You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I wish you good luck with the tier2 and tier3. Frankly I had planned to do that as well, however it turned out much more difficult that I thought: The rendering was just too pretty to reliably detect the gates 🤣
What I had in mind:
At the end of planning stage, compute an additional yaw correction that is necessary and assume a smooth transition so that you can directly add it to the planned trajectory. So the planning algorithm originally doesn't care about yaw as it is independent. However, you know roughly how the gates should look so you could try to align yourself in that orientation already. Obviously the realistic cases are much more complicated than that (gate can oriented such that it looks up or downwards), so you need to be careful with how you decompose rotation.
Be also very careful in the control stage. If you know some drone dynamics, you will realize that a drone has much control in yaw axis than in the rest of them. Ideally you want to incorporate that into your control problem and avoid unrealistic control problem as we try to operate on the limit.
Hi
I am really impressed by your work.
I would like to try your algorithm out in tier2 and tier3 as well (combining with perception, of course).
My idea is to detect gate in the FPV then infers its position and relative orientation and use this as one of the point to go.
However, to do so, I would need the drone to control yaw angle as well.
Could you please let me know of where to start to look at?
Best Regards,
Surfii3z
The text was updated successfully, but these errors were encountered: