Khushnood Naqvi

A travel search engine for India which provides travelers the best routes using multiple modes of transport including trains and flights.

Sample tech used:
-- Robust and scalable back-end services developed in Golang and Java/C++, for finding the best travel route and availability.
-- Android app
-- Web-based UI (done in plain JavaScript for compatibility and speed)

This project involved crawling of millions of websites, while taking care not to overload the websites, with multiple concurrent requests.

Building extractors for relevant pieces of information.

Running tests on randomized records to check data fill rates, and get an idea of the quality of extracted data.

The coding was mainly done in Python and Go. MongoDB was used for storage.

Took the Udacity's Self-Driving Car Engineer course in 2017 which was an intense course which covered the various technologies used to build a Self-Driving Car like localization, sensor fusion, and computer vision. The final project (see link), used ROS as a framework to integrate different parts.

Nanodegree Certificate link: https://confirm.udacity.com/DCYYPPAG

Please search my Github repo for a sample of the project code.

Your robot has been kidnapped and transported to a new location! Luckily, it has a map of this location, a (noisy) GPS estimate of its initial location, and lots of (noisy) sensor and control data.

I implemented a 2-d particle filter in C++. The particle filter has a map and some initial localization information (analogous to what a GPS would provide). At each time step, the filter gets observation and control data.

I use this to find the lost car.

It was part of Udacity's Self-Driving Car Engineer nanodegree.

In this project, I use deep neural networks and convolutional neural networks to clone driving behavior. I train, validate, and test a model using Keras. The model outputs a steering angle to an autonomous vehicle.

I use a Udacity provided simulator to steer a car around a track for data collection. Then I use image data and steering angles to train a neural network and then use this model to drive the car autonomously around the track.