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

About target point in training and testing #32

Closed
penghao-wu opened this issue Nov 29, 2021 · 1 comment
Closed

About target point in training and testing #32

penghao-wu opened this issue Nov 29, 2021 · 1 comment

Comments

@penghao-wu
Copy link

Hi, I noticed that when you are collecting training data using autopilot, your target point are the far_nodes coming from _command_planner. However, when your actual model based agent is tested, it uses the _waypoint_planner to get target point which corresponds to near node. I think it is better to use the near nodes both for training and testing? Or do I miss something?

@ap229997
Copy link
Collaborator

near_node is the next waypoint after 4 metres whereas the far node is the next waypoint after 7 metres. During testing, I don't think it matters much whether you use near node or far node since the waypoints along the route are quite far from each other. But, I agree that it's better to keep it consistent between training and testing.

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

2 participants