A multisensor localization algorithm for mobile robots and its real-time experimental validation

We present a localization system which computes, by extended Kalman filtering, the position and heading of a vehicle using both odometry and the measurement of the relative azimuth angles of known landmarks. Observability of the continuous system is studied and gives information on situations where the performance of the filter may deteriorate. Results of extensive real outdoor experiments with a wheel-type robot moving on a slightly uneven floor are reported. We show that the system achieves a precision of a few centimetres.