arbiter
JournalsPricingAccount

Multimodal attention-guiding takeover alerts in autonomous driving: Comparing visual, auditory, and combined modalities

Zi Dong et al.

International Journal of Industrial Ergonomics2026https://doi.org/10.1016/j.ergon.2026.103879article
AJG 2
Weight
0.50

What the paper says

In the current phase of autonomous driving, drivers are still required to take over the vehicle when the driving environment exceeds the operating design domain of the system or when a failure occurs. This study focuses on the impact of visual-auditory attention-guiding takeover alerts on driver performance and subjective user experience during emergency takeovers. Twenty-eight young participants with advanced driver assistance systems (ADAS) experience were recruited for the experiment. This study involved four combinations of multimodal attention-guiding stimuli, and participants were asked to perform non-driving-related tasks (NDRTs) and takeover tasks in simulated scenarios. Takeover reaction times, eye-tracking data, situational awareness, and subjective evaluations were recorded under four stimulus conditions (Baseline, V-AG, A-AG, and VA-AG). This study found that attention-guiding takeover alerts significantly improved driver performance, situational awareness, comfort, and satisfaction. Multimodal visual-auditory attention-guiding takeover alerts outperformed unimodal alerts in enhancing situational awareness and the overall subjective takeover experience. However, auditory-only attention-guiding alerts were more effective in significantly shortening the time required for drivers to complete the takeover task. • Investigates how different attention-guiding alerts affect takeover performance. • Compares unimodal and multimodal takeover alerts in autonomous driving. • Evaluates alert effectiveness using SAGAT scores and AOI eye-tracking measures. • Provides new insights into takeover alert design for autonomous vehicles. • Discusses the balance of multimodal information in takeover alerts.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1016/j.ergon.2026.103879

Or copy a formatted citation

@article{zi2026,
  title        = {{Multimodal attention-guiding takeover alerts in autonomous driving: Comparing visual, auditory, and combined modalities}},
  author       = {Zi Dong et al.},
  journal      = {International Journal of Industrial Ergonomics},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1016/j.ergon.2026.103879},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Multimodal attention-guiding takeover alerts in autonomous driving: Comparing visual, auditory, and combined modalities

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.