Characterizing driver speeding behavior when using partial-automation in real-world driving

Abstract

Objective: Speeding is a prevalent and complex risky behavior that can be affected by many fac-tors. Understanding how drivers speed is important for developing countermeasures, especially asnew automation features emerge. The current study seeks to identify and describe types of real-world speeding behaviors with and without the use of partial-automation. Methods: This study used a combination of supervised and unsupervised data analysis techniquesto assess relevant factors in real-world speeding epochs, extracted from the MIT Advanced VehicleTechnology Naturalistic Driving Study, and classified them into distinct speeding behaviors.Speeding epochs were defined as traveling at least 5 mph over the speed limit for a minimumduration of 3 s. Vehicle speed-exceedance profiles were characterized over time using DynamicTime Warping and included in multivariate models that evaluated the associations between differ-ent features of the speeding epochs, such as speeding duration and magnitude. Finally, the identi-fied features were used to cluster speeding behaviors using the Gower dissimilarity measure. Results: The analysis yielded four types of behaviors in both partially-automated and manual driv-ing: (i) Incidental speeding (low duration, low magnitude), (ii) Moderate speeding (low duration,moderate magnitude), (iii) Elevated speeding (moderate duration, high magnitude), and (iv)Extended speeding (long duration, high magnitude). When comparing the behaviors with andwithout partial-automation use, both Incidental and Moderate speeding were found to have sig-nificantly longer durations with partial-automation than manual driving. Elevated speeding wasfound to be more prevalent and associated with higher magnitudes during manual than with par-tially-automated driving. Finally, although Extended speeding was more prevalent during automa-tion use, it was associated with a lower mean and maximum speed magnitude compared toExtended speeding during manual driving. Conclusions: This work highlights the variability in speeding behavior between and within par-tially-automated and manual driving. The design of systems that mitigate risky speeding behav-iors should consider targeting divergent behaviors observed between manual and automateddriving as a mechanism to mitigate the prevalence of the different behaviors associated witheach state.