Quantcast

Ann Arbor Times

Thursday, September 25, 2025

University of Michigan study finds matching voices boost trust in self-driving cars

Webp domenicograsso

Domenico Grasso, President | University of Michigan Ann Arbor

Domenico Grasso, President | University of Michigan Ann Arbor

A recent study from the University of Michigan has found that the voice used by automated vehicles (AVs) can significantly affect how much people trust these self-driving cars. The research, presented at the annual meeting of the Human Factors and Ergonomics Society, focused on how similarities between a car’s voice and its driver—especially gender—can influence both logical and emotional trust in AVs.

Researchers surveyed over 300 U.S. drivers who watched videos of an AV operating while listening to different voices explaining its actions. Participants rated their level of trust after each video. Results showed that when the car’s voice matched both the user’s gender and traditional gender roles, participants reported higher levels of cognitive (logical) and affective (emotional) trust. If only gender matched but not traditional gender roles, emotional trust increased but not logical trust.

The study suggests that designing more personalized or customizable voices for AVs could make users feel more comfortable with self-driving technology. It also raises concerns about reinforcing stereotypes through reliance on traditional gender roles in voice design, recommending alternatives such as gender-neutral or nonhuman sounds.

“These findings highlight the importance of considering gender in AV voice design for conveying critical driving information and reveal how societal stereotypes shape AV design,” said Lionel Robert Jr., U-M professor of information and robotics.

“Designing AV voices to feel more personal and relatable could make people more comfortable trusting them,” said Qiaoning (Carol) Zhang, assistant professor at Arizona State University and lead author of the study.

X Jessie Yang, co-author and U-M associate professor, noted that public acceptance is important even for those who do not plan to own a self-driving car: “Even if you never plan to own a self-driving car, you will almost certainly share the road with them. Building trust in these vehicles is crucial for public safety and the seamless integration of automated cars into our transportation system.”

As automated vehicle adoption faces skepticism due to safety concerns—a challenge noted across studies—voice design may be one tool developers use to improve public confidence in this emerging technology.