Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

execute trajectories #12

Open
Armandpl opened this issue May 18, 2023 · 1 comment
Open

execute trajectories #12

Armandpl opened this issue May 18, 2023 · 1 comment

Comments

@Armandpl
Copy link
Owner

Armandpl commented May 18, 2023

  • stanley controller?
  • gain scheduling?
  • calibrate cam?
  • calibration rig? relative to car axles? then we'll know relative to center of mass
@Armandpl
Copy link
Owner Author

Armandpl commented Jun 7, 2023

alright there are multiples ways to go:

  • geometric controllers (stanley/purepursuit): stanley looks like it could work with a bit more tuning
    • but it's not robust in any way
  • Model- and Acceleration-based Pursuit Controller for
    High-Performance Autonomous Racing
    • no idea if this works but its well sold and there is code
    • they claim it's between mpc and geometric methods, good performances but inexpensive and easy to implement
    • main advantage is they take into account tire slip, idk if we need to in our case?
    • they also do some system id, might look into that
  • maybe there exist other controllers like the one above?
  • do some system id on our system, retrain rl, have the neural net output steering for each step
    • scale the steering and voila? depends on the accuracy of the model
    • could try it before the system id though
    • should we model ackerman steering?
  • bite the bullet an implement a mpc controller

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant