Cloud Racing-The Past and Present of Amazon DeepRacer

As early as the advent of automobiles in the early twentieth century, inventors had already proposed unmanned driving. But even in the initial stage of realizing unmanned driving, it has gone through a full century. After all, under complex urban road conditions, if a machine wants to realize functions such as perception, decision-making, and control like humans, it will inevitably face various complex realistic challenges. But needless to say, unmanned driving has become the key research direction of current and future cutting-edge technology companies.

Cloud Racing Opens the Door to Machine Learning

If unmanned driving was originally an element that only existed in science fiction movies, then Amazon DeepRacer successfully projected it into the real world.

As the creator and leader of global cloud computing, Amazon Cloud Technology released the Amazon DeepRacer race car in November 2018. The race car is driven by reinforcement learning-Reinforcement learning (RL) and 3D racing simulator at a ratio of 1/18. Fully self-driving racing car. RL is an advanced machine learning technology that can learn very complex behaviors without labeling training data, and can make short-term decisions while optimizing long-term goals. Amazon DeepRacer solves the autonomous driving technology platform through models. Developers can train, evaluate and adjust the RL model in the simulator, compete in the cloud-based 3D racing simulator, and deploy the model to Amazon DeepRacer to obtain Real-world autonomous driving experience, feel the speed and passion anytime, anywhere.

In order to ensure that the car can play more fully on the field and take the lead on the road of machine learning, Amazon Cloud Technology deliberately equipped it with Intel Atom® processor, 4 megapixels, 1080p resolution camera, high-speed (802.11ac) WiFi, and High-end equipment such as the Intel OpenVino computer vision tool suite has allowed the car to be fully armed from head to toe, achieving breakthroughs one after another in the process of constant trial and error.

At the same time, Amazon Cloud Technology also set up the Amazon DeepRacer League competition (including online simulation competition and offline physical competition) in 2018, aiming to allow people from all over the world to easily participate in machine learning and experience the fun of autonomous driving. The world's first global autopilot racing alliance open to everyone.

On the Amazon DeepRacer platform, developers can in-depth test performance in various environments, continuously optimize the effect of machine learning through data debugging and selection of accessories, and find the future of machine learning in competitions with players from all over the world.

Multi-dimensional upgrade brings a new experience

Less than a year after the release of Amazon DeepRacer, it has attracted thousands of developers around the world to participate in live and virtual competitions, and has shown amazing energy and creativity. In order to satisfy developers' pursuit of speed and enthusiasm for machine learning, in early 2020, Amazon Cloud Technology launched a new generation of Amazon DeepRacer Evo based on Amazon DeepRacer. Compared with the previous generation, the new racing car is equipped with a stereo camera and a laser detection and measurement (LIDAR) sensor on the original basis to make it more powerful and more perceptual. With the help of the new configuration, Amazon DeepRacer will bring developers a better experience in machine learning.

Along with the configuration update of the car, the league competition system also ushered in an upgrade. In 2020, Amazon Cloud Technology has increased the number of large-scale events worldwide and opened more virtual tracks and competition formats. With the newly upgraded Amazon DeepRacer Evo, the efficiency of machine learning has been further improved. From individuals to companies, to the entire region, owning your own driverless racing car and enjoying a racing game has become a "new fashion" in the field of machine learning.

code open source embraces more possibilities

In order to make machine learning burst out with more amazing energy, in April 2021, Amazon Cloud Technology officially opened the Amazon DeepRacer open source code, allowing any developer with basic Linux coding skills to rewrite their own "DeepRacer" as much as possible. Prototype development for new uses is carried out to create an "all-round racing car" that meets more needs.

Want to experience "all-round racing" for the first time? Action is worse than heart!

Move your fingers, hurry up and join us! The atmosphere of the scene will make you a worthwhile trip!

[Amazon Cloud Technology China Summit 2021] takes you to the era of four-wheel drive brothers!

The summit will be held in Shanghai, Beijing and Shenzhen. Together with many industry-leading technology practitioners, we will bring a multi-dimensional forward-looking perspective to share around the reliable technology and services of Amazon Cloud Technology; and a special "Amazon "DeepRacer driving the racing track" allows you to personally visit the front line of AI and go deep into the forefront of machine learning development.

Scan the QR code to sign up and participate in the Amazon Cloud Technology China Summit

For more summit information, please click to view https://aws.amazon.com/cn/about-aws/events/summit2021/index_dev/

what are you waiting for? Hurry up and sign up to join the marathon at the summit site and have a crazy and exciting autonomous car driving competition with Amazon DeepRacer! Let us use AI to pay tribute to the chasing four-wheel-drive boys!