Adaptive Generative UI
2025 Jun – 2026 Jan · UX Engineer Intern
In-vehicle interfaces are static. They show the same things the same way, forcing drivers to dig for information at the exact moments road conditions, fatigue, or hazards make digging dangerous.
Design challenge: Compose the interface itself from contex. Driver state, road conditions, route - instead of asking the driver to navigate to what they need.
Developed a context-aware UI framework that utilizes generative models to synthesize interface components in real-time. By analyzing driver telemetry, cabin state, and environmental context, the system provides proactive information hierarchy, minimizing cognitive load while enhancing vehicle interaction.
- —Modular HMI architecture decoupling UI layout from data streams, enabling seamless adaptation to driver context.
- —React-based orchestration layer synchronizing generative model outputs with vehicle displays at sub-50ms latency.
- —Adaptive HMI prototype translating experimental generative design into safety-critical dashboard implementation.
- •Navigation Mapping
- •Route Itinerary Preview
- •Adaptive Route Analytics
- •Live Traffic
- •Arrival Metrics
- •Thermal Cabin Comfort
- •Visibility Optimization
- •Thermodynamic Seating
- •Spa Mode
- •Microclimate & Destination Outlook
- •En-Route Environmental Timeline
- •Active Weather Advisories
- •Predictive Road Analytics
- •Playback Control
- •Music Queue
- •Audio Engineering
- •Source Switching
- •Multizone Audio
- •Podcast Audiobook Control
- •Tire Pressure Analytics
- •Engine Oil Level Metrics
- •Incident Telemetry Recorder
- •Hydraulic Brake Fluid Integrity
- •Kinetic Brake Pad Wear Analytics
Grounded in two complementary methods: physiological measurement to capture what drivers cannot self-report, and structured usability testing to observe how they interact with dynamic interfaces.
Integrated a multi-sensor pipeline to capture driver state data that feeds directly into the UI's context gating logic. Design decisions grounded in measurable cognitive and physiological signals rather than self-reported preference alone.
Designed a structured testing framework to evaluate how drivers interact with dynamically generated interfaces under varying scenario conditions. Findings directly informed iteration on the isochrone GenUI concept and real-time layout logic.
Three principles shaped every design decision across the project.
Voice and sensor input become generators of new interface components. The driver does not navigate — the interface responds.
Driver Input
Voice · Sensor · Telemetry
Intent Parsing
NLP · Context classification
UI Generation
Component synthesis · Agent selection
Layout Orchestration
Priority scoring · Glance-budget check
Rendered InterfaceHover Me
Sub-50ms · Auto-dismissed when resolved
Example
Driver says "Show me roads to avoid" during a snowstorm → system generates a contextual map overlay with icy patch markers, congestion warnings, and a black ice alert — assembled on demand, dismissed automatically when conditions clear.
Designed in Figma, validated against one primary scenario — Kennedy Expressway, Chicago, 32°F. High information density, genuine safety stakes.
Passenger Comfort Panel
Identity, dual-zone temp, seat controls, tire pressure, and range — one glanceable view. No multi-step navigation.
Danger Zone Map Overlay
Icy patch markers, congestion flags, and black ice alert. Auto-surfaces on weather trigger. Dismissed when conditions clear.
Snow Readiness Module
Tire pressure, brake wear, road focus mode, heated steering — assembled proactively. Surfaces without being asked.
Climate Ring Display
Dual-zone temp as ambient rings in the instrument cluster. Communicates state without pulling sustained attention from the road.
