strategies were built by changing combination of the three kinds of sensors. The
developed navigation planner selected from a priority scheme of the control
strategies using a knowledge-based approach. The average lateral error of the
vehicle guidance based on the fusion of the RTK-GPS and the GDS was 8.4 cm.
The developed sensor fusion methodology with the EKF performed with satisfactory
precision, given that the lateral error was less than the precision of the
RTK-GPS.
The CMU system for autonomous windrowing of hay also used multiple sensors.
The system handled redundant and ambiguous information from sensors using an
arbiter (Ollis and Stentz, 1996).