Experimental Evaluation of a Speed-Adaptive CBF-Inspired Steering Filter for Low-Speed Ackermann Navigation

This study evaluates a speed-adaptive CBF-inspired steering filter for low-speed Ackermann navigation. A scalar quadratic program (QP) acts as a modular steering filter downstream of the nominal path tracker, while measured vehicle speed scales an adaptive elliptical clearance boundary. Simulation studies use Pure Pursuit and MPC nominal steering controllers, whereas the Quanser QCar uses PI speed regulation with Stanley steering. The constraint is inspired by control barrier function (CBF) filtering and is implemented through a reduced steering-channel control-affine approximation. Filter parameters are tuned in a MATLAB R2024bdigital twin and evaluated on the QCar in a structured indoor environment with static obstacles. In simulation, the filtered configurations avoided the collision observed with the unfiltered Pure Pursuit baseline, at the cost of increased path-tracking error. Five repeated QCar trials at 0.4 m/s completed without collision and produced a mean pairwise dynamic-time-warping distance of 0.070±0.030 m. Across 15 fixed-obstacle QCar experiments, using rectangular footprints of 0.48 m×0.21 m for the vehicle and 0.20 m×0.08 m for the obstacle, the estimated minimum surface-to-surface clearance was 0.274±0.041 m (mean ± sample SD), with a 95% confidence interval for the mean of 0.251–0.296 m and an observed range of 0.209–0.336 m; all 15 trials completed without obstacle contact. The results establish empirical feasibility and quantify the simulated clearance–tracking trade-off within the stated low-speed, static-obstacle operating range.