This work aims to investigate how disturbance-aware, robustness-embedding
reference trajectories translate into actual driving performance when executed
by professional drivers in a dynamic driving simulator. The study compares three
planned reference trajectories against a free-driving baseline (NO-REF) to
assess the trade-offs between lap time (LT) performance and steering effort:
NOM, the nominal time-optimal trajectory; TLC, a track-limit-robust,
time-optimal trajectory obtained by tightening margins to the track edges; and
FLC, a friction-limit-robust, time-optimal trajectory obtained by tightening
against axle/tire saturation. All reference trajectories share the same minimum
LT objective with a small steering-smoothness regularizer, and are evaluated
with two professional drivers driving a high-performance car on a virtual
track.
The reference trajectories stem from a disturbance-aware
minimum-LT framework recently proposed by some of the authors, where worst-case
disturbance growth is propagated over a finite horizon and used to
tighten tire-friction and track-limit constraints,
preserving performance while delivering probabilistic safety margins.
LT and steering energy (SE) are evaluated as indicators of driving performance
and steering effort, respectively, while RMS values of lateral deviation, speed
error, and drift angle are used to characterize driving style. The results
reveal a Pareto-like trade-off between LT and SE: NOM achieves the shortest LT,
but with the highest SE, TLC minimizes SE at the expense of longer LT, while FLC
lies near the efficient frontier, markedly reducing SE relative to NOM with only
a minor LT increase. Removing reference trajectories (NO-REF) leads to both
higher SE and longer LT, confirming that trajectory guidance improves pace and
control efficiency. Overall, the findings highlight reference-based and
disturbance-aware planning, particularly the FLC variant, as effective tools for
training and for achieving fast yet stable trajectories.
