ERI: Investigate the Role of Affect in Fostering Trust in Automated Driving

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。该工程研究启动（ERI）拨款将支持与自动驾驶中信任影响作用相关的新知识，促进人类驾驶员和自动驾驶汽车之间的关系。人类的心智有情感和认知两个部分。自动化中的信任也是如此，但情感是信任行为的主要决定因素。然而，自动化的信任影响的研究是稀缺的。因此，研究情感在自动驾驶汽车信任中的作用至关重要。该项目的总体目标是探索影响在自动驾驶中基于信任的交互中的作用。为了实现总体目标，将追求三个综合目标，即：1)使用心理生理学测量建立实时信任预测模型，2）调查自动驾驶车辆中情感与信任之间的关系，3）使用情感测量校准自动驾驶车辆中的信任。 一旦识别出相关的心理生理测量，它们就可以用于构建实时信任预测模型，并且一旦识别出基于信任的交互中的情感的潜在结构与自动驾驶汽车中的信任之间的关系并且构建实时信任预测模型，情感可以帮助使用情感分析来构建和校准自动驾驶汽车中的驾驶员信任。因此，这项研究的结果将促进科学和国民健康的进步（例如，防止碰撞），推进我们对自动驾驶及其他领域基于信任的双向交互的理解。首先，本研究将使用心理生理学措施建立实时信任预测模型，这可以克服以往研究的局限性，主要是在会话结束时测量一次信任或两次作为前和后的信任水平，这并没有反映自动化中信任的动态性质。其次，本研究将通过检查与自动驾驶中的信任相关的情感反应的潜在结构以及情感反应如何与信任的不同方面相关，来调查自动驾驶车辆中情感与信任之间的关系。第三，本研究将通过使用自我报告和心理生理数据测量的自动驾驶中的情感启发来检查情感的作用。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).This Engineering Research Initiation (ERI) grant will support research that will contribute new knowledge related to the role of affect in trust in automated driving, promoting the relationships between human drivers and automated vehicles. The human mind has the affective and cognitive components. So does trust in automation, but affect is the primary determinant of trusting behavior. However, studies of affect on trust in automation are scarce. Therefore, it is critical to examine the role of affect in trust in automated vehicles. The overall objective of the project is to explore the role of affect in trust-based interaction in automated driving. In order to attain the overall objective, three integrated aims will be pursued, i.e., 1) build real-time trust prediction models using psychophysiological measures, 2) investigate the relations between affect and trust in automated vehicles, and 3) calibrate trust in automated vehicles using affect heuristics. Once relevant psychophysiological measures are identified, they can be used to build real-time trust prediction models and once the relationships between the latent structure of affect in trust-based interaction and trust in AVs are identified and the real-time trust prediction model is built, affect can help build and calibrate driver trust in AVs using affect heuristics. Hence, the results from this research will promote the progress of science and national health (e.g., preventing crashes) by advancing our understanding of bidirectional trust-based interaction in automated driving and beyond. First, this research will build real-time trust prediction models using psychophysiological measures, which can overcome the limitations of previous research that mainly measured trust once at the end of a session or twice as pre- and post- levels of trust, which did not reflect the dynamic nature of trust in automation. Second, this research will investigate the relations between affect and trust in automated vehicles by examining the latent structure of affective responses related to trust in automated driving and how affective responses are related to different aspects of trust. Third, this research will examine the role of affect by making use of affect heuristic in automated driving measured by both self-reported and psychophysiological data. Such research endeavors will help understand the role of affect in trust in automated driving.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.