Deepak Ramani's Projects
This repo contains the files for building a basic autonomous driving framework
This is my blog where I write about technical, nerdy things about basic setup, tools, ideas, research papers, robotics, data analysis, ML/DL, and anything that I feel might help people.
This repo allows utterances to create new comments as issues
A script to create boiled leather reading order of AFFC and ADWD (a part of the ASOIAF)
In this project, the goal is to design a path planner that is able to create smooth, safe paths for the car to follow along a 3 lane highway with traffic. A successful path planner will be able to keep inside its lane, avoid hitting other cars, and pass slower moving traffic all by using localization, sensor fusion, and map data.
Change data capture demo with postgres, debezium connectors, apache Kafka and S3.
Repo containing source files of Mlops-grocery-sales infrastructure and Github actions workflow for CI/CD
data engineering zoom camp 2023
Repo for the Deep Learning Nanodegree Foundations program.
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
Code and helper scripts for article on Medium "How Docker Can Help You Become A More Effective Data Scientist"
All my dotfiles essential to setup a new environment go here.
This repo contains all the source files of my blog
Setup all the things to run ML fastai tasks in AWS EC2 instance.
Friends of Tracking: Tutorial on valuing actions in football.
repo to hold pdfs, notebooks, and data for FOT lectures
A list of cool features of Git and GitHub.
Building a self driving car for GTA 5
ROS2 End-to-End Lane Following Model with LGSVL Simulator
Last row tracking data and code
Laurie's code for Metrica tracking data.
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
Contains all the tex and papers used in creating the report.
Capstone project for Mlops-zoomcamp
MLOPS Zoomcamp
This project is to use Model Predictive Control (MPC) to drive a car in a game simulator. The server provides reference waypoints (yellow line in the demo video) via websocket, and we use MPC to compute steering and throttle commands to drive the car. The solution must be robust to 100ms latency, since it might encounter in real-world application.