Team : imara
Section: Scientific Foundations
Sensors and information processing
Sensors and single-sensor information processing
The first step in the design of a control system are sensors and the information we want to extract from them, either for driver assistance or for fully automated guided vehicles. We put aside the internal sensors which are rather well integrated. Internal sensors give information on the host vehicle state, such as its velocity and steering angle information. The necessary information from external sensors (Laser, Radar, image sensors, etc.) are of several types:
localization of the vehicle with respect to the infrastructure, i.e. lateral positioning on the road can be obtained by mean of vision (lane markings) or by mean of magnetic, optic or radar devices;
localization of the surrounding vehicles and determination of their behavior can be obtained by a mix of vision, laser or radar;
detection of obstacles other than vehicles: pedestrians, animals objects on the road etc. that require many types of sensors.
Since INRIA is very involved in image processing, IMARA emphasize the vision technique, particularly stereo-vision, in relation with MIT and ENSMP.
Multi-sensor data fusion
The next research problem is the multi-sensor data fusion system consisting of a set of internal and external sensors which information is fused within one data fusion unit. The different sensor processing units deliver processed information about the road geometry (curvature, etc.). They also deliver information about relevant objects detected in the vicinity of the vehicle. The fusion involves as its name implies the processing of various informations coming from different sensors in order to get a better picture of the environment of the vehicle. Two different sensors, apart from providing different coverage, can detect the same object, but with differing accuracy of the parameters (for instance, range and angle) describing that object. This information is complimentary, and leads to a measurement of higher integrity, accuracy and confidence. In addition to this, certain sensors may see information ``invisible'' to other sensors, such as video's ability to locate road markings. This too assists in improving the positioning of objects with respect to the real-world, rather than the subject vehicle.
Since IMARA aims at integrating different techniques into real-world vehicles, it is implied into the development of data fusion work packages, i.e. in the CARSENSE project.
Sharp, Icare, Fractales.