Friction and Road Condition Estimation using Dynamic Bayesian Networks*

An essential factor in ensuring driving stability and traffic safety of vehicles is knowledge about road condition and maximum tire-road friction potential. In previous research systems that either measure friction-related parameters or estimate the friction coefficient via a mathematical model have been proposed. However, the performance of these systems can be negatively impacted by environmental factors or require sufficient excitation in the form of tire slip, which is often too low under practical conditions. Therefore, this paper investigates if a more robust estimation can be achieved by fusing the information of multiple sources using a dynamic Bayesian network, which models the statistical relationship between different heterogeneous sources of information and the maximum friction coefficient. The algorithm is applied to data from a passenger vehicle to demonstrate the performance under real conditions. By using the dynamic Bayesian network the error can be reduced by up to 50%. To our knowledge this is the first time a dynamic Bayesian network is used to estimate road condition and friction coefficient.