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

The plan for open source code? #3

Closed
LarryZhangy opened this issue Jul 3, 2023 · 8 comments
Closed

The plan for open source code? #3

LarryZhangy opened this issue Jul 3, 2023 · 8 comments

Comments

@LarryZhangy
Copy link

Great work!It helped me a lot!
Could you tell me what is the plan for open source code?
Thank you very much!

@kashyap7x
Copy link
Collaborator

Thanks for your interest.

We plan to welcome community contributions to nuPlan garage for new results on the Val14 benchmark and the corresponding planner code. We want to make contributing to this project easy and transparent, so we will create a contribution guide after we have released our pre-trained models. The first release (for PDM-Open, PDM-Offset and PDM-Hybrid) is scheduled for this week.

@LarryZhangy
Copy link
Author

Thanks for your response.

I'm very interested in contributing to this project and looking forward to seeing the contribution guidelines!
I wonder if there are any candidate papers for the Val14 benchmark ?

@Syzygianinfern0
Copy link

From https://arxiv.org/abs/2302.07753, it looks like Urban Driver has much better performance metrics as compared to IDM. But it is not that way in your paper. Is there a reason to it?

@LarryZhangy
Copy link
Author

I want to contribute to this project, but i dont know which algorithm(from some paper) is worth to be Implemented.

@kashyap7x
Copy link
Collaborator

@Syzygianinfern0: Urban Driver (like all other learned methods) is great at open-loop ego-forecasting, which is the primary focus in the evaluations in Marcel's earlier paper https://arxiv.org/abs/2302.07753
It is the same in our paper: the OLS (Open Loop Score) metric of Urban Driver is 76, compared to 38 for IDM (Table 2). See Section 4 for an explanation of why the CLS and OLS metrics are not aligned.

@LarryZhangy: we are still in the process of finalizing the contribution guide, please be patient and we will release it soon! I don't have a concrete suggestion for which paper is worth most to implement. Some interesting candidates could be PlanT (https://www.katrinrenz.de/plant/) or any of the nuPlan challenge submissions that placed 2nd to 4th (https://opendrivelab.com/AD23Challenge.html#nuplan_planning)

@Syzygianinfern0
Copy link

Is there an estimated timeline on the visualization scripts?

@DanielDauner
Copy link
Collaborator

@Syzygianinfern0 Adding the visualization scripts is not our highest priority at the moment. However, you can visualize our planners using the nuBoard from nuPlan’s devkit.

@mh0797
Copy link
Collaborator

mh0797 commented Jul 24, 2023

Update:
We just merged the initial version of our contribution guidelines (see here)
Hence, I am closing this issue.

Feel free to reopen if the guidelines do not answer all of your questions.

@mh0797 mh0797 closed this as completed Jul 24, 2023
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

5 participants