Package Summary

Tags No category tags.
Version 1.0.3
License GPLv3
Build type CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/MOLAorg/mola.git
VCS Type git
VCS Version develop
Last Updated 2024-04-29
Dev Status DEVELOPED
CI status No Continuous Integration
Released RELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty

Additional Links

Maintainers

  • Jose-Luis Blanco-Claraco

Authors

  • Jose-Luis Blanco-Claraco

mola_relocalization

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty.

Note that particle filtering is implemented in its own repository under mrpt_navigation.

Method #1: mola::RelocalizationICP_SE2

Takes a global and a local metric map, a SE(2) ROI, and tries to match the local map in the global map by running ICP from all initial guesses defined by a regular SE(2) lattice, returning the result as a SE(3) hashed lattice.

This method is based on mp2p_icp ICP pipelines.

Method #2: mola::RelocalizationLikelihood_SE2

Takes a global metric map, an observation, and a SE(2) ROI, and evaluates the likelihood of the observation in a regular SE(2) lattice.

This is based on mrpt maps observationLikelihood() evaluation, so the main parameters that determine the way likelihood is computed must be defined on before hand within each of the metric map layers of the input reference map. At present this algorithm is useful for these sensor/map types: - observations: pointclouds/2d_scan, reference_map: 2D gridmap - observations: pointclouds, reference_map: pointclouds

Example result for the mola::RelocalizationLikelihood_SE2 method (from a unit test, see the code for details):

mola_relocalize_figs

Figure: (top-left) Reference map. (bottom-left) Query map (actually, a decimated version is used internally). (top-right) Visualization of a slice of the returned likelihood field over a SE(2) ROI. The "slice" is for orientation (phi) equal to 0 (close to the actual pose transformation between the two maps). (bottom-right) The same likelihood slice, in real (x,y) coordinates (meters). The clear peak reveals, approximately, the location of the sought SE(2) transformation between the maps. Further refining is possible using ICP using this as initial guess.

Build and install

Refer to the root MOLA repository.

Docs and examples

See this package page in the documentation.

License

This package is released under the GNU GPL v3 license. Other options available upon request.

CHANGELOG

Changelog for package mola_relocalization

1.0.3 (2024-04-22)

  • RelocalizationICP_SE2: work in multiple threads and provides a feedback functor
  • Add new ICP-based relocalization method
  • Fix package.xml website URL
  • Contributors: Jose Luis Blanco-Claraco

1.0.2 (2024-04-04)

  • Implement SE(2) relocalization grid method
  • New package mola_relocalization
  • Contributors: Jose Luis Blanco-Claraco

1.0.1 (2024-03-28)

1.0.0 (2024-03-19)

0.2.2 (2023-09-08)

0.2.1 (2023-09-02)

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged mola_relocalization at Robotics Stack Exchange

Package Summary

Tags No category tags.
Version 1.0.3
License GPLv3
Build type CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/MOLAorg/mola.git
VCS Type git
VCS Version develop
Last Updated 2024-04-29
Dev Status DEVELOPED
CI status No Continuous Integration
Released RELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty

Additional Links

Maintainers

  • Jose-Luis Blanco-Claraco

Authors

  • Jose-Luis Blanco-Claraco

mola_relocalization

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty.

Note that particle filtering is implemented in its own repository under mrpt_navigation.

Method #1: mola::RelocalizationICP_SE2

Takes a global and a local metric map, a SE(2) ROI, and tries to match the local map in the global map by running ICP from all initial guesses defined by a regular SE(2) lattice, returning the result as a SE(3) hashed lattice.

This method is based on mp2p_icp ICP pipelines.

Method #2: mola::RelocalizationLikelihood_SE2

Takes a global metric map, an observation, and a SE(2) ROI, and evaluates the likelihood of the observation in a regular SE(2) lattice.

This is based on mrpt maps observationLikelihood() evaluation, so the main parameters that determine the way likelihood is computed must be defined on before hand within each of the metric map layers of the input reference map. At present this algorithm is useful for these sensor/map types: - observations: pointclouds/2d_scan, reference_map: 2D gridmap - observations: pointclouds, reference_map: pointclouds

Example result for the mola::RelocalizationLikelihood_SE2 method (from a unit test, see the code for details):

mola_relocalize_figs

Figure: (top-left) Reference map. (bottom-left) Query map (actually, a decimated version is used internally). (top-right) Visualization of a slice of the returned likelihood field over a SE(2) ROI. The "slice" is for orientation (phi) equal to 0 (close to the actual pose transformation between the two maps). (bottom-right) The same likelihood slice, in real (x,y) coordinates (meters). The clear peak reveals, approximately, the location of the sought SE(2) transformation between the maps. Further refining is possible using ICP using this as initial guess.

Build and install

Refer to the root MOLA repository.

Docs and examples

See this package page in the documentation.

License

This package is released under the GNU GPL v3 license. Other options available upon request.

CHANGELOG

Changelog for package mola_relocalization

1.0.3 (2024-04-22)

  • RelocalizationICP_SE2: work in multiple threads and provides a feedback functor
  • Add new ICP-based relocalization method
  • Fix package.xml website URL
  • Contributors: Jose Luis Blanco-Claraco

1.0.2 (2024-04-04)

  • Implement SE(2) relocalization grid method
  • New package mola_relocalization
  • Contributors: Jose Luis Blanco-Claraco

1.0.1 (2024-03-28)

1.0.0 (2024-03-19)

0.2.2 (2023-09-08)

0.2.1 (2023-09-02)

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged mola_relocalization at Robotics Stack Exchange

Package Summary

Tags No category tags.
Version 1.0.3
License GPLv3
Build type CMAKE
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/MOLAorg/mola.git
VCS Type git
VCS Version develop
Last Updated 2024-04-29
Dev Status DEVELOPED
CI status No Continuous Integration
Released RELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty

Additional Links

Maintainers

  • Jose-Luis Blanco-Claraco

Authors

  • Jose-Luis Blanco-Claraco

mola_relocalization

C++ library with algorithms for relocalization, global localization, or pose estimation given a large initial uncertainty.

Note that particle filtering is implemented in its own repository under mrpt_navigation.

Method #1: mola::RelocalizationICP_SE2

Takes a global and a local metric map, a SE(2) ROI, and tries to match the local map in the global map by running ICP from all initial guesses defined by a regular SE(2) lattice, returning the result as a SE(3) hashed lattice.

This method is based on mp2p_icp ICP pipelines.

Method #2: mola::RelocalizationLikelihood_SE2

Takes a global metric map, an observation, and a SE(2) ROI, and evaluates the likelihood of the observation in a regular SE(2) lattice.

This is based on mrpt maps observationLikelihood() evaluation, so the main parameters that determine the way likelihood is computed must be defined on before hand within each of the metric map layers of the input reference map. At present this algorithm is useful for these sensor/map types: - observations: pointclouds/2d_scan, reference_map: 2D gridmap - observations: pointclouds, reference_map: pointclouds

Example result for the mola::RelocalizationLikelihood_SE2 method (from a unit test, see the code for details):

mola_relocalize_figs

Figure: (top-left) Reference map. (bottom-left) Query map (actually, a decimated version is used internally). (top-right) Visualization of a slice of the returned likelihood field over a SE(2) ROI. The "slice" is for orientation (phi) equal to 0 (close to the actual pose transformation between the two maps). (bottom-right) The same likelihood slice, in real (x,y) coordinates (meters). The clear peak reveals, approximately, the location of the sought SE(2) transformation between the maps. Further refining is possible using ICP using this as initial guess.

Build and install

Refer to the root MOLA repository.

Docs and examples

See this package page in the documentation.

License

This package is released under the GNU GPL v3 license. Other options available upon request.

CHANGELOG

Changelog for package mola_relocalization

1.0.3 (2024-04-22)

  • RelocalizationICP_SE2: work in multiple threads and provides a feedback functor
  • Add new ICP-based relocalization method
  • Fix package.xml website URL
  • Contributors: Jose Luis Blanco-Claraco

1.0.2 (2024-04-04)

  • Implement SE(2) relocalization grid method
  • New package mola_relocalization
  • Contributors: Jose Luis Blanco-Claraco

1.0.1 (2024-03-28)

1.0.0 (2024-03-19)

0.2.2 (2023-09-08)

0.2.1 (2023-09-02)

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged mola_relocalization at Robotics Stack Exchange