实操 | Getting started with Self-Driving Car : Prepare

Coding

• Before everything we need programming skills in C++ and Python.

• Book: Modern C++ Programming with Test-Driven Development.

Talk

• NVIDIA at CES 2016 - Self Driving Cars and Deep Learning GPUs

Post

• Autonomous driving - do it yourself!

Online Cousrses

I can’t imagine writing this article without mentioning the outstanding online course provided by Udacity. Self-Driving Car Engineer Nanodegree will guide you through the aspects of computer vision, deep learning and vehicle kinematics. The only disadvantage is the price, as it costs around 800$ for each of the three terms.

There is a free alternative, that is prepared by MIT - Introduction to Deep Learning and Self Driving Cars. It is not as complementary as the course from previous paragraph (it focuses only on the deep learning approaches), but it still might be considered as an interesting introduction to the field.

Packages

1. Autoware

   Open-source software for urban autonomous driving

2. Repo for Predicting Steering Wheel

   TensorFlow implementation based on End to End Learning for Self-Driving Cars.

3. The Udacity open source self-driving car project

   Official Site
   

   Github Repo

4. Udacity Self Driving Car Nano Degree - Behavior Cloning Project

   Preview Syllabus

   Example Homework

   • https://github.com/dolaameng/Udacity-SDC_Behavior-Cloning.git
   • https://github.com/shangliy/driving_clone.git

Knowledge

as in the syllabus of Udacity Self-Driving Car Nano-degree

• Deep Learning

• Computer Vision

• Sensor Fusion

• Localization

• Control

• Path Planning

• Elective

• Systems

Reference

• In-Depth on Udacity’s Self-Driving Car Curriculum