With autonomous vehicles becoming more common and established, there are some problems to overcome before their full potential can be reached. One of these problems is the lack of information about the condition of the road, which traditionally would be acquired from the driver operating the vehicle. Volvo Autonomous Solutions are developing an autonomous hauler, made for operating in off-road workplaces, such as quarries and mines. In these off-road workplaces, road maintenance is limited and often performed only when deemed necessary by a driver. This thesis investigates the issue of detecting irregularities in the road on an autonomous vehicle. To achieve this data from an Inertial Measurement Unit (IMU) and a Global Navigation Satellite System (GNSS) unit mounted on the vehicle is collected, analysed, and classified to find any irregularities in the road. In order to improve confidence in the classification of the irregularities, false positives are reduced by using an occupancy grid solution. The results show that the use of IMU data can be used to detect irregularities and that the use of an occupancy grid increases the confidence of detected irregularities.