Unlock the Potential of AI with AWS DeepRacer

2018: The Inception of AWS DeepRacer

At AWS re:Invent in 2018, the introduction of AWS DeepRacer was a game-changer. It was a fully autonomous race car that demonstrated the capabilities of reinforcement learning. As an engineer with a background in legacy networks, I was initially skeptical but quickly became fascinated by the potential. The AWS DeepRacer League was also announced, with physical races at AWS Summits worldwide in 2019 and a virtual league in a simulated environment. This opened up a whole new world of opportunities for both experienced and novice developers.

My colleagues and I from JigsawXYZ wasted no time and headed straight to the MGM Grand after the keynote. Despite the long queues, we remained determined. We observed other participants racing while waiting our turn. Each racer had to answer questions about their driving preferences to select a pre-trained model. In contrast to later competitions, racers had to physically follow the car and place it back on the track when it deviated. We noticed that the AWS-provided models were not as stable or fast as they are today and frequently went off-track. However, we quickly realized that by quickly replacing the car on the track, we could achieve a good lap time. Using this strategy, we managed to secure second place on the leaderboard.

2019: Building a Community and Diving Deeper

Back in London, the interest in AWS DeepRacer grew exponentially. We had the opportunity to speak at multiple events, including hosting our own "An evening with DeepRacer" gathering. As the 2019 season approached, I knew I had to earn my own finals spot. I started training models in the AWS DeepRacer console and experimenting with the physical car. This included remote control and first-person view projects, which enhanced my understanding of the technology.

At the 2019 London AWS Summit, I achieved a remarkable feat by winning the AWS DeepRacer Championship with a lap time of 8.9 seconds. This was a significant improvement from the previous year and sparked the creation of the AWS DeepRacer Community. Since then, the community has grown to over 45,000 members, creating a vibrant ecosystem of like-minded individuals.

My curiosity about the inner workings of AWS DeepRacer led me to contribute to open source projects. This allowed me to run the training stack locally and gain a deeper understanding of AWS services such as Amazon SageMaker and AWS RoboMaker. These efforts not only enhanced my skills but also led to my nomination as an AWS Community Builder.

2020 - 2023: Virtual Racing and Continued Growth

The COVID-19 pandemic forced AWS DeepRacer competitions to move online in 2020 and 2021. Despite the challenges, events like the AWS DeepRacer F1 Pro-Am kept the community engaged. The introduction of the AWS DeepRacer Evo, with its advanced stereo cameras and lidar detector, marked a significant hardware upgrade.

In 2022, in-person racing returned, and I set a new world record at the London Summit. Although I didn't win the finals that year, the experience of competing and connecting with fellow racers was invaluable. It reaffirmed my love for AWS DeepRacer and the community.

2023 brought more intense competition. I set another world record in London but fell short of winning first place. However, I managed to secure a finals spot by winning a virtual league round for Europe. The opportunity to reconnect with the AWS DeepRacer community was a rewarding experience.

The Lasting Impact of AWS DeepRacer

Over the past six years, AWS DeepRacer has had a profound impact on my professional and personal life. It has provided me with a strong foundation in AI and ML, improved my coding skills, and helped me 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 have achieved recognition as a top UK startup.

As the official AWS DeepRacer league comes to an end, I am excited to see what the community will achieve next. This journey has shaped my career and life in ways I never imagined when I first saw that small autonomous car on stage in 2018. For those interested in starting their own AI and ML journey, I encourage you to explore the AWS DeepRacer resources available on the AWS website. You can also join the thriving community on Discord to connect with other enthusiasts and learn from their experiences.

About the author: Matt Camp is an AI and ML enthusiast who has been involved with AWS DeepRacer since its inception. He is currently working 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.