For estimating the road surface two different methods are compared, one that uses a RANSAC-approach to iterate for a good surface model fit and one that uses conditional random fields for modeling the probability of different parts of the elevation map to be part of the road. A way to detect curb lines and how to use them to improve the road surface estimate is shown. Both methods for road classification show good results with a few differences that are discussed towards the end of the report. An example of how the road surface estimate can be used to detect obstacles is also included.