摘要: |
Until fully automated vehicles become a reality, drivers must take over vehicle control from driving automation systems, even with little or no advance warning, when the automation encounters its operational boundaries. Empirical studies have shown that such control transitions are challenging for human drivers who are engaged in non-driving related tasks and can lead to relatively long response times and inappropriate responses in the presence of conflicts that are not immediately visible within the driver’s field of view (McDonald et al., 2019). However, most human-machine interfaces (HMI) for takeover requests (TOR) direct the driver back to the vehicle control without providing further information about the dynamic driving situations which is critical for the driver’s situation awareness (SA) and response selection. This work aims to explore HMI approaches to improve driver SA and guide appropriate driver responses in challenging takeover situations. The basic idea is to provide the driver with a coherent and integrated situation representation as well as intervention assistance to help shape the driver’s initial responses. The proposed work will leverage the Virginia Tech Transportation Institute’s (VTTI) virtual reality driving platform that allows the research team to rapidly prototype various HMI options and examine human-subjects’ responses in various takeover scenarios. It is anticipated that the proposed work will identify the most appropriate HMIs to facilitate accurate driver SA and appropriate responses in challenging takeover scenarios. The human-subject experiment will also provide a better understanding of human-machine interaction in takeover situations. The findings would further benefit original equipment manufacturers (OEMs) by informing future design and evaluation of HMIs to enhance driver safety, trust, and acceptance of automated vehicles. |