NVIDIA-AI-IOT / jetracer

An autonomous AI racecar using NVIDIA Jetson Nano
MIT License
1.06k stars 319 forks source link

Dynamically adjusting JetRacer speed #112

Closed HamburgDave closed 2 years ago

HamburgDave commented 3 years ago

Has anyone tried to change JetRacer's speed (throttle) based on the images or maybe y-axis values? For example having a higher throttle on a straight section, slower in turns?

arickchan commented 2 years ago

I have using the floting value x , and change it to absolute value [ abs (x) ], use a formula 1 - abs (x), if x is at center (value = 0), the car can run with original setting speed, if x has +/- value, the speed will be reduced.

arickchan commented 2 years ago

But I think can have a better method to setup better dynamic speed of the car

HamburgDave commented 2 years ago

Thank you for the reply and this sounds quite interesting! I'd be interested in learning more if you're available.

There may be a demonstration of scale (1:10/1:5) cars in conjunction with the Indy Autonomous Challenge event on Oct. 23. It would be great, if possible, to incorporate your approach into the demo. Let me know if you're interested and we can discuss it further.

The other challenge I've been facing is training JetRacer to execute an overtaking (passing) maneuver. I think it can be done without adding a lidar but not sure. Would be interested in your thoughts on this as well if it's something you've considered. Thanks again for the reply and looking forward to connecting.

On Sep 24, 2021, at 3:27 AM, arickchan @.***> wrote:

 But I think can have a better method to setup better dynamic speed of the car

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.