Gwangju Institute of Science and Technology, School of Integrated Technology, Gwangju 61005, Korea.
Sensors (Basel). 2021 Mar 21;21(6):2206. doi: 10.3390/s21062206.
Autonomous vehicle technology increasingly allows drivers to turn their primary attention to secondary tasks (e.g., eating or working). This dramatic behavior change thus requires new input modalities to support driver-vehicle interaction, which must match the driver's in-vehicle activities and the interaction situation. Prior studies that addressed this question did not consider how acceptance for inputs was affected by the physical and cognitive levels experienced by drivers engaged in Non-driving Related Tasks (NDRTs) or how their acceptance varies according to the interaction situation. This study investigates naturalistic interactions with a fully autonomous vehicle system in different intervention scenarios while drivers perform NDRTs. We presented an online methodology to 360 participants showing four NDRTs with different physical and cognitive engagement levels, and tested the six most common intervention scenarios (24 cases). Participants evaluated our proposed seven natural input interactions for each case: touch, voice, hand gesture, and their combinations. Results show that NDRTs influence the driver's input interaction more than intervention scenario categories. In contrast, variation of physical load has more influence on input selection than variation of cognitive load. We also present a decision-making model of driver preferences to determine the most natural inputs and help User Experience designers better meet drivers' needs.
自动驾驶技术越来越允许驾驶员将主要注意力转移到次要任务上（例如，进食或工作）。这种显著的行为变化因此需要新的输入方式来支持驾驶员与车辆的交互，而这些输入方式必须与驾驶员的车内活动和交互情况相匹配。先前的研究虽然解决了这个问题，但并未考虑到接受输入的方式会如何受到执行非驾驶相关任务（NDRTs）的驾驶员的身体和认知水平的影响，也没有考虑到他们的接受程度会根据交互情况而有所不同。本研究在不同的干预场景下，通过驾驶员执行 NDRTs 来调查与全自动驾驶系统的自然交互。我们向 360 名参与者展示了具有不同身体和认知参与度的四种 NDRTs，并测试了六个最常见的干预场景（24 种情况）。参与者为每个案例评估了我们提出的七种自然输入交互方式：触摸、语音、手势以及它们的组合。结果表明，NDRTs 对驾驶员的输入交互的影响比干预场景类别更大。相比之下，物理负荷的变化对输入选择的影响大于认知负荷的变化。我们还提出了驾驶员偏好的决策模型，以确定最自然的输入方式，帮助用户体验设计师更好地满足驾驶员的需求。
