Darshil Shah took a lot away from his first ever participation in Humber Polytechnic's annual AWS DeepRacer competition.
Shah - who is a graduate of the Cloud Computing and, most recently, Artificial Intelligence with Machine Learning programs - felt signing up for AWS DeepRacer was an excellent learning opportunity for him considering his areas of study. Shah said much of what was learned in class was used to help his team excel at the competition.
AWS DeepRacer is a fully autonomous racing league with a 1/18th scale race car driven by a machine learning (ML) algorithm. The students are tasked with programming the vehicle how to drive on a cloud-based 3D racing simulator. They can test the effectiveness of their programming, adjust as needed and then see the impact it has on their lap time.
When the competition is ready to happen, the model cars are taken from the virtual track to a real one where they race to determine which has the best time to declare a winner.
In addition to the programming skills needed to get the car navigating the track, other skills were utilized. Initially, some of the models were leaving the track. So, Shah and his team used their collective leadership skills to ensure everyone stayed motivated and on task while tapping into their problem-solving skills needed to fix the issue.
"I'm certainly glad that I joined AWS DeepRacer," said Shah. "It was an amazing experience and a valuable one for a student taking Artificial Intelligence with Machine Learning. We really enjoyed it and were having so much fun they had to tell us to go home one night because we had stayed so late working."
Mihai Albu is a professor with the Faculty of Applied Sciences & Technology and a researcher at Humber. He's overseeing Humber's AWS DeepRacer competition that was expanded this year to include, for the first time, teams from Cambria, Conestoga, Seneca and George Brown colleges.
In total, more than 65 students across 15 teams were at North Campus for the competition.
Albu said the competition is valuable for learners as they develop their programming skills while gaining practical experience.
It also teaches the students about the concept of reinforcement learning, which is a ML technique that trains software to make decisions to achieve the most optimal results. The students learn as they experiment with different parameters in the programming and can see the results of their decisions in real time based on how their model does on the lap.
Albu said the competition is a good way for students to experiment and learn about AI and ML and shows them the real-world application of the technology.
"What I think is great about AWS DeepRacer is that the students are learning and having fun at the same time while they're racing," said Albu, adding that with AI becoming more prevalent in our day-to-day lives it's valuable for students to gain experience with the technology regardless of what they're studying.
Computer Science student Faraz Tabatabaei was part of a team from Seneca College. He's been interested in robotics and coding from a young age and found that taking part was illuminating. He learned more about the Python programming language and gained a much better understanding of AI.
"When you see your code come to life on the track, it feels pretty great," said Tabatabaei.
Finishing in first place was the Sharks team from Cambrian College while George Brown's Synergy finished second. Humber's TechTitans and Team Jarvis finished third and fourth, respectively.
This AWS DeepRacer competition is open to students from all faculties and programs across Humber. Interested students are invited to send an email to Albu at mihai.albu@humber.ca expressing their interest in participating in the competition.
