My team's main focus areas are:- Creation of large scale automatic ground truth pipelines to train neural networks with massive amounts of diverse, high-quality data. Use this fleet-learning approach to replace potentially brittle run-time algorithms with robust learned models.- Developing an accurate and detailed geometric and semantic understanding of the world using the best of both machine-learned and engineered models.- Building robust, causal, predictive models for other… Show more My team's main focus areas are:- Creation of large scale automatic ground truth pipelines to train neural networks with massive amounts of diverse, high-quality data. Use this fleet-learning approach to replace potentially brittle run-time algorithms with robust learned models.- Developing an accurate and detailed geometric and semantic understanding of the world using the best of both machine-learned and engineered models.- Building robust, causal, predictive models for other agents in both geometry and semantic state spaces.- Decision making, motion planning, and control modules using state-of-the-art AI techniques including methods for high-dimensional search, trajectory optimization, reinforcement learning, model-predictive control, etc. Show less

Worked on geometric scene understanding to significantly improve the performance of Autopilot using fleet learning techniques.

Worked on various systems needed to ship Tesla's in-house computer vision system, that was developed from scratch, for the second generation Autopilot.

Developed various modules such as velocity planning and control, automatic lane change, etc. for the first generation Autopilot.

Designs, develops and maintains software for automotive electronic control systems, works with hardware engineers and other team members to integrate software into vehicle electronic control systems, and performs system level testing and validation

Research and development of a robust, camera-based, perception system to recognize and register various road-marks on the vehicle's drivable road surface in-order to precisely localize the car. This project was part of the autonomous driving team of Volkswagen.