<b>Just the Two of Us: A Novel Exploration into Perception and Performance of Human-Autonomous Vehicle Teaming (HAVT)</b>

<p dir="ltr">Human – Agent Teaming (HAT) is a rapidly emerging research field that seeks to combine human and non-human agent capabilities to enhance performance, efficiency, and safety of mutual tasks across various domains. In the driving context, the idea of a driver ‘teaming’ with a semi-autonomous vehicle (AV) is a relatively novel concept. However, this framing could significantly help to improve driver’s interactions with highly autonomous vehicles, thereby promoting safety in surface transportation systems. To date, frameworks and models have been developed to study HAT within driving. However, as a first step, there have been no investigations into whether current drivers of semi-AVs perceive their vehicles to be teammates or simply intelligent tools. Also, very few empirical studies have quantified how drivers team with semi-AVs. This dissertation proposes to take first steps towards addressing this research gap in three phases.</p><p dir="ltr">In the first study, an online survey was developed and deployed using a crowdsourcing platform to understand the perceptions current owners of Society of Automotive Engineers (SAE) L2 and L3 (partially and conditionally automated vehicles, respectively) have toward viewing themselves as teammates with their semi-AVs. More than 50% of drivers currently do or could one day in the future view their semi-AV as a teammate. In the second study, using knowledge gained in the first study, an in-lab driving simulation study was conducted to examine the effects of agent availability (driver and vehicle) via agent communication (i.e., in-vehicle displays) on select human – AV teaming (HAVT) outcomes. Most drivers felt an overall sense of teaming that was associated with moderately high trust, lower physical effort, and a general sense of productivity during the driving task. The final study examined communication modalities for agent collaboration. The goal was to understand whether the way in which the vehicle communicates with the driver (text vs. speech) influences HAVT outcomes. This work can help provide a fundamental understanding of the psychology of semi-AV drivers, which can inform the design of in-vehicle displays that intelligently support coordination, cooperation, and collaboration within HAVT contexts.</p>