In 2018, I sat in the audience at AWS re:Invent when Andy Jassy announced AWS DeepRacer, a fully autonomous 1/18 scale race car powered by reinforcement learning. At the time, I knew little about ai or machine learning (ML). As an engineer transitioning from legacy networks to cloud technologies, I had never considered myself a developer. But AWS DeepRacer instantly captured my interest with its promise that even inexperienced developers could get involved in ai and ML.
Also announced was the AWS DeepRacer League, which will include physical races at AWS Summits around the world in 2019 and a virtual league in a simulated environment. The winners would qualify to compete for the grand champion title in Las Vegas the following year. For 2018, because AWS DeepRacer had just been introduced, re:Invent attendees were able to compete in person at the MGM Grand using pre-trained models.
My colleagues and I from JigsawXYZ immediately headed to the MGM Grand after the keynote. Despite the long lines, we persevered and watched others run while we waited. Participants answered questions about driving preferences to select a pre-trained model. Unlike later competitions, racers had to physically follow the car and put it back on the track when it strayed.
We realized that the models provided by AWS were unstable and slow by current standards and frequently drifted. We concluded that quickly replacing the car on the track could result in a good lap time. With this strategy we achieved second place in the classification.
The night before the final, we found out that we had qualified due to a withdrawal. Panic set in when we realized we would be competing on stage in front of thousands of people without knowing much about ML. We desperately try to train a model overnight to avoid embarrassment.
The next morning, we found ourselves in the front row of the main auditorium, next to Andy Jassy. Our boss, Rick Fish, represented our team. After a spirited introduction from Indycar commentator Ryan Myrehn, Rick set a lap time of 51.50 seconds, securing the title of 2018 AWS DeepRacer Grand Champion!
Image 2: Rick Fish accepting the AWS DeepRacer trophy from Matt Wood
2019: Building community and going deeper
Back in London, interest in AWS DeepRacer skyrocketed. We speak at multiple events, including our own An evening with DeepRacer meeting. As the 2019 season approached, I needed to earn my own spot in the finals. I started training models on the AWS DeepRacer console and experimenting with the physical car, including remote control and first-person view projects.
At the 2019 AWS London Summit, I won the AWS DeepRacer Championship with a lap time of 8.9 seconds, a significant improvement from the previous year. This event also prompted the creation of the AWS DeepRacer Communitywhich has since grown to have more than 45,000 members.
My interest in understanding the inner workings of AWS DeepRacer grew. Contributed to open source projects that enabled the training stack to be run locally, delving into AWS services such as amazon SageMaker and AWS RoboMaker. These efforts led to my nomination as an AWS Community Builder.
Working on community projects improved my skills in Python, Jupyter, numpy, pandas and ROS. These experiences proved invaluable when I joined Unitary, an ai startup focused on reducing harmful content online. In one year, we built a world-class inference platform that processes more than 2 billion video frames daily using dynamically scaled amazon Elastic Kubernetes Service (amazon EKS) clusters.
Image 3: Unitary at the AWS London Summit showing dynamically scaled inference using 1000+ EKS nodes
2020-2023: virtual races and continued growth
The COVID-19 pandemic shifted AWS DeepRacer competitions online for 2020 and 2021. Despite this, exciting events like AWS DeepRacer F1 Pro-Am kept the community engaged. The introduction of AWS DeepRacer Evo, with stereo cameras and a lidar detector, marked a major hardware upgrade.
In-person racing returned in 2022 and I set a new world record at the London Summit. While I didn't win the finals that year, the experience of competing and connecting with other runners was still invaluable.
Images 4 and 5: The author lifts the 2022 London Summit trophy (left). DeepRacer community members and the pit crew host an AWS DeepRacer workshop at re:Invent 2023 (right).
2023 brought more intense competition. Although I set another world record in London, it wasn't enough to take first place. I finally got a place in the finals by winning a virtual league round for Europe. While my performance in the finals did not improve from previous results, the opportunity to reconnect with the AWS DeepRacer community was rewarding.
Conclusion: The Lasting Impact of AWS DeepRacer
Over the past six years, AWS DeepRacer has deeply impacted my professional and personal life. It has helped me develop a solid foundation in ai and ML, improve my coding skills, and build a network of friends and professional contacts in the tech industry. The experience gained through AWS DeepRacer directly contributed to my success at Unitary, where we gained recognition as one of the UK's top startups.
As the official AWS DeepRacer league comes to a close, I'm excited to see what the community will achieve next. This journey has shaped my career and my life in ways I never expected when I first saw that little self-driving car on stage in 2018.
For those interested in starting their own journey in ai and ML, I invite you to explore the AWS DeepRacer resources available on the AWS website. You can also join the thriving Discord community to connect with other enthusiasts and learn from their experiences.
About the author
camp matt is an ai and machine learning enthusiast who has been involved with AWS DeepRacer since its inception. He currently works at Unitary, applying his skills to develop cutting-edge content moderation technology. Matt is an AWS Community Builder and continues to contribute to open source projects in the AWS DeepRacer community.
