Investigating Explanations in Conditional and Highly Automated Driving: The Effects of Situation Awareness and Modality

Multi-level explanations improve driver trust: The study found that explanations designed at the "comprehension" level (SA L2)—which help drivers understand why the autonomous vehicle is behaving a certain way, not just what it's doing—generated the highest situational trust among 340 test participants, suggesting that deeper understanding matters more than basic information.

Explanations help drivers stay mentally engaged: By providing explanations based on situation awareness levels, the research showed that drivers could "redirect their attention to the important objects in traffic," indicating that well-designed AI explanations help keep drivers cognitively connected to the vehicle's decision-making even when they're not actively controlling it.

The "out-of-the-loop" problem is real and solvable: As vehicles become more automated, drivers lose awareness of what's happening on the road. This study demonstrates that explanations specifically designed to address this gap—helping drivers perceive, comprehend, and anticipate traffic situations—can meaningfully improve both understanding and trust in automated systems.

How explanations are delivered matters: The research tested both visual-only and visual-plus-audio explanations, suggesting that the modality (format) of explanations affects how well drivers understand autonomous vehicle behavior, though the abstract doesn't specify which combination performed best.