发表机构
Toyota Research Institute（丰田研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述系统梳理九个受损驾驶领域的91项研究，提出性能退化与事件响应范式及成熟度框架，揭示方法学异常，并建议标准化以促进跨领域检测与辅助系统开发。
AI 中文摘要
受损驾驶，包括分心、疲劳和中毒，每年导致数千人死亡。受损检测及相关辅助技术正在迅速发展，但其全部潜力仍未得到实现。受损研究成熟度的不一致以及各领域内部的异常现象是关键障碍，包括分类学特征描述、实验数据收集方法以及研究中受损处理的差异。我们提出了一项统一的受损研究综述，涵盖九个受损领域的91项研究，并在三个维度上进行编码：受损诱导方法、场景危险以及可观察现象和指标。我们的主要发现包括：（1）针对现有受损领域提出的性能退化与事件响应范式；（2）沿三个维度的成熟度框架；（3）对受损研究方法的分析，揭示了场景和指标处理中的异常与空白。我们进一步提出了标准化方法的建议，以支持未来跨领域研究以及整体检测和辅助系统的开发。
英文摘要
Impaired driving, including distraction, fatigue, and intoxication, leads to thousands of fatalities annually. Impairment detection and related assistive technologies are rapidly advancing, but their full potential remains unrealized. The inconsistent maturity of impairment research and anomalies within individual domains are key barriers, including variations in taxonomic characterization, experimental data-collection methodologies, and treatment of impairments across studies. We present a unified review of impairment studies, covering 91 studies across nine impairment domains coded on three dimensions: impairment induction methods, scenario hazards, and observable phenomena and metrics. Our key findings include: (1) a proposed performance-degradation vs. event-response paradigm for existing impairment domains, (2) a maturity framework along the three dimensions, and (3) an analysis of impairment research methodologies, revealing anomalies and gaps in the treatment of scenarios and metrics. We further propose recommendations for standardizing methodologies to support future cross-domain research and development of holistic detection and assistive systems.
Comments23 pages, 1 figure. To be published in the 18th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI '26) September 20-23, 2026, Gothenburg, Sweden
