Jerrick Hoang

Papers

Total Citations

H-Index

About

Jerrick Hoang is a researcher whose work sits at the critical intersection of autonomous driving, robotics, and machine learning. His primary research focus is on developing safe and physically realistic motion forecasting systems, with a key emphasis on ensuring that predicted vehicle trajectories are not only accurate but also physically feasible. His most notable contribution, the 2021 paper "Physically Feasible Vehicle Trajectory Prediction," has garnered 7 citations and addresses a fundamental gap in autonomous driving: the tendency of standard trajectory prediction models to output paths that violate basic physical constraints, such as kinematics and dynamics. By formalizing three essential properties for physically realistic motion, Hoang’s work provides a crucial framework for building safer and more reliable autonomous systems. This research is particularly impactful for students and engineers working on perception and planning stacks for self-driving cars, as it bridges the gap between pure prediction accuracy and real-world drivability. Hoang’s contributions are helping to push the field toward more robust and trustworthy autonomy.