Mental States & Machine: Enhancing Driver Engagement in Automated Vehicles for Safer Transitions

Details

• Creators:
  Lo, Wei-Hsiang ; Chu, Aries ; Luo, Yue ; Etu, Egbe-Etu ; Attar, Nada ; Huang, Gaojian
• Corporate Creators:
  San Jose State University
• Corporate Contributors:
  Research and Education in Promoting Safety (REPS) Tier-1 University Transportation Center (UTC) ; United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Autonomous Vehicle Handover Drivers Human Machine Systems Machine Learning Mental Condition
• Publication/ Report Number:
  REPS-HU-25-01
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report (November 2023 - August 2025)
• Corporate Publisher:
  Research and Education in Promoting Safety (REPS) Tier-1 University Transportation Center (UTC)
• Abstract:
  The current automated vehicles are not perfect, which means that human intervention, known as a takeover, is still necessary. For signaling takeover requests, informative (contralateral) displays were investigated and proven effective compared to instructional (ipsilateral) displays. However, how drivers interpret the information can vary based on the driver’s mental state, which remains unclear in earlier research. To address this, the current study aims to investigate the effect of modality (visual and tactile signal), scenario (lane-changing and lane-keeping scenario), mental state (control (baseline), anger, sadness, happiness, internal distraction (mind-wandering), external distraction, and fatigue) on the takeover performance and physiological data. As an exploratory pilot study, six participants were engaged in the current study. Three participants were assigned to the scenario with a visual takeover request, while the other three were assigned to the scenario with a tactile takeover request. The results reveal that lane-keeping was associated with lower decision-making accuracy than lane-changing scenarios. Additionally, the tactile signal request had marginally higher decision-making accuracy than the visual signal. Lastly, the visual signal was associated with a marginally greater change in wrist joint angle compared to the tactile signal in a lane-keeping scenario. Overall, the findings of this study could guide the development of human-machine interfaces to enhance safety under various mental states in future automated vehicles.
• Format:
  PDF
• Funding:
  69A3552348323
• Collection(s):
  University Transportation Centers Autonomous Vehicles
• Main Document Checksum:
  urn:sha-512:40841e4f050e176cd99087cd37d70d27f81433e72e176c44b419db3f72f03f8bb62aa651d11fd2f715c2d5960ff4bc71cf1ea94bb0da222e840e9909f0fcb210
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/86331/dot_86331_DS1.pdf
• File Type:
  [PDF - 901.84 KB ]