Research on Automatic Classification for Driving Scenarios Based on Big Data and Ontology

With the rapid development of intelligent connected vehicle technology, the construction of driving scenarios library has become more urgent and important, and its completeness directly determines the perception and decision-making ability of intelligent connected vehicles. To solve the problem of high cost and insufficient coverage for driving scenarios data collection, this research proposes a driving scenarios modeling and automatic classification algorithm based on big data and ontology. Specifically, the driving scenarios are first modeled based on ontology, and the data from multiple sensors are fused to instantiate the driving scenarios model. Furthermore, the scenarios rule base is constructed based on the expert experience and laws. Finally, combining the scenarios rule base and the instantiated scenarios, the inference engine is used to realize the automatic classification of driving scenarios, which provides the basis for further building a more complete driving scenarios library.