Detailed Description

SLAM and PF-localization algorithms.

Back to list of all libraries | See all modules

Library `mrpt-slam`

[New in MRPT 2.0.0]

This library is part of MRPT and can be installed in Debian-based systems with:

    sudo apt install libmrpt-slam-dev

See: Using MRPT from your CMake project

Interesting stuff in this library:

mrpt::slam::CMetricMapBuilder: A virtual base for both ICP and RBPF-based SLAM.
mrpt::slam::CMonteCarloLocalization2D: Particle filter-based (Monte Carlo) localization for a robot in a planar scenario.
mrpt::maps::CMultiMetricMap: The most versatile kind of metric map, which contains an arbitrary number of any other maps.
Kalman Filters-based Range-Bearing SLAM, in 2D and 3D: See mrpt::slam::CRangeBearingKFSLAM and mrpt::slam::CRangeBearingKFSLAM2D.
Data association: The NN and the JCBB algorithms, as very generic templates. See data_association.h

See the full list of classes in mrpt::slam. Note that there are many classes in that namespace not in the library mrpt-slam, but in libraries mrpt-slam depends on. However, in you set mrpt-slam as a dependence of your project, you can be safe all mrpt::slam classes will be available to you.

See also: For Graph-SLAM, see the namespace mrpt::graphslam in the library mrpt-graphslam.

Collaboration diagram for [mrpt-slam]:

Classes
class	mrpt::detectors::CDetectorDoorCrossing

class	mrpt::maps::CRBPFParticleData
	Auxiliary class used in mrpt::maps::CMultiMetricMapPDF. More...

class	mrpt::slam::CGridMapAligner
	A class for aligning two multi-metric maps (with an occupancy grid maps and a points map, at least) based on features extraction and matching. More...

class	mrpt::slam::CICP
	Several implementations of ICP (Iterative closest point) algorithms for aligning two point maps or a point map wrt a grid map. More...

struct	mrpt::slam::map_keyframe_t
	Map keyframe, comprising raw observations and they as a metric map. More...

class	mrpt::slam::CIncrementalMapPartitioner
	Finds partitions in metric maps based on N-cut graph partition theory. More...

struct	mrpt::slam::TMetricMapAlignmentResult
	Used as base class for other result structures of each particular algorithm in CMetricMapsAlignmentAlgorithm derived classes. More...

class	mrpt::slam::CMetricMapsAlignmentAlgorithm
	A base class for any algorithm able of maps alignment. More...

class	mrpt::slam::CMonteCarloLocalization2D
	Declares a class that represents a Probability Density Function (PDF) over a 2D pose (x,y,phi), using a set of weighted samples. More...

class	mrpt::slam::CMonteCarloLocalization3D
	Declares a class that represents a Probability Density Function (PDF) over a 3D pose (x,y,phi,yaw,pitch,roll), using a set of weighted samples. More...

class	mrpt::slam::COccupancyGridMapFeatureExtractor
	A class for detecting features from occupancy grid maps. More...

class	mrpt::slam::CRejectionSamplingRangeOnlyLocalization
	An implementation of rejection sampling for generating 2D robot pose from range-only measurements within a landmarks (beacons) map. More...

class	mrpt::slam::PF_implementation< PARTICLE_TYPE, MYSELF, STORAGE >
	A set of common data shared by PF implementations for both SLAM and localization. More...

class	mrpt::slam::TKLDParams
	Option set for KLD algorithm. More...

struct	mrpt::slam::TMonteCarloLocalizationParams
	The struct for passing extra simulation parameters to the prediction stage when running a particle filter. More...

Namespaces
	mrpt::slam

Modules
	Metric SLAM algorithms

	Data association

Typedefs
using	mrpt::slam::similarity_func_t = std::function< double(const map_keyframe_t &kf1, const map_keyframe_t &kf2, const mrpt::poses::CPose3D &relPose2wrt1)>
	Type of similarity evaluator for map keyframes. More...

Enumerations
enum	mrpt::slam::TICPCovarianceMethod { mrpt::slam::icpCovLinealMSE = 0, mrpt::slam::icpCovFiniteDifferences }
	ICP covariance estimation methods, used in mrpt::slam::CICP::options. More...

enum	mrpt::slam::similarity_method_t : uint8_t { mrpt::slam::smMETRIC_MAP_MATCHING = 0, mrpt::slam::smOBSERVATION_OVERLAP, mrpt::slam::smCUSTOM_FUNCTION }
	For use in CIncrementalMapPartitioner. More...

Functions
template<class BINTYPE >
bool	mrpt::slam::PF_implementation< PARTICLE_TYPE, MYSELF, STORAGE >::PF_SLAM_implementation_gatherActionsCheckBothActObs (const mrpt::obs::CActionCollection actions, const mrpt::obs::CSensoryFrame sf)
	Auxiliary method called by PF implementations: return true if we have both action & observation, otherwise, return false AND accumulate the odometry so when we have an observation we didn't lose a thing. More...

Observations overlap functions
double	mrpt::slam::observationsOverlap (const mrpt::obs::CObservation o1, const mrpt::obs::CObservation o2, const mrpt::poses::CPose3D *pose_o2_wrt_o1=nullptr)
	Estimates the "overlap" or "matching ratio" of two observations (range [0,1]), possibly taking into account their relative positions. More...

double	mrpt::slam::observationsOverlap (const mrpt::obs::CObservation::Ptr &o1, const mrpt::obs::CObservation::Ptr &o2, const mrpt::poses::CPose3D *pose_o2_wrt_o1=nullptr)
	Estimates the "overlap" or "matching ratio" of two observations (range [0,1]), possibly taking into account their relative positions. More...

double	mrpt::slam::observationsOverlap (const mrpt::obs::CSensoryFrame &sf1, const mrpt::obs::CSensoryFrame &sf2, const mrpt::poses::CPose3D *pose_sf2_wrt_sf1=nullptr)
	Estimates the "overlap" or "matching ratio" of two set of observations (range [0,1]), possibly taking into account their relative positions. More...

double	mrpt::slam::observationsOverlap (const mrpt::obs::CSensoryFrame::Ptr &sf1, const mrpt::obs::CSensoryFrame::Ptr &sf2, const mrpt::poses::CPose3D *pose_sf2_wrt_sf1=nullptr)
	Estimates the "overlap" or "matching ratio" of two set of observations (range [0,1]), possibly taking into account their relative positions. More...

Typedef Documentation

◆ similarity_func_t

using mrpt::slam::similarity_func_t = typedef std::function<double( const map_keyframe_t& kf1, const map_keyframe_t& kf2, const mrpt::poses::CPose3D& relPose2wrt1)>

Type of similarity evaluator for map keyframes.

For use in CIncrementalMapPartitioner

Definition at line 49 of file CIncrementalMapPartitioner.h.

Enumeration Type Documentation

◆ similarity_method_t

enum mrpt::slam::similarity_method_t : uint8_t

For use in CIncrementalMapPartitioner.

Enumerator
smMETRIC_MAP_MATCHING
smOBSERVATION_OVERLAP
smCUSTOM_FUNCTION

Definition at line 27 of file CIncrementalMapPartitioner.h.

◆ TICPCovarianceMethod

enum mrpt::slam::TICPCovarianceMethod

ICP covariance estimation methods, used in mrpt::slam::CICP::options.

Enumerator
icpCovLinealMSE	Use the covariance of the optimal registration, disregarding uncertainty in data association.
icpCovFiniteDifferences	Covariance of a least-squares optimizer (includes data association uncertainty)

Definition at line 27 of file CICP.h.

Function Documentation

◆ observationsOverlap() [1/4]

double mrpt::slam::observationsOverlap	(	const mrpt::obs::CObservation *	o1,
		const mrpt::obs::CObservation *	o2,
		const mrpt::poses::CPose3D *	pose_o2_wrt_o1 = `nullptr`
	)

Estimates the "overlap" or "matching ratio" of two observations (range [0,1]), possibly taking into account their relative positions.

Note: This is used in mrpt::slam::CIncrementalMapPartitioner

Definition at line 26 of file observations_overlap.cpp.

References mrpt::obs::CObservation2DRangeScan::buildAuxPointsMap(), mrpt::maps::TMatchingExtraResults::correspondencesRatio, IS_CLASS, mrpt::maps::TMatchingParams::maxAngularDistForCorrespondence, and mrpt::maps::TMatchingParams::maxDistForCorrespondence.

Referenced by eval_similarity_observation_overlap(), and mrpt::slam::observationsOverlap().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ observationsOverlap() [2/4]

double mrpt::slam::observationsOverlap	(	const mrpt::obs::CObservation::Ptr &	o1,
		const mrpt::obs::CObservation::Ptr &	o2,
		const mrpt::poses::CPose3D *	pose_o2_wrt_o1 = `nullptr`
	)

inline

Estimates the "overlap" or "matching ratio" of two observations (range [0,1]), possibly taking into account their relative positions.

Note: This is used in mrpt::slam::CIncrementalMapPartitioner

Definition at line 34 of file observations_overlap.h.

References mrpt::slam::observationsOverlap().

Here is the call graph for this function:

◆ observationsOverlap() [3/4]

double mrpt::slam::observationsOverlap	(	const mrpt::obs::CSensoryFrame &	sf1,
		const mrpt::obs::CSensoryFrame &	sf2,
		const mrpt::poses::CPose3D *	pose_sf2_wrt_sf1 = `nullptr`
	)

Estimates the "overlap" or "matching ratio" of two set of observations (range [0,1]), possibly taking into account their relative positions.

This method computes the average between each of the observations in each SF.

Note: This is used in mrpt::slam::CIncrementalMapPartitioner

◆ observationsOverlap() [4/4]

double mrpt::slam::observationsOverlap	(	const mrpt::obs::CSensoryFrame::Ptr &	sf1,
		const mrpt::obs::CSensoryFrame::Ptr &	sf2,
		const mrpt::poses::CPose3D *	pose_sf2_wrt_sf1 = `nullptr`
	)

inline

Estimates the "overlap" or "matching ratio" of two set of observations (range [0,1]), possibly taking into account their relative positions.

This method computes the average between each of the observations in each SF.

Note: This is used in mrpt::slam::CIncrementalMapPartitioner

Definition at line 58 of file observations_overlap.h.

References mrpt::slam::observationsOverlap().

Here is the call graph for this function:

◆ PF_SLAM_implementation_gatherActionsCheckBothActObs()

template<class PARTICLE_TYPE , class MYSELF , mrpt::bayes::particle_storage_mode STORAGE>

template<class BINTYPE >

bool mrpt::slam::PF_implementation< PARTICLE_TYPE, MYSELF, STORAGE >::PF_SLAM_implementation_gatherActionsCheckBothActObs	(	const mrpt::obs::CActionCollection *	actions,
		const mrpt::obs::CSensoryFrame *	sf
	)

Auxiliary method called by PF implementations: return true if we have both action & observation, otherwise, return false AND accumulate the odometry so when we have an observation we didn't lose a thing.

On return=true, the "m_movementDrawer" member is loaded and ready to draw samples of the increment of pose since last step. This method is smart enough to accumulate CActionRobotMovement2D or CActionRobotMovement3D, whatever comes in.

Definition at line 46 of file PF_implementations.h.

Detailed Description

Library `mrpt-slam`

Classes

Namespaces

Modules

Typedefs

Enumerations

Functions

Observations overlap functions

Typedef Documentation

◆ similarity_func_t

Enumeration Type Documentation

◆ similarity_method_t

◆ TICPCovarianceMethod

Function Documentation

◆ observationsOverlap() [1/4]

◆ observationsOverlap() [2/4]

◆ observationsOverlap() [3/4]

◆ observationsOverlap() [4/4]

◆ PF_SLAM_implementation_gatherActionsCheckBothActObs()