As part of autonomous vehicle projects, car manufacturers are looking for a positioning solution that is accurate, reliable and economically viable.





SYSNAV is experimenting an adapted version of its magneto-inertial technology for cost effective positioning and geolocation of autonomous vehicles. The objective to replace GPS-RTK as it is too expensive for mass production and does not have 100% availability.


The SYSNAV BlueForce AD solution for autonomous vehicle merges sensor data from cameras, LIDAR, GNSS, odometer, cartography  and SYSNAV’s core magneto-inertial positioning technology, using data fusion algorithms,.


To correct the drift of inertial sensors, the SYSNAV module regularly verifies its estimated position by using external information (detection of marks). For example, lane matching uses real time visual recognition to identify the lane separation marks on the roads.


To evaluate the performance of the data fusion algorithms, the calculated positioning is then compared to that of the GPS-RTK module present in the test vehicles. When GPS signal reception conditions are good, GPS-RTK is indeed considered the best positioning information available with ~ 3 cm accuracy.


Conversely, positioning information from the inertial sensors is used to improve the geolocation accuracy of objects used for landmarks detection with “map matching”. Algorithms exploit a means of lateral registration based on fusion between camera data and HD mapping. Test results demonstrate performances comparable to those of GPS-RTK, ie ~ 3 cm accuracy.


Upon the loss of all registration signals (GPS, lane matching, etc.) SYSNAV’s solution can maintain a 30cm accuracy after 15 sec at a speed of 90 km/h  (ie 400 m).





  • Positioning safety for autonomy Levels 3 and beyond

  • Extend hands-off lane-keeping ability for Level 2