DonkeyCar, https://www.donkeycar.com/, is a free, open source project that provides instructions and source code to build, program, train and even race your own small-scale autonomous car. At its’ core, DonkeyCar is a high level self driving library written in Python. It was developed with a focus on enabling fast experimentation and easy contribution. It is has been called the Hello World of autonomous vehicles. This session will show you how easy and inexpensive it is to get started with autonomous vehicles. The session will cover:
- The anatomy of an autonomous scale car
- Behavioral Cloning or how to train a neural network to drive like you
- What you need to get started
- How to get help if you get stuck
- How to find others for learning and competing
I am driven to do three things; to learn new stuff all the time, to work with crazy-smart people that challenge me, and to create beautifully architected software that matters. I've been lucky enough to work at some great companies and at times I've created my own companies to provide this environment. My career has moved from science, to scientific programming, to game development, to eLearning, to full-stack web development. I've worked on platforms ranging from 8 bit microprocessors to massively scalable cloud services. I've designed and programmed many successful products and built a multitude of software tools and frameworks. I've built and managed high performance engineering teams. I've built and sold successful companies. I love engineering software. I am a core committer on the DonkeyCar project, www.donkeycar.com, an open source framework for self-driving scale cars. I am in the top 2% reputation on stackoverflow for 2019 (as of July). I like to learn things and help others learn.