AI / ML Models


AirSim is a simulator for drones, cars and more, built on Unreal Engine (we now also have an experimental Unity release). It is open-source, cross platform, and supports hardware-in-loop with popular flight controllers such as PX4 for physically and visually realistic simulations.


Apollo is a high performance, flexible architecture which accelerates the development, testing, and deployment of Autonomous Vehicles.

Autonomous Driving Cookbook

The Autonomous Driving Cookbook is a project run by Project Road Runner at Micrsoft Garage. It comprises of tutorials for beginning, researchers, and experts alike, in the form of Jupyter notebooks.


The AutoRally platform is a high-performance testbed for self-driving vehicle research. Using an RC vehicle, AutoRally opens the space of aggressive autonomous off-road driving to researchers and hobbyists.

Autoware.AI is the world's first "All-in-One" open-source software for autonomous driving technology. It is based on ROS 1 and available under Apache 2.0 license. It contains modules for localization, detection, prediction and planning, and vehicle control.

Awesome Autonomous Vehicles

Awesome Autonomous Vehicles is a curated list of resources (software, hardware, research papers) related exclusively to autonomous vehicles.

Awesome Robotic Tooling

This page lists tools for professional robotic development with ROS in C++ and Python, some related to autonomous driving.

CARLA Simulator

CARLA is an open-source simulator for autonomous driving research, developed from the ground up to support development, training, and validation of autonomous driving systems. The simulation platform supports flexible specification of sensor suites and environmental conditions.


A plugin for GTAV that transforms it into a vision-based self-driving car research environment. Collecting data from the game's driving simulation, it's exported in JSON format to be used with a self-driving model.

Donkey Car

Donkey Car is an open source DIY self driving platform for small scale cars.

Lanenet Lane Detection

Lanenet is an implementation of lanenet model for real time lane detection using deep neural network model

LGSVL Simulator

LGSVL is an Autonomous Vehicle Simulator testing autonomous vehicle algorithms. It integrates with some of the other platforms on this page, including Apollo.

Open Autonomous Driving

This page lists open source resources related to autonomous vehicles, including sensors, perception, and path planning.

Open Source Self Driving Car Initiative

The Open Source Self Driving Car Initiative maintains a page of full stack open source software and hardware to allow anyone to build from toy to full size self driving cars.


A Python code collection of robotics algorithms, especially for autonomous navigation.

Self-Driving Pi Car

Self-Driving Pi Car is a deep neural network based self-driving car, that combines Lego Mindstorms NXT with the computational power of a Raspberry Pi 3.

Udacity Self-Driving Car Source Code

Source code for all of the projects used in Udacity's Self-Driving Car Engineer Nanodegree.


Webots is an open source and multi-platform desktop application used to simulate robots. It provides a complete development environment to model, program and simulate robots

ML Model Frameworks


Tensorflow is a javascript library for implementing machine learning. Includes pre-trained models for autonomous vehicle related tasks such as object detection and image classification.


PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook's AI Research lab. The 'torchvision' package consists of popular datasets, model architectures, and common image transformations for computer vision.