To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles
To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles
复制标题
解释还是不解释：自动驾驶汽车解释必要性研究
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Katherine Driggs Campbell
中科院分区：
文献类型：
--
作者：
Yuan Shen;Shanduojiao Jiang;Yanlin Chen;E. Yang;Xilun Jin;Yuliang Fan;Katherine Driggs Campbell
在自动驾驶系统的背景下，如自动驾驶汽车，可解释的人工智能引起了研究人员的广泛兴趣。最近的研究发现，为自动驾驶车辆的动作提供解释有很多好处，例如，增加信任和接受，但很少强调何时需要解释以及解释的内容如何随上下文而变化。在这项工作中，我们调查的情况下，人们需要解释，以及如何解释的关键程度与情况和驱动程序类型的变化。通过用户实验，我们要求参与者评估解释的必要性，并测量在不同情况下对他们对自动驾驶汽车信任的影响。我们还提出了一个自驾车解释数据集，其中包含第一人称解释和1103个视频片段的必要性的相关度量，增强了伯克利深度驱动注意力数据集。此外，我们提出了一个基于学习的模型，预测如何必要的解释一个给定的情况下，在真实的时间，使用相机数据输入。我们的研究表明，驱动程序类型和上下文决定了是否需要解释，以及什么有助于改善互动和理解。
Explainable AI, in the context of autonomous systems, like self driving cars, has drawn broad interests from researchers. Recent studies have found that providing explanations for an autonomous vehicle actions has many benefits, e.g., increase trust and acceptance, but put little emphasis on when an explanation is needed and how the content of explanation changes with context. In this work, we investigate which scenarios people need explanations and how the critical degree of explanation shifts with situations and driver types. Through a user experiment, we ask participants to evaluate how necessary an explanation is and measure the impact on their trust in the self driving cars in different contexts. We also present a self driving explanation dataset with first person explanations and associated measure of the necessity for 1103 video clips, augmenting the Berkeley Deep Drive Attention dataset. Additionally, we propose a learning based model that predicts how necessary an explanation for a given situation in real time, using camera data inputs. Our research reveals that driver types and context dictates whether or not an explanation is necessary and what is helpful for improved interaction and understanding.