I am currently the Head of Perception at Lyft Self-Driving Program. My team is responsible for all on-vehicle perception capabilities of Lyft's Autonomous Vehicle. This incldues Computer Vision, 3D Perception, Tracking, Sensor Calibration, and the machine learning infrasturure to deploy real-time deep learned models on the vehicle platform. Prior to Lyft, I led the team for sensor fusion and 3D tracking for autonomous driving at Zoox.

In my academic life, I obtained PhD in Computer Science from Cornell University. I was a visiting research scholar at the Stanford AI Lab where I started the Brain4Cars and RoboBrain projects. I also have a Bachelors degree in Electrical Engineering from IIT Delhi.

My recent talk @Scale Conference on self-supervised learning for autonomous driving

• 网络加速器免 on self-supervised learning for Autonomous driving @Scale conference, October 2024

• Blog post on sensor calibration for Autonomous Vehicle, August 2024

• Lyft open sourced one of the largest 3D Perception and Prediction data set for Autonomous Vehicle, July 2024

• Spotlight from Lyft on my journey, Feb 2024

• One paper accepted to CVPR 2018.

• Joined Lyft Self Driving Program, January 2018

• Best student paper award at CVPR 2016 (Deep learning on spatio-temporal graphs)

• PhD thesis, May 2016.

• Structural-RNN accepted as an ORAL to CVPR 2016.

• Our paper on sensory-fusion RNN-LSTM for driver activity anticipation is accepted to ICRA 2016

• I recently gave talks at Oculus, University of Washington Seattle, Keynote at the ICCV workshop on Autonomous driving, BayLearn Symposium, Qualcomm, and Zoox Labs on: Deep Learning for Spatio-Temporal Problems: On Cars, Humans, and Robots (免费vpm全球网络加速器, 300MB) (pdf, 30MB)

• Neuralmodels: A deep learning package for quick prototyping of structures of Recurrent Neural Networks and for deep learning over spatio-temporal graphs.

• 网络加速器下载 driving data set and sensory-fusion RNN code.