{"id":20789482,"url":"https://github.com/real-stanford/umpnet","last_synced_at":"2025-05-05T19:44:07.248Z","repository":{"id":46044493,"uuid":"455773222","full_name":"real-stanford/umpnet","owner":"real-stanford","description":"[RA-L / ICRA 2022] UMPNet: Universal Manipulation Policy Network for Articulated Objects","archived":false,"fork":false,"pushed_at":"2022-02-16T07:11:56.000Z","size":2325,"stargazers_count":56,"open_issues_count":2,"forks_count":6,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-30T23:11:08.499Z","etag":null,"topics":["computer-vision","robotics","simulation"],"latest_commit_sha":null,"homepage":"https://ump-net.cs.columbia.edu/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/real-stanford.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-02-05T04:22:27.000Z","updated_at":"2025-02-19T08:08:18.000Z","dependencies_parsed_at":"2022-07-18T21:49:07.470Z","dependency_job_id":null,"html_url":"https://github.com/real-stanford/umpnet","commit_stats":null,"previous_names":["real-stanford/umpnet","columbia-ai-robotics/umpnet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/real-stanford%2Fumpnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/real-stanford%2Fumpnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/real-stanford%2Fumpnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/real-stanford%2Fumpnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/real-stanford","download_url":"https://codeload.github.com/real-stanford/umpnet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252564102,"owners_count":21768589,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","robotics","simulation"],"created_at":"2024-11-17T15:24:19.652Z","updated_at":"2025-05-05T19:44:07.215Z","avatar_url":"https://github.com/real-stanford.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# UMPNet: Universal Manipulation Policy Network for Articulated Objects\n\n\n[Zhenjia Xu](http://www.zhenjiaxu.com/),\n[Zhanpeng He](https://zhanpenghe.github.io/),\n[Shuran Song](https://www.cs.columbia.edu/~shurans/)\n\u003cbr\u003e\nColumbia University\n\u003cbr\u003e\nRobotics and Automation Letters (RA-L) / ICRA 2022\n\n### [Project Page](https://ump-net.cs.columbia.edu/) | [Video](https://youtu.be/KqlvcL9RqKM) | [arXiv](https://arxiv.org/abs/2109.05668)\n\n## Overview\nThis repo contains the PyTorch implementation for paper \"UMPNet: Universal Manipulation Policy Network for Articulated Objects\".\n\n![teaser](figures/teaser.jpg)\n## Content\n\n- [Prerequisites](#prerequisites)\n- [Data Preparation](#data-preparation)\n- [Testing](#testing)\n- [Training](#training)\n\n## Prerequisites\n\nWe have prepared a conda YAML file which contains all the python dependencies.\n```sh\nconda env create -f environment.yml\n```\n\n## Data Preparation\n\nPrepare object URDF and pretrained model.\n- [mobility_dataset](https://ump-net.cs.columbia.edu/download/mobility_dataset.zip): URDF of 12 training and 10 testing object categories.\n- [pretrained](https://ump-net.cs.columbia.edu/download/pretrained.zip): pretrained model.\n\nDownload, unzip, and organize as follows:\n```\n/umpnet\n    /mobility_dataset\n    /pretrained\n    ...\n```\n\n## Testing\n\n### Test with GUI\n\nThere are also two modes of testing: exploration and manipulation.\n```sh\n# Open-ended state exploration\npython test_gui.py --mode exploration --category CATEGORY\n\n# Goal conditioned manipulation\npython test_gui.py --mode manipulation --category CATEGORY\n```\nHere `CATEGORY` can be chosen from:\n- training categories]: Refrigerator, FoldingChair, Laptop, Stapler, TrashCan, Microwave, Toilet, Window, StorageFurniture, Switch, Kettle, Toy\n- [Testing categories]: Box, Phone, Dishwasher, Safe, Oven, WashingMachine, Table, KitchenPot, Bucket, Door\n\n![teaser](figures/objects.jpg)\n### Quantitative Evaluation\nThere are also two modes of testing: exploration and manipulation.\n```sh\n# Open-ended state exploration\npython test_quantitative.py --mode exploration\n\n# Goal conditioned manipulation\npython test_quantitative.py --mode manipulation\n```\nBy default, it will run quantitative evaluation for each category. You can modify pool_list(L91) to run evaluation for a specific category.\n\n## Training\nHyper-parameters mentioned in paper are provided in default arguments.\n```sh\npython train.py --exp EXP_NAME\n```\nThen a directory will be created at `exp/EXP_NAME`, in which checkpoints, visualization, and replay buffer will be stored.\n\n## BibTeX\n```\n@article{xu2022umpnet,\n  title={UMPNet: Universal manipulation policy network for articulated objects},\n  author={Xu, Zhenjia and Zhanpeng, He and Song, Shuran},\n  journal={IEEE Robotics and Automation Letters},\n  year={2022},\n  publisher={IEEE}\n}\n```\n\n## License\n\nThis repository is released under the MIT license. See [LICENSE](LICENSE) for additional details.\n\n## Acknowledgement\n\n- The code for [spherical sampling](spherical_sampling.py) is modified from [area-beamforming](https://github.com/marc1701/area-beamforming).\n- The code for [UNet](unet_parts.py) is modified from [Pytorch-UNet](https://github.com/milesial/Pytorch-UNet).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freal-stanford%2Fumpnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freal-stanford%2Fumpnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freal-stanford%2Fumpnet/lists"}