Ziran Wang
Purdue University, IN·Engineering·Early-career
Automated vehicles keep getting more capable, yet many crashes and failures still happen when people tune out or when the car acts in ways they cannot follow. A core reason is that current systems treat every person the same.
- Fields
Engineering
Computer Science
Psychology
- Topics
automated vehicles
autonomous driving
shared control
- Grants
- 1 known grant, through Sep 2031
What they work on
- Determine how visual attention, spoken language and physical actions reveal a vehicle occupant's cognitive state during interaction with automation, using behavioral sensing.
- Build inference models that estimate a driver's intent from these behavioral signals and track how the intent changes over time.
- Characterize how intent estimates differ across individuals so that automated vehicles can personalize their responses instead of using fixed interaction rules.
- Develop and test a shared-control approach in which the vehicle chooses to act, defer or intervene based on the inferred human state, evaluated in simulation and on an instrumented vehicle.
More about the research
They ignore differences in attention, intentions and decision-making. This project asks how an automated vehicle can act as a partner to its occupant rather than treating them as a passive user. The idea is to make the vehicle's behavior match what the person expects and needs in the moment.
Why it matters
Unsafe handoffs between people and automated vehicles contribute to crashes and erode public trust. Vehicles that read a driver's attention and intent and adjust their behavior could reduce these unsafe interactions and improve trust in automation. That could support wider, safer use of automated transportation. The same methods may carry over to other safety-critical settings where people and intelligent machines work together.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Areen Alsaid
University of Michigan-Dearborn, MI·Engineering
Develop a framework for how driver trust transfers between automation levels and driving contexts, using survey studies that also assess the role of environmental factors.
Xuegang Ban
University of Washington, WA·Engineering
Adapt and scale privacy-preserving techniques so that traffic, trajectory, and naturalistic driving data can be shared securely under both centralized and distributed data-sharing models, and evaluate them on real-world transportation datasets.
Chong Pak
Clemson University, SC·Psychology
Determine how individual differences in working memory and attention control (the ability to focus and resist distraction) relate to how well people perform with automated systems, using newly developed, validated attention control measures.
The school
Purdue University: 43 labs on PI Pages, $932M a year on research, 833 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.