{"id":31223672,"url":"https://github.com/mit-acl/roman_ros","last_synced_at":"2025-09-21T22:54:18.139Z","repository":{"id":271570650,"uuid":"902994310","full_name":"mit-acl/roman_ros","owner":"mit-acl","description":"ROS1/2 wrapper for ROMAN, a view-invariant global localization method","archived":false,"fork":false,"pushed_at":"2025-07-29T00:19:55.000Z","size":686,"stargazers_count":88,"open_issues_count":0,"forks_count":11,"subscribers_count":4,"default_branch":"ros2","last_synced_at":"2025-07-29T02:31:14.793Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mit-acl.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2024-12-13T17:43:41.000Z","updated_at":"2025-07-29T00:20:00.000Z","dependencies_parsed_at":"2025-05-08T21:30:00.529Z","dependency_job_id":"3aa56f8f-342d-4ce1-9750-6e7a775aaff8","html_url":"https://github.com/mit-acl/roman_ros","commit_stats":null,"previous_names":["mit-acl/roman_ros"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mit-acl/roman_ros","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mit-acl%2Froman_ros","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mit-acl%2Froman_ros/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mit-acl%2Froman_ros/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mit-acl%2Froman_ros/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mit-acl","download_url":"https://codeload.github.com/mit-acl/roman_ros/tar.gz/refs/heads/ros2","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mit-acl%2Froman_ros/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276318993,"owners_count":25621651,"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","status":"online","status_checked_at":"2025-09-21T02:00:07.055Z","response_time":72,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2025-09-21T22:54:15.674Z","updated_at":"2025-09-21T22:54:18.134Z","avatar_url":"https://github.com/mit-acl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ROMAN ROS2\n\n\u003cimg src=\"./media/opposite_view_loop_closure.jpg\" alt=\"Opposite view loop closure\" width=\"500\"/\u003e\n\nWelcome to roman_ros2, a ROS2 wrapper for [ROMAN](https://github.com/mit-acl/ROMAN) (\u003cins\u003eR\u003c/ins\u003eobust \u003cins\u003eO\u003c/ins\u003ebject \u003cins\u003eM\u003c/ins\u003eap \u003cins\u003eA\u003c/ins\u003elignment A\u003cins\u003en\u003c/ins\u003eywhere).\nROMAN is a view-invariant global localization method that maps open-set objects and uses the geometry, shape, and semantics of objects to find the transformation between a current pose and previously created object map.\nThis enables loop closure between robots even when a scene is observed from *opposite views.*\n\nDemo videos, the paper, and more can be found at the [ROMAN project website](https://acl.mit.edu/roman/). \nCheckout the main branch for the ROS1 wrapper.\n\n## Citation\n\nIf you find ROMAN useful in your work, please cite our [paper](https://www.roboticsproceedings.org/rss21/p029.pdf):\n\nM.B. Peterson, Y.X. Jia, Y. Tian, A. Thomas, and J.P. How, \"ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization,\"\n*Robotics: Science and Systems*, 2025.\n\n```\n@inproceedings{peterson2025roman,\n  title={{ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization}},\n  author={Peterson, Mason B and Jia, Yi Xuan and Tian, Yulun and Thomas, Annika and How, Jonathan P},\n  booktitle={Robotics: Science and Systems (RSS)},\n  pdf={https://www.roboticsproceedings.org/rss21/p029.pdf},\n  year={2025}\n}\n```\n\n# Install\n\n#### Step 1: Set up and build ROS workspace\n\nIn the **root directory of your ROS workspace** (for example, `mkdir ~/roman_ws \u0026\u0026 cd ~/roman_ws`) run:\n\n```\ngit clone https://github.com/mit-acl/roman_ros.git src/roman_ros2\nvcs import src \u003c src/roman_ros2/install/packages.yaml\ncolcon build\n```\n\n#### Step 2: Install ROMAN Python package\n\nFirst, **activate the python environment** you would like to use with ROMAN. For example, build and source a python virtual environment as follows:\n\n```\npython3 -m venv ./venv\ntouch ./venv/COLCON_IGNORE # so that colcon does not try to build packages in the environment\nsource ./venv/bin/activate\n```\n\nOnce your environment has been activated, run\n\n```\n./src/roman_ros2/install/install_roman.bash\n```\n\nto install the ROMAN python package and download required model weights.\n\n#### Step 3: Set up environment variables\n\nFor running `roman_ros2`, you will need to set the `ROMAN_WEIGHTS` environment variable. \nYou may want to run the following to add this environment variable to your `.zshrc` file:\n\n```\necho export ROMAN_WEIGHTS=$(realpath ./src/roman_ros2/weights) \u003e\u003e ~/.zshrc\n```\n\nor `.bashrc` file:\n\n```\necho export ROMAN_WEIGHTS=$(realpath ./src/roman_ros2/weights) \u003e\u003e ~/.bashrc\n```\n\nFinally, the examples will source your python environment by calling `$ROMAN_ENV_ACTIVATE`. \nBefore running the examples run (or put the following in your `~/.zshrc` or `~/.bashrc`):\n\n```\nexport ROMAN_ENV_ACTIVATE=\u003cenvironment activation command\u003e\n```\n\nIf you used a Python virtual environment as described above, this would look something like: `export ROMAN_ENV_ACTIVATE=\"source ~/roman_ws/venv/bin/activate\"`\n\n#### Step 4: Build the ROS2 workspace\n\nNote that `roman_ros2` currently requires that `--simlink-install` option is not used when building. In `~/roman_ws` or the root of your workspace location, run:\n\n```\ncolcon build\n```\n\n# Examples\n\nA few example demos can be run following the [examples instructions](./examples/README.md).\nThe provided examples include running ROMAN on a pre-recorded bag, using ROMAN for single robot loop closures, and the main `roman_ros2` demo that creates ROMAN maps across two camera sessions and then aligns the maps from the camera sessions without any initial pose information.\n\n# Device Requirements\n\nTo run ROMAN with full performance, a GPU is required. \nHowever, ROMAN can still be run on CPU only although semantics cannot be computed and ROMAN will run much slower, which both cause a degradation in performance.\n\nIf you would like to configure the repo to use CPU, cd into this repo and run\n\n```\npython3 ./scripts/configure_cpu_or_gpu.py --device cpu\n```\n\n---\n\nThis research is supported by Ford Motor Company, DSTA, ONR, and\nARL DCIST under Cooperative Agreement Number W911NF-17-2-0181.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmit-acl%2Froman_ros","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmit-acl%2Froman_ros","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmit-acl%2Froman_ros/lists"}