Linux 32/64 bits, 2.6 kernel

7 – 1.6 GHz min, 2GB RAM


The hyrid fusion package is dedicated to outdoor vehicle positioning based on combination of differents sensor sources such as GPS, odometers and IMUs (Inertial Measurement Units).

Localization,Data fusion,ADAS

Compared to using a single standard GPS receiver, it provides the following features:

  • high frequency positioning service (up to 50 Hz)
  • accurate relative positioning
  • continuity of service in GPS outage zones (tunnels, urban areas with buildings, forests, etc.)

The hybrid fusion package implements Interacting Multiple Model (IMM) and Extended Kalman filter (EKF) data fusion algorithms.

IMM, contrary to classical methods, is based on the discretization of the vehicle evolution space into simple maneuvers. Each maneuver is represented by a simple dynamic model such as a constant velocity or a constant turning model. This allows the method to be optimized for highly dynamic vehicles. In this package, the Hybrid Fusion module allows to take into account unusual vehicle maneuvers during some special driving situations, including very strong accelerations, high speed turnings or backwards driving with stop stages. Moreover this package includes some additional modules allowing the generic formatting of the sensors data (Odometer, INS, GPS) in order to be easily usable by Hybrid Fusion module. A bird view module is also provided in order to display the result of this positioning algorithm.