Sensor Data Fusion in Automotive Applications

Abstract

Sensor data fusion plays an important role in current and future vehicular active safety systems. The development of new advanced sensors is not sufficient enough without the utilisation of enhanced signal processing techniques such as the data fusion methods. A stand alone sensor cannot overcome certain physical limitations as for example the limited range and the field of view. Therefore combining information coming from different sensors broadens the area around the vehicle covered by sensors and increases the reliability of the whole system in case of sensor failure. In general, data fusion is not something innovative in research; a lot has been done for military applications, but it is rather a new approach in the automotive field. The state-ofthe-art in the automotive field is the fusion of many heterogeneous onboard sensors, e.g. radars, laserscanners, cameras, GPS devices and inertial sensors, and the use of map data coming from digital map databases. A functional model very similar to the Joint Directors of Laboratories (JDL), which is the most prevalent in data fusion, is used in automotive fusion. According to this model the data processing is divided to the following levels: signal, object, situation and application. All these levels communicate and exchange data through a storage and system manager. The JDL model is only a functional model which allows different architectures for fusion implementation. These architectures are divided in centralized, distributed and hybrid; each one has advantages and disadvantages. In the data fusion process the main focus is on object and situation refinement levels, which refer to the state estimation of objects and the relations among them, correspondingly. The discrimination between these levels is also made by using the terms low and high level fusion instead of object and situation refinement. There are several vehicular applications that fusion of data coming from many different sensors is necessary. These can be divided into three main categories: longitudinal support, lateral support and intersection safety applications. There is a current tendency to exploit also wireless communications in vehicles. Talking cars forming ad hoc networks may be useful in future applications to cover more safety cases that can not be covered so far, due to physical limitations of onboard sensors. In this way the electronic horizon and the awareness of the driver can be extended even to some kilometres away. A lot of ongoing research is focused on the design of efficient protocols and architectures for vehicular ad hoc networks and on the standardization of this kind of vehicular communication. O pe n A cc es s D at ab as e w w w .in te ch w eb .o rg