In 2018, I sat within the viewers at AWS re:Invent the place Andy Jassy introduced AWS DeepRacer, a totally autonomous 1/18 scale race automobile powered by reinforcement studying. On the time, I knew little about AI and machine studying (ML). As an engineer migrating from legacy networks to cloud know-how, I by no means considered myself as a developer. Nonetheless, AWS DeepRacer instantly caught my curiosity with its promise of permitting even inexperienced builders to become involved in AI and ML.
The AWS DeepRacer League was additionally introduced. It options bodily races at AWS Summits to be held all over the world in 2019, in addition to digital leagues in simulated environments. The winner will likely be eligible to compete for the title of Grand Champion in Las Vegas the next yr. In 2018, AWS DeepRacer was simply introduced, permitting re:Invent attendees to compete immediately at MGM Grand utilizing pre-trained fashions.
My JigsawXYZ colleagues and I headed straight to the MGM Grand after the keynote. Regardless of the lengthy line, we persevered whereas ready and observing others racing. Individuals chosen a pre-trained mannequin by answering questions on their driving preferences. Not like later competitions, racers needed to bodily observe down their automobiles and get them again on observe once they veered.
We discovered that the mannequin offered by AWS was unstable and sluggish by right now’s requirements, and ceaselessly went off observe. We concluded that we may get good lap instances by rapidly altering automobiles on the observe. This technique secured second place on the leaderboard.
The evening earlier than the finals, we discovered that we had certified attributable to elimination. Panic set in after I realized I might be competing on stage in entrance of hundreds of individuals with little data of ML. We desperately tried to coach the mannequin in a single day to keep away from embarrassment.
The following morning we have been within the entrance row of the auditorium, subsequent to Andy Jassy. Our boss, Rick Fish, represented the staff. After a spirited introduction from IndyCar commentator Ryan Mylane, Rick posted a lap time of 51.50 seconds, incomes him the title of 2018 AWS DeepRacer Grand Champion.
Picture 2 – Rick Fish receiving the AWS DeepRacer trophy from Matt Wooden
2019: Construct your group and dig deeper
Once I returned to London, curiosity in AWS DeepRacer exploded. We have now spoken at a number of occasions, together with internet hosting our personal occasions. A night with DeepRacer To assemble collectively. Because the 2019 season approached, I wanted to earn myself a spot within the finals. I began coaching the mannequin within the AWS DeepRacer console and began experimenting with bodily automobiles, together with distant management and first-person initiatives.
On the 2019 London AWS Summit, I gained the AWS DeepRacer Championship with a lap time of 8.9 seconds. This was a major enchancment over the earlier yr. This occasion additionally AWS DeepRacer Communitywhich has since grown to greater than 45,000 members.
I grew to become all for understanding the inside workings of AWS DeepRacer. I contributed to open supply initiatives that will let you run coaching stacks regionally and delved into AWS providers corresponding to Amazon SageMaker and AWS RoboMaker. For these efforts, I used to be named an AWS Group Builder.
I improved my expertise in Python, Jupyter, numpy, pandas, and ROS by engaged on group initiatives. These experiences proved invaluable after I joined Unitary, an AI startup centered on decreasing dangerous on-line content material. In lower than a yr, we constructed a world-class inference platform that processes greater than 2 billion video frames on daily basis utilizing dynamically scaled Amazon Elastic Kubernetes Service (Amazon EKS) clusters.
Picture 3 – Unitary demonstrating dynamically scaled inference with 1000+ EKS nodes at AWS London Summit
2020-2023: Digital racing and continued progress
Because of the COVID-19 pandemic, the 2020 and 2021 AWS DeepRacer competitions have been moved on-line. Regardless of this, thrilling occasions just like the AWS DeepRacer F1 Professional-Am stored the group engaged. The {hardware} has been considerably upgraded with the introduction of AWS DeepRacer Evo with stereo cameras and LIDAR detectors.
In-person racing resumed in 2022 and I set a brand new world report on the London Summit. Regardless that I did not win the finals that yr, the expertise of competing and connecting with my fellow racers was nonetheless invaluable.
Pictures 4 and 5 – Writer holding the 2022 London Summit trophy (left) DeepRacer group members and pit crew internet hosting the AWS DeepRacer workshop at re:Invent 2023 (proper)
In 2023, competitors is much more intense. In London, he set one other world report, but it surely wasn’t sufficient for him to take first place. Ultimately, they successfully gained the Europa League spherical and certified for the ultimate. Though our efficiency within the finals didn’t enhance on our earlier outcomes, the chance to reconnect with the AWS DeepRacer group was worthwhile.
Conclusion: The lasting impression of AWS DeepRacer
Over the previous six years, AWS DeepRacer has had a huge effect on my skilled and private life. This helped me construct a robust basis in AI and ML, enhance my coding expertise, and community with pals and professionals within the tech business. The expertise I gained by way of AWS DeepRacer immediately contributed to my success at Unity, gaining recognition as a prime UK startup.
Because the official AWS DeepRacer League attracts to an in depth, we will not wait to see what the group accomplishes subsequent. This journey formed my profession and life in methods I by no means anticipated after I first noticed that small self-driving automobile on stage in 2018.
If you’re all for beginning your individual AI and ML journey, we encourage you to discover the AWS DeepRacer sources accessible on the AWS web site. You can even be part of Discord’s lively group to attach with different fanatics and study from their experiences.
Concerning the writer
matt camp is an AI and ML fanatic and has been concerned with AWS DeepRacer from the start. He presently works at Unitary, making use of his expertise to growing cutting-edge content material moderation know-how. Matt is an AWS Group Builder and continues to contribute to open supply initiatives within the AWS DeepRacer group.
