Anushka Tiwari
Computer engineering
Hometown: Tempe, AZ, United States
Graduation date: Spring 2026
FURI | Spring 2026
Vision-Based End-to-End Trajectory Prediction for Autonomous Vehicles using the Waymo Open Dataset
Current autonomous vehicle perception models lack interpretability, it is not known which visual features drive trajectory decisions, creating safety and accountability gaps. This research investigates which visual cues most significantly influence waypoint prediction accuracy using the waymo open dataset. The researcher develops task specific attention mechanism that explicitly prioritizes semantically meaningful road regions over irrelevant ones, comparing its performance against CNN-LSTM baseline using ADE and FDE metrics. Findings will quantify feature-level contributions to trajectory prediction, advancing explainable AI in autonomous driving and enabling engineers to identify and correct perception blind spots before they cause harm.
Mentor: Bharatesh Chakravarthi
It’s hip to be square.
Students presenting projects at the Fulton Forge Student Research Expo are encouraged to download this personal QR code and include it within your poster. This allows expo attendees to explore more about your project and about you in the future.
Right click the image to save it to your computer.