batching_pomp  1.0
This is an implementation of an algorithmic framework for anytime motion planning on large dense roadmaps.
Public Member Functions | List of all members
batching_pomp::cspacebelief::KNNModel Class Reference

Derived class of Model that uses kNN to represent the C-space belief. More...

#include <KNNModel.hpp>

Inherits batching_pomp::cspacebelief::Model< BeliefPoint >.

Public Member Functions

 KNNModel (size_t _KNN, double _prior, double _priorWeight, const std::function< double(const BeliefPoint &, const BeliefPoint &)> &_distanceFunction)
 
void setPrior (double _prior)
 
void setPriorWeight (double _priorWeight)
 
void setKNN (size_t _knn)
 
void addPoint (const BeliefPoint &data) override
 
void removePoint (const BeliefPoint &data) override
 
double estimate (const BeliefPoint &query) const override
 

Detailed Description

Derived class of Model that uses kNN to represent the C-space belief.

Implements a C-Space Belief Model using k-Nearest Neighbour lookup and weighted averaging over the results of neighbouring belief points. The weights are inversely proportional to the distance between the queried point and the neighbouring belief points.

Constructor & Destructor Documentation

◆ KNNModel()

batching_pomp::cspacebelief::KNNModel::KNNModel ( size_t  _KNN,
double  _prior,
double  _priorWeight,
const std::function< double(const BeliefPoint &, const BeliefPoint &)> &  _distanceFunction 
)
inline
Parameters
[in]_KNNThe value of k for KNN lookup
[in]_distanceFunctionThe ompl::NearestNeighbours::Distance Function to set

Member Function Documentation

◆ addPoint()

void batching_pomp::cspacebelief::KNNModel::addPoint ( const BeliefPoint data)
inlineoverridevirtual

Add a data point to the belief manager.

Parameters
[in]dataThe datapoint to add to the belief manager.

Implements batching_pomp::cspacebelief::Model< BeliefPoint >.

◆ estimate()

double batching_pomp::cspacebelief::KNNModel::estimate ( const BeliefPoint query) const
inlineoverridevirtual

Estimate the configuration space belief of the query

Parameters
[in]queryThe datapoint for which the probability of collision is estimated.
Returns
The probability of collision of query in (0,1)

Implements batching_pomp::cspacebelief::Model< BeliefPoint >.

◆ removePoint()

void batching_pomp::cspacebelief::KNNModel::removePoint ( const BeliefPoint data)
inlineoverridevirtual

Remove a data point from the belief manager (rarely used)

Parameters
[in]dataThe datapoint to remove from the belief manager.

Implements batching_pomp::cspacebelief::Model< BeliefPoint >.


The documentation for this class was generated from the following file: