Developing NVIDIA’s End-to-End VLA Solution for Autonomous Driving and Deploying on NVIDIA Chips

Formerly the Google self-driving car project.

Build a perception pipeline to make the car see and understand the world.

Developed and deployed the latest advancements in artificial intelligence, computer vision and machine learning to help build safe and efficient self-driving vehicles.

Dedicated to system design, implementation, integration, performance improvements and onboard validation of GPU and other type of acceleration systems available on vehicle.

Worked on algorithms such as deep learning inference libraries, fast geometry computations, system latency diagnostics, sensor data visualization and efficient utilities.

Develop computer vision, sensor fusion and machine learning algorithms to support the products of Autonomous Vehicle (AV) and Driver Assist Technologies (DAT).

Implement, validate and test the algorithm on a vehicle and perform benchmarking.

Working on multi-sensor fusion projects involving LIDAR, Camera, Radar, Ultrasonic, etc.

Implemented LIDAR and RADAR data fusion to achieve the model based vehicle detection and tracking for autonomous urban driving.

Designed and programmed the algorithm in C++ using dynamic Bayesian Network and Particle filter to detect and track the vehicle.

Integrated the whole system into the Real-time system RTMaps and analyzed the data in real time.