Fuzzy linguistic reporting in driving simulators

The growth of new intelligent transportation on board systems has increased dramatically drivers´ attention to secondary tasks other than driving. Potential risk of committing mistakes while driving suggests the need to evaluate the onboard systems in order to ensure safe driving practices. An interesting possibility consists of using simulators to perform this evaluation. Simulators can provide analysts with great amount of data describing the performed driving and details about each different situation type. Unluckily, handling this huge amount of information is not easy and to perform a series of repetitive experiments can be very tedious. This application paper deals with the development of a computational system capable of automatically generating linguistic descriptions of driving activity from vehicle simulator data. Based on Fuzzy Logic, and as a contribution towards the development of Computational Theory of Perceptions, the proposed solution is part of our research on granular linguistic models of phenomena. This paper presents a first prototype that is part of a long term practical project devoted to evaluate vehicle onboard systems interacting with professional drivers in different situations. At this stage, we focus on generating simple reports about the quality of driving in a specific context. We have used real time-series data from a vehicle simulator to evaluate the performance of our approach.