June 2022 trajdata has been open sourced! It's a new, unified interface to many trajectory forecasting datasets, greatly simplifying the process of training and evaluating models on multiple motion datasets. Also, our paper on incorporating class uncertainty within trajectory forecasting has been accepted to IROS 2022! See you in Kyoto!
April 2022 3 new paper acceptances! They focus on 1) mitigating the effect of erroneous object tracking on prediction (arXiv, to appear at IV), 2) injecting planning-awareness into prediction and perception evaluation (arXiv, to appear at IV), and 3) leveraging conformal prediction to develop early warning systems with provable false negative rates (arXiv, to appear at WAFR).

About Me

I am currently a Research Scientist in NVIDIA's Autonomous Vehicle Research Group. Prior to joining NVIDIA, I received my Ph.D. in Aeronautics and Astronautics under the supervision of Marco Pavone in 2021 and an M.S. in Computer Science in 2018, both from Stanford University. I received my B.A.Sc. in Engineering Science from the University of Toronto in 2016.

My research interests are rooted in trajectory forecasting and its interactions with the rest of the autonomy stack. This usually includes a mix of improving raw prediction performance, integrating prediction with perception and planning, and holistically evaluating autonomy stack performance. I have also previously conducted research in the fields of computer vision, natural language processing, and data science, frequently leveraging concepts from them in my current research.

If you'd like to conduct an internship in our group along these topics, please apply here!

Resume/CV (updated September 2022)