Autonomous vehicle race puts ML models to the test
At the “DeepRacer” event, NASA and KBR interns and other employees faced off at NASA’s Goddard Space Flight Center on August 8 to see whose machine-learning (ML) models could propel an AWS DeepRacer vehicle around a track the fastest. The AWS DeepRacer is a 1/18th-scale race car that allows reinforcement learning AI models built in virtual environments to be tested in the real world.
The racers’ machine-learning models, says the company, rewarded vehicles for speed and accuracy for staying on the course, allowing each vehicle to autonomously make short-term decisions to achieve long-term goals. The winning vehicle, by KBR intern Minh Nguyen, circled the track in 13.14 seconds.
“We are proud to have played a key role in an event that fueled interns’ imaginations and developed their AI skills,” says Byron Bright, President, KBR Government Solutions U.S. “The DeepRacer event also provided an opportunity for NASA to experiment with autonomous systems for future exploration missions and showcased how the private and public sector can collaborate to leverage and advance technology.”
KBR worked with AWS and NASA to organize the event, as well as a pre-race, four-hour workshop with an AWS DeepRacer expert to help interns build, test, and fine-tune their reinforcement learning models.
Related articles:
Amazon scale-model autonomous car aims to jump-start devs with AI
Robot racing car unveiled at Mobile World Congress
Autonomous ship guidance system combines probabilistic modeling, AI
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
