Release ReSC-pilot on Hugging Face

[NielsRogge]

Hello @JaimeParker 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability.If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.

The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),
you can also claim the paper as yours which will show up on your public profile at HF.

I see that the code and pre-trained model weights will be released once the refactoring work is complete, would you like to host the model you've pre-trained on https://huggingface.co/models once it's ready? Would you also consider open-sourcing any datasets or demos?
Hosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,
link it to the paper page, etc.

If you're down, leaving a guide here. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin
class which adds from_pretrained and push_to_hub to the model which lets you to upload the model and people to download and use models right away.
If you do not want this and directly want to upload model through UI or however you want, people can also use hf_hub_download.

After uploaded, we can also link the models to the paper page (read here) so people can discover your model.

You can also build a demo for your model on Spaces, we can provide you a ZeroGPU grant,
which gives you A100 GPUs for free.

Let me know if you're interested/need any guidance :)

Kind regards,

Niels

[JaimeParker]

@NielsRogge

Hi Niels,

Thank you for reaching out and for your interest in my work! I appreciate your suggestions on improving its visibility and making it more accessible through Hugging Face.

I’m not very familiar with Hugging Face’s ecosystem, but your insights are really helpful. When we open-source the project, we’ll definitely consider ways to maximize its impact, including hosting on HF if it aligns with our goals.

This work is a quadrotor motion planning framework, similar to Fast-Planner and EGO-Planner, but with an integrated reinforcement learning (RL) training framework. I’m not sure how well this fits within the Hugging Face community, as robotics research and tools are typically open-sourced on GitHub (I guess, my opinion).

Regarding the paper, its availability depends on licensing constraints related to the target journal. At the very least, an arXiv perpetual non-exclusive license should be fine, but I’m not sure how HF’s paper hosting aligns with these policies.

Thanks again for your detailed guidance on using HF! I’ll keep it in mind as we move forward.

Best,
Zhaohong

[NielsRogge]

Thank you for the clarifications!

At Hugging Face we are developing LeRobot for easier access to state-of-the-art robotics. We recently integrated the Pi0 policy.

We mainly recommend Github for open-sourcing code, but Hugging Face whenever you want to release model weights, datasets, or want to demo your model in an easy way. For example, LeRobot stores the weights of all its trained policies here: https://huggingface.co/models?other=lerobot. They all also have a "robotics" tag, enabling people to easier find them.

A demo can be found here: https://huggingface.co/spaces/lerobot/visualize_dataset.

If you have any of these artifacts, I'm happy to guide you on how to make them easier accessible.

Kind regards,
Niels

[JaimeParker]

@NielsRogge

Hi Niels,

Thanks for the additional information and examples! It’s great to see Hugging Face expanding into robotics with LeRobot. Once we open-source the project on GitHub, we’ll also look into integrating it with HF where appropriate (like model weights and demos that you mentioned).

Appreciate your guidance and will keep it in mind as moving forward.

Best,
Zhaohong