Experimental Evaluation of Path-Following Performance in a Scaled Autonomous Vehicle: Effects of Localization, Path Geometry, Speed, and Pure Pursuit Look-Ahead Distance

Reliable execution of a planned path is essential for autonomous mobile robots and vehicle-like robot platforms. This study experimentally evaluates the path-following performance of a scaled Ackermann-steered autonomous vehicle under different localization and controller configurations. A QCar 2 platform was operated in a hardware-in-the-loop configuration using a Pure Pursuit lateral controller and a proportional-integral longitudinal speed controller. Two localization approaches were compared in the closed control loop: a kinematic localization method and an Extended Kalman Filter. A full factorial (24) experimental design included the localization method, reference-path geometry (rounded rectangle and figure-eight), commanded speed (0.4 and 0.7 m/s), and Pure Pursuit look-ahead distance (0.3 and 0.6 m), resulting in 16 test configurations. Realized vehicle trajectories were recorded independently using an OptiTrack motion-capture system and compared with the planned paths. Path-following performance was assessed using cross-track error, symmetric Hausdorff distance, and mean bidirectional nearest-neighbor distance. Within the tested runs, differences between the localization variants were small, with mean (CTERMS) values of 0.0929 m and 0.0921 m for the Extended Kalman Filter and kinematic variants, respectively. In contrast, substantially larger differences in trajectory deviations and traveled-path length were observed across path geometries, look-ahead distances, and commanded speeds. The figure-eight path, particularly at the shorter look-ahead distance and higher speed, showed the largest deviations and path-length excess within the tested configurations. The results show that, under the tested laboratory conditions, path-execution quality was more strongly associated with controller tuning and planned-path geometry than with the investigated localization variant. The study provides experimentally validated guidance for selecting path-following parameters for Ackermann-steered autonomous mobile robots.