Learning-based motion planning for AMZ Driverless
HTML-код
- Опубликовано: 11 сен 2024
- gotthard driverless is now able to learn and thus improve the lap times consecutively!
Further information can be found in: www.idsc.ethz.c...
_____________________________________________________
Visit our website and follow us on social media!
AMZ driverless Website: driverless.amzracing.ch
AMZ Racing on Facebook: / amzracing
AMZ Racing on Twitter: am...
AMZ Racing on Instagram: www.instagram....
Hi guys, are you getting close to the car's power/traction limits with your system? if not, then what is your number one bottleneck? Is it sensing, planning or control?
We are getting to the traction limit in corners. In the fast corners, we are taking advantage of the aerodynamics package. At this point, the bottleneck looks to be combined. Not a single package but rather the fusion of all of them.
@@jurajkabzan86 Wow, so the actual trajectory it's taking already reaches physical limits.
Why does it often run wide? Does it fail at holding the planned trajectory or is that indeed the trajectory it computed as optimal?
(PS that guy on LikedIn copied my comment :) )
Good job! Is it beating your human lap times?
Nope its not. Not yet - next car is coming soon.
Good work.
The car seems to be somewhat afraid of cutting corners. I don't doubt you can get this thing to drive faster without human driver. It just needs some more confidence =).
Amazing. Could you use a drone view to improve it?