12345qiupeng
/
gtsam
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
gtsam/cpp/BetweenFactor.h

78 lines
1.9 KiB
C
Raw Normal View History

BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
/**
* @file BetweenFactor.h
* @authors Frank Dellaert, Viorela Ila
**/
#pragma once
#include <ostream>
#include "NonlinearFactor.h"
#include "GaussianFactor.h"
#include "Lie.h"
#include "Matrix.h"
namespace gtsam {
/**
* A class for a measurement predicted by "between(config[key1],config[key2])"
* T is the Lie group type, Config where the T's are gotten from
*/
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
template<class Config, class Key, class T>
class BetweenFactor: public NonlinearFactor2<Config, Key, T, Key, T> {
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
private:
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
typedef NonlinearFactor2<Config, Key, T, Key, T> Base;
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
T measured_; /** The measurement */
public:
// shorthand for a smart pointer to a factor
typedef typename boost::shared_ptr<BetweenFactor> shared_ptr;
/** Constructor */
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
BetweenFactor(const Key& key1, const Key& key2, const T& measured,
case change: SharedGaussian and SharedDiagonal are now classes with their own header file. Needed for MATLAB TORO hail Mary
2010-01-23 01:36:57 +08:00
const SharedGaussian& model) :
NOISE MODEL. This is a big edit but with no templates involed, so it should not be a big deal. New namespace gtsam::noiseModel collects all noise models, which provide efficient whitening and chain-rule implementation needed for optimization. The class hierarchy gives us the ability to use models from full covariances to i.i.d. unit variance noise with a single interface, where the latter will be much cheaper. From now on, all non-linear factors take a shared_ptr to a Gaussian noise model. This is done through the parameter (const sharedGaussian& model). The use of a shared pointer allows us to share one noise models for thousands of factors, if applicable. Just like Richard's Symbol change, there is a compile flag GTSAM_MAGIC_GAUSSIAN which allows you to use doubles, vectors, or matrices to created noise models on the fly. You have to set it to the correct dimension. Use of this is *not* encouraged and the flag will disappear after some good soul fixed all unit tests.
2010-01-18 13:38:53 +08:00
Base(model, key1, key2), measured_(measured) {
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
}
/** implement functions needed for Testable */
/** print */
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
void print(const std::string& s) const {
Base::print(s);
Pose2Prior is now a typedef, improved some derivatives
2010-01-17 00:46:57 +08:00
measured_.print("measured");
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
}
/** equals */
bool equals(const NonlinearFactor<Config>& expected, double tol) const {
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
const BetweenFactor<Config, Key, T> *e =
dynamic_cast<const BetweenFactor<Config, Key, T>*> (&expected);
Pose2Prior is now a typedef, improved some derivatives
2010-01-17 00:46:57 +08:00
return e != NULL && Base::equals(expected) && this->measured_.equals(
e->measured_, tol);
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
}
/** implement functions needed to derive from Factor */
/** vector of errors */
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
Vector evaluateError(const T& p1, const T& p2, boost::optional<Matrix&> H1 =
boost::none, boost::optional<Matrix&> H2 = boost::none) const {
Pose2Prior is now a typedef, improved some derivatives
2010-01-17 00:46:57 +08:00
T hx = between(p1, p2, H1, H2); // h(x)
Large gtsam refactoring To support faster development *and* better performance Richard and I pushed through a large refactoring of NonlinearFactors. The following are the biggest changes: 1) NonLinearFactor1 and NonLinearFactor2 are now templated on Config, Key type, and X type, where X is the argument to the measurement function. 2) The measurement itself is no longer kept in the nonlinear factor. Instead, a derived class (see testVSLAMFactor, testNonlinearEquality, testPose3Factor etc...) has to implement a function to compute the errors, "evaluateErrors". Instead of (h(x)-z), it needs to return (z-h(x)), so Ax-b is an approximation of the error. IMPORTANT: evaluateErrors needs - if asked - *combine* the calculation of the function value h(x) and the derivatives dh(x)/dx. This was a major performance issue. To do this, boost::optional<Matrix&> arguments are provided, and tin EvaluateErrors you just says something like if (H) *H = Matrix_(3,6,....); 3) We are no longer using int or strings for nonlinear factors. Instead, the preferred key type is now Symbol, defined in Key.h. This is both fast and cool: you can construct it from an int, and cast it to a strong. It also does type checking: a Symbol<Pose3,'x'> will not match a Symbol<Pose2,'x'> 4) minor: take a look at LieConfig.h: it help you avoid writing a lot of code bu automatically creating configs for a certain type. See e.g. Pose3Config.h. A "double" LieConfig is on the way - Thanks Richard and Manohar !
2010-01-14 06:25:03 +08:00
// manifold equivalent of h(x)-z -> log(z,h(x))
NOISE MODEL. This is a big edit but with no templates involed, so it should not be a big deal. New namespace gtsam::noiseModel collects all noise models, which provide efficient whitening and chain-rule implementation needed for optimization. The class hierarchy gives us the ability to use models from full covariances to i.i.d. unit variance noise with a single interface, where the latter will be much cheaper. From now on, all non-linear factors take a shared_ptr to a Gaussian noise model. This is done through the parameter (const sharedGaussian& model). The use of a shared pointer allows us to share one noise models for thousands of factors, if applicable. Just like Richard's Symbol change, there is a compile flag GTSAM_MAGIC_GAUSSIAN which allows you to use doubles, vectors, or matrices to created noise models on the fly. You have to set it to the correct dimension. Use of this is *not* encouraged and the flag will disappear after some good soul fixed all unit tests.
2010-01-18 13:38:53 +08:00
return logmap(measured_, hx);
Fixed double map lookup
2010-01-13 00:11:24 +08:00
}
1) add a compose function that compose all the poses in a factor graph given the spanning tree 2) add a new graph-inl.h which takes care of all the boost graph related functions to prevent the copy and paste across several classes
2010-01-13 00:12:25 +08:00
/** return the measured */
Pose2Prior is now a typedef, improved some derivatives
2010-01-17 00:46:57 +08:00
inline const T measured() const {
return measured_;
}
1) add a compose function that compose all the poses in a factor graph given the spanning tree 2) add a new graph-inl.h which takes care of all the boost graph related functions to prevent the copy and paste across several classes
2010-01-13 00:12:25 +08:00
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
/** number of variables attached to this factor */
Pose2Prior is now a typedef, improved some derivatives
2010-01-17 00:46:57 +08:00
inline std::size_t size() const {
return 2;
}
BetweenFactor is a template that models the measurement between two Lie types e.g. Pose2 or Pose3. Pose2Factor and Pose3Factor are now simply typedefs.
2010-01-08 23:32:45 +08:00
};
} /// namespace gtsam