Race miniature automobiles using solely Artificial Intelligence and Machine Learning | Technology
|Race miniature automobiles using solely Artificial Intelligence and Machine Learning|
Race tiny cars using only Artificial Intelligence and Machine Learning
Thirteen college students from across Canada are in Ottawa to put their AI skills to the test.
It's called the Amazon Web Services DeepRacer League, where small 1/18 scale cars are trained to complete a race track as fast as possible, by themselves.
"It has important components to make autonomous driving," says Amanda Foo, senior manager of the DeepRace technical program.
They are driven by what is called reinforcement learning.
"It's like training a dog," says Masoud Karimi, a mechanical engineering student at Carleton University. “When the car works well in the simulation, we give it a good reward. And when you get out of the track, we penalize it."
The cars have an incorporated HD camera to give a view of the road and collect the information you need to make your own decisions.
"It collects all your information from this camera here and determines the color schemes, determine where it is outside the limits versus the limits versus the medium of the track," says Foo.
"It will take a picture every 1/15 second and analyze," says software engineering student at the University of Calgary, Aleksander Berezowski. "And choose accelerate, slow down, increasing leftward or rightward increase".
DeepRacer League is the first global league of autonomous racing world, open to everyone. This is the first year we have created a student league.
"High school students to university and college age can compete in the virtual league," says Nicole Foster, director of public policy for Amazon Web Services. "And there are prizes and opportunities to earn scholarships also as part of the competition."
The winning student will receive a gift card from Amazon $ 1,000 to accompany his first place trophy.
But beyond the prizes, many here expect a career that helps automate the world around us.
“I played around with code, watched my car race around the track, and then watched it get better,” says Princeton Dychinco, a student at the British Columbia Institute of Technology. "So it was really cool to see the impact of what I was writing, of what could actually happen."
Source: CTV News, Direct News 99