Computational modeling study demonstrates accurate takeover time prediction across multimodal sensory cues in automated driving, highlighting its utility for designing safer vehicle transitions.
In conditionally automated driving, takeover time (TOT) is critical for ensuring a safe transition from automated to manual control. Existing TOT prediction models provide limited explanations of the multimodal cognitive processes underlying takeover responses across contexts. This study proposes QN-MHPV2, a physiologically grounded cognitive model based on Queueing Network–Model Human Processor theory. It constrains the processing and integration of multimodal warning cues (visual, auditory, and tactile) within functional brain networks using neuroscientific and physiological evidence. It enables information-processing routes whose selection is modulated by modality × warning-parameter settings × environmental context, and it models inter-regional neural transmission delays in TOT computation. Calibrated using a driving-simulator experiment, QN-MHPV2 explains TOT variability with R2 = 0.9084 and reproduces TOT variation trends reported in ten prior studies (R2 = 0.9325). The model provides an interpretable, simulation-based tool for takeover-request design and strategy screening.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: