The $400 AWS DeepRacer radio-controlled, four-wheel drive car is being offered as a "Reinforcement Learning" platform for hardware and software developers. An increasingly popular area of research, reinforcement learning is an advanced type of machine learning where an "agent" learns how to behave in an interactive environment by performing actions and seeing the results.
"Reinforcement Learning is one of the technologies that are used to make self-driving cars a reality," says Amazon Chief Evangelist for AWS. "The AWS DeepRacer is the perfect vehicle (so to speak) for you to go hands-on and learn all about it. We're ramping up volume production and you will be able to buy one of your very own very soon."
The AWS DeepRacer features an Intel Atom processor onboard, a 4-megapixel camera with 1080p resolution, fast (802.11ac) Wi-Fi, multiple USB ports, and enough battery power to last for about two hours. The Atom processor runs Ubuntu 16.04 LTS, ROS (Robot Operating System), and the Intel OpenVino computer vision toolkit.
The device includes a fully-configured cloud environment that developers can use to train their Reinforcement Learning models. It takes advantage of the new Reinforcement Learning feature in the Amazon SageMaker machine learning service and also includes a 3D simulation environment powered by the company's AWS RoboMaker cloud robotics service.
Users can train an autonomous driving model against a collection of predefined race tracks included with the simulator and then evaluate them virtually or download them to a AWS DeepRacer car and verify performance in the real world. Interested developers can pre-order the AWS DeepRacer and sign up to be part of the preview.
The company also announced the AWS DeepRacer League – the world's first global autonomous racing league, open to anyone. In 2019, says the company, there will be a series of live racing events at AWS Global Summits around the world, as well as virtual events and tournaments throughout the year.
The company says