{"id":20791375,"url":"https://github.com/hyperplane-lab/rgbmanip","last_synced_at":"2025-05-05T21:17:26.934Z","repository":{"id":230027339,"uuid":"777119033","full_name":"hyperplane-lab/RGBManip","owner":"hyperplane-lab","description":"Official implementation of RGBManip (ICRA2024)","archived":false,"fork":false,"pushed_at":"2024-08-29T13:19:20.000Z","size":6548,"stargazers_count":33,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-05T21:17:19.566Z","etag":null,"topics":["monocular-depth-estimation","rl","robotics"],"latest_commit_sha":null,"homepage":"https://rgbmanip.github.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hyperplane-lab.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-03-25T08:35:35.000Z","updated_at":"2025-04-22T08:38:14.000Z","dependencies_parsed_at":"2024-08-29T14:48:19.401Z","dependency_job_id":"3a196f98-ad77-4ae3-b7a3-c487b2a46047","html_url":"https://github.com/hyperplane-lab/RGBManip","commit_stats":null,"previous_names":["hyperplane-lab/rgbmanip"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyperplane-lab%2FRGBManip","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyperplane-lab%2FRGBManip/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyperplane-lab%2FRGBManip/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyperplane-lab%2FRGBManip/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hyperplane-lab","download_url":"https://codeload.github.com/hyperplane-lab/RGBManip/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252577028,"owners_count":21770721,"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":["monocular-depth-estimation","rl","robotics"],"created_at":"2024-11-17T15:44:18.284Z","updated_at":"2025-05-05T21:17:26.916Z","avatar_url":"https://github.com/hyperplane-lab.png","language":"Python","readme":"# Adapose\n\n## Install\n\nInstall dependencies using `pip install -r requirements.txt`. The instalation is tested with `setuptools==65.6.3`. Some later versions may not be compatible.\n\n*Potential Dependency Inssues:* Users have reported `Module not Found` error with mplib. This project is developed when the newest version of mplib is `mplib==0.0.8`. Newer versions if mplib may not be compatible with this project. We recommend using `mplib\u003c=0.1.0`\n\n## Download Dataset and Checkpoints\n\nWe provided scripts to fully automate dataset and checkpoint downloading from google drive. Just run `sh install.sh` to do the stuff and wait. The total file size to download is around 1GB.\n\nYou can also manually download them following the steps:\n\nFirst, the dataset can be downloaded from [google drive](https://drive.google.com/file/d/154g8SzGFWOcLLjes40aTXFoREX47-ZPk/view?usp=sharing). Download it and decompress it into `downloads/dataset`\n\nSecond, download checkpoints for Pose Estimator from [google drive](https://drive.google.com/drive/folders/1WshZaRVllWxHfUFK1--e1hQd_64dAKMz?usp=sharing), and move all four checkpoints into `downloads/pose_estimator/\u003cname\u003e.pth`.\n\nThird, download checkpoints for Global Scheduling Policy from [google drive](https://drive.google.com/drive/folders/1YMI38jeLkPJQa_HJ-RnbQV36zPk4_OvH?usp=sharing), and save all checkpoints into `downloads/global_sheduling_policy/\u003cname\u003e_0.pt`. Notice the `_0` is necessary since our code examines this number. Use `controller.load=CheckpointPath` option to load checkpoints.\n\n## Run Experiments\n\nTo run experiments, use command line options: `python train.py dataset=?? task=?? pose_estimator=?? manipulation=?? controller=?? train=??`\n\nPossible options include:\n\n- dataset:\n  - cabinet_train\n  - cabinet_test\n  - drawer_train\n  - drawer_test\n  - mug_train\n  - mug_test\n  - pot_train\n  - pot_test\n  - real_world\n- task:\n  - open_cabinet\n  - open_cabinet_45\n  - open_cabinet_no_dr\n  - open_drawer\n  - open_drawer_30\n  - open_drawer_no_dr\n  - open_pot\n  - pick_mig\n  - real_world\n- pose_extimator:\n  - adapose_cabinet\n  - adapose_drawer\n  - adapose_mug\n  - adapose_pot\n  - ground_truth\n- manipulation:\n  - open_cabinet\n  - open_cabinet_open_loop\n  - open_drawer\n  - open_drawer_open_looop\n  - open_pot\n  - open_pot_open_loop\n  - pick_mug\n  - pick_mug_open_loop\n- controller\n  - gt_pose\n  - heuristic_pose\n  - rl\n- train\n  - controller\n  - test\n  - collect: Used to collect offline data for some baselines.\n  - test_baselines: Test with offline actions generated by some baselines.\n\nSome other possible arguments are:\n\n- task.num_envs=X: Number of parallel environments.\n- headless=True/False: Whether to show graphics.\n- viewerless=True/False: Whether to disable on-hand camera to accelerate some non-vision tasks.\n- exp_name=XXX: The name of the experiment (used for saving models and logging).\n- controller.load=Checkpoint: Load the saved controller checkpoint.\n\nAll other configurations can be modified using the [hydra](https://hydra.cc/docs/intro/) style command line options.\n\n## Miscs\n\nThe scripts for drawing the plots included in our paper is also provided in `miscs/plot`.\n\n## Citations\n\nTo cite us at\n\n```latex\n@article{an2023rgbmanip,\n  title={RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation},\n  author={An, Boshi and Geng, Yiran and Chen, Kai and Li, Xiaoqi and Dou, Qi and Dong, Hao},\n  journal={arXiv preprint arXiv:2310.03478},\n  year={2023}\n}\n```","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhyperplane-lab%2Frgbmanip","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhyperplane-lab%2Frgbmanip","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhyperplane-lab%2Frgbmanip/lists"}