Ongoing Research Projects

Our research advances human-centered AI and adaptive systems that coordinate with people as their states, goals, and capabilities evolve.

NSF EDSE automation intervention project graphic
Sponsor: NSF EDSE PIs: Yunmei Liu and David Kaber

Funded ProjectCognitive-Emotional State Assessment for Adaptive Automation Intervention

This project aims to develop an integrated cognitive-emotional state assessment system to support real-time automation intervention and adaptive system design. By combining physiological sensing, behavioral performance data, and machine learning, the project aims to detect changes in human cognitive workload, emotional state, and task engagement during human-automation interaction.

The resulting models will help identify when and how automation should intervene, adapt, or provide support in order to improve safety. This work contributes to the design of human-centered automation systems that respond not only to task conditions, but also to the evolving cognitive and emotional states of the human operator.

Website
AI-enabled virtual reality manufacturing foundry project graphic
Sponsor: NSF FINDERS FOUNDRY PI: Yunmei Liu

Funded ProjectAI-Enabled Virtual Reality Manufacturing Foundry

This NSF FINDERS FOUNDRY Planning project develops an AI-enabled virtual reality platform to help high school students explore modern manufacturing careers. The platform will provide safe, accessible, and authentic opportunities for students to learn manufacturing workflows, practice decision-making, and interact with a supportive AI mentor.

By making advanced manufacturing careers more visible and engaging, the project aims to strengthen students’ interest in manufacturing pathways and help them understand AI as a transparent learning support for feedback, reflection, and problem solving.

Aggressive Driving project graphic
Sponsor: UofL Jon Rieger Seed Grant PI: Yunmei Liu

Funded ProjectAggressive Driving in Mixed Traffic

This project studies how aggressive driving behaviors in mixed human-AV traffic propagate from individual driver state and local maneuvers to traffic-flow safety and efficiency. The work combines CARLA-SUMO human-in-the-loop experiments, empirical human driver modeling, SUMO/TraCI traffic-flow simulation, and human-aware adaptive AV control to understand how surrounding AV aggressiveness and human driver aggressiveness shape workload, trust, stress, speed choice, braking, lane changes, congestion, and surrogate safety outcomes.

Presentation 1: HFES 2025

Publications From This Project

  1. Das, U.*, Chen, Y.*, Chowdhury, M. H.*, and Liu, Y.† (2026). A vision-based multimodal framework for quantifying novice driver behavioral responses to aggressive overtaking in continuous simulator traffic. International Conference on Applied Human Factors and Ergonomics. Accepted.
  2. Chen, Y.*, Chowdhury, M. H.*, and Liu, Y.† (2026). From driver intent to road-user perception: a narrative and systematic review of perceived aggressive driving. International Conference on Applied Human Factors and Ergonomics. Accepted.

Video Demo

This demo illustrates a representative aggressive-overtaking scenario in continuous mixed-traffic simulation and demonstrates the behavioral responses detected using our vision-based multimodal framework. It accompanies the study: Das, U.*, Chen, Y.*, Chowdhury, M. H.*, and Liu, Y.† (2026), “A Vision-Based Multimodal Framework for Quantifying Novice Driver Behavioral Responses to Aggressive Overtaking in Continuous Simulator Traffic,” International Conference on Applied Human Factors and Ergonomics (AHFE), accepted.

Teen Driver Safety Education project graphic
Sponsor: NHTSA with KYTC PI: Yunmei Liu

Funded ProjectTeen Driver Safety Education

This project develops a simulator-ready curriculum package to support teen driver safety education in Kentucky high schools. The work will align teacher lesson plans, student materials, classroom debriefs, and an interactive driving scenario with KYTC and KOHS safety messaging on distracted driving and aggressive driving.

The project will integrate a classroom rotation model, driving-log feedback on behaviors such as speed choice, following distance, braking, and hazard response, and an optional wearable-sensor component that provides a student-friendly driver-state snapshot. A classroom pilot will assess the module's feasibility and learning value before the final toolkit is delivered for use by educators and transportation safety partners.

EMG-based upper-limb prosthetic control evaluation setup
Sponsor: NA

Human-Centered Design for Natural Upper-Limb Prosthetic Control

This project focuses on advancing upper-limb prosthetic control from conventional control modes toward more natural and intuitive control. Our prior work compared alternative prosthetic control strategies, generated workload and usability evidence for early-stage design, and examined VR as a scalable platform for testing prosthetic manipulation tasks before full physical-device deployment. Together, these studies provide human-centered design guidance for selecting and refining prosthetic control interfaces that better align with users’ movement intentions, improve performance, reduce workload, and support rehabilitation training.

Seizure-EEG project graphic
Sponsor: NA

AI-Driven Scalp EEG Modeling for Seizure Detection and Signal Enhancement

We develop AI methods that transform multichannel scalp EEG into spatial, visual, and geometry-aware representations for neurological condition detection. This work supports robust seizure detection, EEG spatial super-resolution, and reliable biomedical signal modeling for real-time and clinically meaningful assessment.

Communication Barriers project graphic
Sponsor: NA

Communication Barriers in Patient-Provider Interactions

This project examines how communication barriers disrupt patient-provider communication and affect patient experience, clinical decision-making, health outcomes, and healthcare system efficiency. Building on a scoping review of patient-provider communication studies, the work maps how barriers intersect and identifies intervention opportunities including interpreter services, cultural and empathy training, plain-language and visual supports, AI-enabled translation and chatbot tools, clinical note-taking agents, and wearable or remote-monitoring technologies. The goal is to inform adaptive, patient-centered communication systems that combine AI support with real-time human-state and context awareness.

Research-Related News

View all news

Showing all 21 news items.