In a pre-post experiment (n = 41), we test the impact of an AI Coach's explanatory communications modeled after the instructions of human driving experts. Participants were divided into four (4) groups to assess two (2) dimensions of the AI coach's explanations: information type ('what' and 'why'-type explanations) and presentation modality (auditory and visual). We directly compare how AI Coaching sessions employing these techniques impact driving performance, cognitive load, confidence, expertise, and trust in an observation learning context. Through interviews, we delineate the learning process of our participants. Results show that an AI driving coach can be useful for teaching performance driving skills to novices. Comparing between groups, we find the type and modality of information influences performance outcomes. We attribute differences to how information directed attention, mitigated uncertainty, and influenced overload experienced by participants. These, in turn, affected how successfully participants were able to learn. Results suggest efficient, modality-appropriate explanations should be opted for when designing effective HMI communications that can instruct without overwhelming. Further, they support the need to align communications with human learning and cognitive processes. Results are synthesized into eight design implications for future autonomous vehicle HMI and AI coach design.

翻译：在一项前测-后测实验（n=41）中，我们测试了以人类驾驶专家指令为模型的AI教练解释性沟通的影响。参与者被分为四组，以评估AI教练解释的两个维度：信息类型（“是什么”和“为什么”类解释）和呈现模式（听觉和视觉）。我们直接比较了在观察学习情境中，采用这些技术的AI教练环节如何影响驾驶表现、认知负荷、自信度、专业知识和信任。通过访谈，我们描绘出参与者的学习过程。结果表明，AI驾驶教练在向新手传授性能驾驶技能方面具有实用价值。组间比较发现，信息的类型和模式会影响表现结果。我们将差异归因于信息如何引导注意力、缓解不确定性以及影响参与者所经历的负荷过载。这些因素进而决定了参与者能否成功学习。研究建议，在设计有效且不过度负担用户的HMI通信时，应优先采用高效且符合模态特点的解释。此外，研究支持了将通信与人类学习和认知过程对齐的必要性。研究结果被综合为未来自动驾驶车辆HMI和AI教练设计的八项设计启示。