Jetracer team

Team Jetracer is testing and using the Jetracer framework on robotic race cars and the Donkeycar Simulator.

Developers

Fully Autonomous Test Run

Drew Britten 05/19/2021

Jetracer Autonomous DIY Optimized

The Triton AI Jetracer team has cracked the code for the NVIDIA Jetracer DIY, optimizing how the Jetracer steering and throttle decisions made with PyTorch. The Triton AI Jetracer DIY robot now has the fastest lap time at 11.32 seconds because of the optimized training algorithm with carefully selected training images. Watch and learn a few Jetracer techniques to implement on your own Jetracer! Ask any questions Jetracer questions about our Jetracer!

Jetracer outside

Fully Autonomous part 1

Fully Autonomous part 2

Triton AI Jetracer DIY

Waveshare Jetracer Pro

Triton AI Jetracer DIY
– Uses a multiplexer to relay the signal from the radio controller to steering servo and motor.
– When channel 3 is switched on the multiplexer switches to the PWM. This is how the Jetracer controls the throttle and steering.
– Uses standard Jetracer github repo and Adafruit-PureIO library for I2C with PWM.

Waveshare Jetracer Pro
– Uses Waveshare “expansion board” that is a custom multipurpose PCB that distributes power to the Jetson and motors from 8.4v batteries.
– The expansion board also acts as the PWM interfacing the jetson to the motors via singal.
– Expansion board also uses OLED to display IP address when connecting via Jupyter Notebook.
– Uses Waveshare/Jetracer github repo fork and UPDATED Adafruit-PureIO library.
– Need to create Waveshare repo folder for more library resources for the expansion board.

Camera mount

The Waveshare Jetracer Pro kit comes with a metal camera mount that can cause the PCB to break if the camera mount had a major impact. So our team member Lavita designed a new “breakable” camera mount prototype that is a magnetically re-attachable.

All Jetracer posts

Virtual Tournament 7/31/21

Drew Britten 07/31/2021

Robocar Virtual Tournament7/31/2021 NEW TRACK! https://youtu.be/bE8LnOQ3PfQ Triton AI gets second place with Jetsim on the new circuit launch track in the final latter of Virtual

COSMOS High School Workshop

Drew Britten 07/14/2021

COSMOSHigh School virtual Workshop7/14/2021 Triton AI had the opportunity to conduct a virtual programming workshop for the COSMSOS Autonomous driving summer program! 25+ High school

Circuit Launch Tournament 5/22/2021

Drew Britten 05/22/2021

Circuit Launch Tournament May 22, 2021 Full Tournament video After more than a year of virtual and outdoor events we were finally able to compete

Jetracer Optimized

Drew Britten 05/19/2021

Jetracer Autonomous DIY Optimized https://youtu.be/fgqukxg3LHc The Triton AI Jetracer team has cracked the code for the NVIDIA Jetracer DIY, optimizing how the Jetracer steering and

Jetsim’s First Tournament

Parth Patel 03/22/2021

Jetsim’s first Virtual Tournament This was the first tournament that I entered using Jetsim. Andrew and I spent a lot of time and effort into

Jetsim

Drew Britten 03/20/2021

Jetsim is Alive! https://youtu.be/OslGWZIrPxMThe Triton AI Jetracer team has successfully built an autonomous driving model in the Donkeycar simulator using NVIDIA’s open source Jetracer framework.

Jetracer Pro Modification

Drew Britten 01/26/2021

Waveshare Jetracer Pro gets modified https://youtu.be/bwDbZgUgWmc Triton AI has added some modifications to the Waveshare Jetracer Pro kit! It is now controlled via radio controller

Jetbot

Parth Patel 01/03/2021

Jetbot https://youtu.be/-KbXeafMG50 Team Jetracer is experimenting with the Waveshare Jetbot to understand how Pytorch works in detail. Jetbot and Jetracer have a lot in common