graphslam
=========
.. image:: https://github.com/JeffLIrion/python-graphslam/actions/workflows/python-package.yml/badge.svg?branch=master
:target: https://github.com/JeffLIrion/python-graphslam/actions/workflows/python-package.yml
.. image:: https://coveralls.io/repos/github/JeffLIrion/python-graphslam/badge.svg?branch=master
:target: https://coveralls.io/github/JeffLIrion/python-graphslam?branch=master
Documentation for this package can be found at https://python-graphslam.readthedocs.io/.
This package implements a Graph SLAM solver in Python.
Features
--------
- Optimize `R^2`, `R^3`, `SE(2)`, and `SE(3)` datasets
- Analytic Jacobians
- Supports odometry and landmark edges
- Supports custom edge types (see `tests/test_custom_edge.py <https://github.com/JeffLIrion/python-graphslam/blob/master/tests/test_custom_edge.py>`_ for an example)
- Import and export .g2o files
Installation
------------
.. code-block::
pip install graphslam
Example Usage
-------------
SE(3) Dataset
^^^^^^^^^^^^^
.. code-block:: python
>>> from graphslam.graph import Graph
>>> g = Graph.from_g2o("data/parking-garage.g2o") # https://lucacarlone.mit.edu/datasets/
>>> g.plot(vertex_markersize=1)
>>> g.calc_chi2()
16720.02100546733
>>> g.optimize()
>>> g.plot(vertex_markersize=1)
**Output:**
::
Iteration chi^2 rel. change
--------- ----- -----------
0 16720.0210
1 45.6644 -0.997269
2 1.2936 -0.971671
3 1.2387 -0.042457
4 1.2387 -0.000001
+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+
| **Original** | **Optimized** |
+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+
| .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/parking-garage.png | .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/parking-garage-optimized.png |
+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+
SE(2) Dataset
^^^^^^^^^^^^^
.. code-block:: python
>>> from graphslam.graph import Graph
>>> g = Graph.from_g2o("data/input_INTEL.g2o") # https://lucacarlone.mit.edu/datasets/
>>> g.plot()
>>> g.calc_chi2()
7191686.382493544
>>> g.optimize()
>>> g.plot()
**Output:**
::
Iteration chi^2 rel. change
--------- ----- -----------
0 7191686.3825
1 319950425.6477 43.488929
2 124950341.8035 -0.609470
3 338165.0770 -0.997294
4 734.7343 -0.997827
5 215.8405 -0.706233
6 215.8405 -0.000000
+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+
| **Original** | **Optimized** |
+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+
| .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/input_INTEL.png | .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/input_INTEL-optimized.png |
+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+
References and Acknowledgments
------------------------------
1. Grisetti, G., Kummerle, R., Stachniss, C. and Burgard, W., 2010. `A tutorial on graph-based SLAM <http://domino.informatik.uni-freiburg.de/teaching/ws10/praktikum/slamtutorial.pdf>`_. IEEE Intelligent Transportation Systems Magazine, 2(4), pp.31-43.
2. Blanco, J.L., 2010. `A tutorial on SE(3) transformation parameterizations and on-manifold optimization <http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.468.5407&rep=rep1&type=pdf>`_. University of Malaga, Tech. Rep, 3.
3. Carlone, L., Tron, R., Daniilidis, K. and Dellaert, F., 2015, May. `Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization <https://smartech.gatech.edu/bitstream/handle/1853/53710/Carlone15icra.pdf>`_. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 4597-4604). IEEE.
4. Carlone, L. and Censi, A., 2014. `From angular manifolds to the integer lattice: Guaranteed orientation estimation with application to pose graph optimization <https://arxiv.org/pdf/1211.3063.pdf>`_. IEEE Transactions on Robotics, 30(2), pp.475-492.
Thanks to Luca Larlone for allowing inclusion of the `Intel and parking garage datasets <https://lucacarlone.mit.edu/datasets/>`_ in this repo.
Live Coding Graph SLAM in Python
--------------------------------
If you're interested, you can watch as I coded this up.
1. `Live coding Graph SLAM in Python (Part 1) <https://youtu.be/yXWkNC_A_YE>`_
2. `Live coding Graph SLAM in Python (Part 2) <https://youtu.be/M2udkF0UNUg>`_
3. `Live coding Graph SLAM in Python (Part 3) <https://youtu.be/CiBdVcIObVU>`_
4. `Live coding Graph SLAM in Python (Part 4) <https://youtu.be/GBAThis-_wM>`_
5. `Live coding Graph SLAM in Python (Part 5) <https://youtu.be/J3NyieGVwIw>`_
Raw data
{
"_id": null,
"home_page": "https://github.com/JeffLIrion/python-graphslam",
"name": "graphslam",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "graphslam,slam,graph,optimization,mapping",
"author": "Jeff Irion",
"author_email": "jefflirion@users.noreply.github.com",
"download_url": "https://files.pythonhosted.org/packages/19/12/04ff8145ef171b81fec9042f156e903a14656f290778d0433f14c7842d07/graphslam-0.0.17.tar.gz",
"platform": null,
"description": "graphslam\n=========\n\n.. image:: https://github.com/JeffLIrion/python-graphslam/actions/workflows/python-package.yml/badge.svg?branch=master\n :target: https://github.com/JeffLIrion/python-graphslam/actions/workflows/python-package.yml\n\n.. image:: https://coveralls.io/repos/github/JeffLIrion/python-graphslam/badge.svg?branch=master\n :target: https://coveralls.io/github/JeffLIrion/python-graphslam?branch=master\n\n\nDocumentation for this package can be found at https://python-graphslam.readthedocs.io/.\n\n\nThis package implements a Graph SLAM solver in Python.\n\nFeatures\n--------\n\n- Optimize `R^2`, `R^3`, `SE(2)`, and `SE(3)` datasets\n- Analytic Jacobians\n- Supports odometry and landmark edges\n- Supports custom edge types (see `tests/test_custom_edge.py <https://github.com/JeffLIrion/python-graphslam/blob/master/tests/test_custom_edge.py>`_ for an example)\n- Import and export .g2o files\n\n\nInstallation\n------------\n\n.. code-block::\n\n pip install graphslam\n\n\nExample Usage\n-------------\n\nSE(3) Dataset\n^^^^^^^^^^^^^\n\n.. code-block:: python\n\n >>> from graphslam.graph import Graph\n\n >>> g = Graph.from_g2o(\"data/parking-garage.g2o\") # https://lucacarlone.mit.edu/datasets/\n\n >>> g.plot(vertex_markersize=1)\n\n >>> g.calc_chi2()\n\n 16720.02100546733\n\n >>> g.optimize()\n\n >>> g.plot(vertex_markersize=1)\n\n\n**Output:**\n\n::\n\n Iteration chi^2 rel. change\n --------- ----- -----------\n 0 16720.0210\n 1 45.6644 -0.997269\n 2 1.2936 -0.971671\n 3 1.2387 -0.042457\n 4 1.2387 -0.000001\n\n\n+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+\n| **Original** | **Optimized** |\n+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+\n| .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/parking-garage.png | .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/parking-garage-optimized.png |\n+-----------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+\n\n\nSE(2) Dataset\n^^^^^^^^^^^^^\n\n.. code-block:: python\n\n >>> from graphslam.graph import Graph\n\n >>> g = Graph.from_g2o(\"data/input_INTEL.g2o\") # https://lucacarlone.mit.edu/datasets/\n\n >>> g.plot()\n\n >>> g.calc_chi2()\n\n 7191686.382493544\n\n >>> g.optimize()\n\n >>> g.plot()\n\n\n**Output:**\n\n::\n\n Iteration chi^2 rel. change\n --------- ----- -----------\n 0 7191686.3825\n 1 319950425.6477 43.488929\n 2 124950341.8035 -0.609470\n 3 338165.0770 -0.997294\n 4 734.7343 -0.997827\n 5 215.8405 -0.706233\n 6 215.8405 -0.000000\n\n\n+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+\n| **Original** | **Optimized** |\n+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+\n| .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/input_INTEL.png | .. image:: https://raw.githubusercontent.com/JeffLIrion/python-graphslam/master/docs/source/images/input_INTEL-optimized.png |\n+--------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+\n\nReferences and Acknowledgments\n------------------------------\n\n\n1. Grisetti, G., Kummerle, R., Stachniss, C. and Burgard, W., 2010. `A tutorial on graph-based SLAM <http://domino.informatik.uni-freiburg.de/teaching/ws10/praktikum/slamtutorial.pdf>`_. IEEE Intelligent Transportation Systems Magazine, 2(4), pp.31-43.\n2. Blanco, J.L., 2010. `A tutorial on SE(3) transformation parameterizations and on-manifold optimization <http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.468.5407&rep=rep1&type=pdf>`_. University of Malaga, Tech. Rep, 3.\n3. Carlone, L., Tron, R., Daniilidis, K. and Dellaert, F., 2015, May. `Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization <https://smartech.gatech.edu/bitstream/handle/1853/53710/Carlone15icra.pdf>`_. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 4597-4604). IEEE.\n4. Carlone, L. and Censi, A., 2014. `From angular manifolds to the integer lattice: Guaranteed orientation estimation with application to pose graph optimization <https://arxiv.org/pdf/1211.3063.pdf>`_. IEEE Transactions on Robotics, 30(2), pp.475-492.\n\n\nThanks to Luca Larlone for allowing inclusion of the `Intel and parking garage datasets <https://lucacarlone.mit.edu/datasets/>`_ in this repo.\n\n\nLive Coding Graph SLAM in Python\n--------------------------------\n\nIf you're interested, you can watch as I coded this up.\n\n1. `Live coding Graph SLAM in Python (Part 1) <https://youtu.be/yXWkNC_A_YE>`_\n2. `Live coding Graph SLAM in Python (Part 2) <https://youtu.be/M2udkF0UNUg>`_\n3. `Live coding Graph SLAM in Python (Part 3) <https://youtu.be/CiBdVcIObVU>`_\n4. `Live coding Graph SLAM in Python (Part 4) <https://youtu.be/GBAThis-_wM>`_\n5. `Live coding Graph SLAM in Python (Part 5) <https://youtu.be/J3NyieGVwIw>`_\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Graph SLAM solver in Python",
"version": "0.0.17",
"project_urls": {
"Homepage": "https://github.com/JeffLIrion/python-graphslam"
},
"split_keywords": [
"graphslam",
"slam",
"graph",
"optimization",
"mapping"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "191204ff8145ef171b81fec9042f156e903a14656f290778d0433f14c7842d07",
"md5": "25c64b482927fb1354fc01a53e11975a",
"sha256": "482770a1e6aea732bbc5944d83a65e1ed74c458e29fc40b69f33178a3a87b574"
},
"downloads": -1,
"filename": "graphslam-0.0.17.tar.gz",
"has_sig": false,
"md5_digest": "25c64b482927fb1354fc01a53e11975a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 35466,
"upload_time": "2023-11-17T08:27:15",
"upload_time_iso_8601": "2023-11-17T08:27:15.411866Z",
"url": "https://files.pythonhosted.org/packages/19/12/04ff8145ef171b81fec9042f156e903a14656f290778d0433f14c7842d07/graphslam-0.0.17.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-11-17 08:27:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "JeffLIrion",
"github_project": "python-graphslam",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "graphslam"
}
JSON
