Real-World Use of Automated Driving Systems and their Safety Consequences: A Naturalistic Driving Data Analysis

Automated driving systems (ADS) have the potential to fundamentally change transportation, and a growing number of these systems have entered the market and are currently in use on public roadways. However, drivers may not use ADS as intended due to misunderstandings about system capabilities and limitations. Moreover, the real-world use and effects of this novel technology on transportation safety are largely unknown. To investigate driver interactions with ADS, we examined existing naturalistic driving data collected from 50 participants who drove personally owned vehicles with partial ADS for 12 months. We found that 47 out of 235 safety-critical events (SCEs) involved ADS use. An in-depth analysis of these 47 SCEs revealed that people misused ADS in57% of SCEs (e.g., engaged in secondary tasks, used the systems not on highways, or with hands off the wheel). During 13% of SCEs, the ADS neither reacted to the situation nor warned the driver. A post-study survey showed that drivers found ADS useful and usable and felt more comfortable engaging in secondary tasks when ADS were in use. This study also captured some scenarios where the ADS did not meet driver expectations. The findings of this report may help inform the development of human-machine interfaces and training programs and provide awareness of the potential for unintended use of ADS and their associated safety consequences. This research can be downloaded from the Virginia Tech Transportation Institute at https://safed.vtti.vt.edu/wp-content/uploads/2021/01/Safe-D-Final-Research-Report_VTTI-00-029_Final-ready-for-Site.pdf