Flexible on-board stream processing for automotive sensor data

Vehicle testing and diagnosis requires huge amounts of data to be gathered and analyzed. Not all possibly interesting data can be stored because of the limited memory available in a tested vehicle. On-board preprocessing of data and decisions about which information has to be kept or omitted is thus vital for vehicle testing routines. This paper introduces a method for flexible on-board processing of sensor data of a vehicle. The approach is motivated by sensor network ideas and makes use of stream processing techniques. A processing graph model for automotive applications is proposed, which consists of operator nodes and connecting data streams. This model supplies both recording and processing functionality together. To account for dynamic changes of conditions within a vehicle—most of the time only a small portion of the vehicle states are interesting for diagnosis—both the model and actual software are built in such a way that the whole system can automatically be adapted at runtime whenever certain conditions are detected. The proposed stream processing model has been implemented in a proof-of-concept industrial application, that was deployed to an automotive on-board unit. Results show that this approach effectively trades a little more on-board processing power for a large data volume, that does not need to be saved and transmitted for off-board usage anymore.