Toward Adaptive Driving Styles for Automated Driving with Users' Trust and Preferences

As autonomous vehicles (AVs) become ubiquitous, users' trust will be critical for the successful adoption of such systems. Prior works have shown that the driving styles of AVs can impact how users trust and rely on such systems. However, users' preferred driving style may vary with changes in trust or road conditions, experience, and personal driving preferences. We explore methods to adapt the driving style of an AV to match the preferred driving style of users to improve their trust in the vehicle. We conducted a pilot study ($n=16$) on a simulated urban environment, where the users experience various static and adaptive driving styles for different pedestrian and traffic-related scenarios. Our results indicate that users best trust AVs that closely match their preferences ($p< 0.05$). We believe that exploring the effects of AV driving style on users' trust and workload will provide necessary steps towards developing human-aware automated systems.

I. Introduction and Background

Autonomous driving technologies can potentially change the future of mobility, with increased safety [11]. [29], comfort [12], [26], and social and environmental sustainability [19], [30]. Despite recent technological advancements in the field of artifi-cial intelligence (AI) and robotics, several challenges continue to exist in the widespread deployment of fully autonomous vehicles (AVs) [27] [33] and remain an active area of research [1]. Even if these issues are resolved, prior works have shown that the users' trust is critical for successful acceptance and adoption of autonomous systems [20,[28]. Trust in automation is defined as an “attitude that an agent will help achieve an individual's goals in a situation characterized by uncertainty and vulnerability” [22]. In this work, we examine users' trust in AV s in the context of driving styles. We investigate how users' trust influences their preferred driving style and how to adapt the AV's driving style to improve users' trust.