FFNNController Class Reference

class for robot controller that uses the georg's matrixlib for direct matrix inversion for n channels (simple one layer networks) More...

#include <ffnncontroller.h>

Inherits AbstractController.

Inheritance diagram for FFNNController:

[legend]Collaboration diagram for FFNNController:

[legend]List of all members.


Public Member Functions
	FFNNController (const std::string &networkfilename, int history, bool input_only_x=false)
	networkfilename is the file to load the network from, and history is the number of time steps the network gets input from (in sensce of dimension of input)
virtual void	init (int sensornumber, int motornumber)
	initialisation of the controller with the given sensor/ motornumber Must be called before use.
virtual	~FFNNController ()
virtual int	getSensorNumber () const
	returns the number of sensors the controller was initialised with or 0 if not initialised
virtual int	getMotorNumber () const
	returns the mumber of motors the controller was initialised with or 0 if not initialised
virtual void	step (const sensor , int number_sensors, motor , int number_motors)
	performs one step (includes learning).
virtual void	stepNoLearning (const sensor , int number_sensors, motor , int number_motors)
	performs one step without learning.
virtual bool	store (FILE *f) const
	stores the controller values to a given file (binary).
virtual bool	restore (FILE *f)
	loads the controller values from a given file (binary).
virtual std::list< iparamkey >	getInternalParamNames () const
	The list of the names of all internal parameters given by getInternalParams().
virtual std::list< iparamval >	getInternalParams () const
virtual paramval	getParam (const paramkey &key) const
	returns the value of the requested parameter or 0 (+ error message to stderr) if unknown.
virtual bool	setParam (const paramkey &key, paramval val)
	sets the value of the given parameter or does nothing if unknown.
virtual paramlist	getParamList () const
	The list of all parameters with there value as allocated lists.
Protected Member Functions
void	putInBuffer (matrix::Matrix *buffer, const matrix::Matrix &vec, int delay=0)
matrix::Matrix	calculateSmoothValues (const matrix::Matrix *buffer, int number_steps_for_averaging_) const
	calculate time-smoothed values
matrix::Matrix	assembleNetworkInputXY (matrix::Matrix xbuffer, matrix::Matrix ybuffer) const
matrix::Matrix	assembleNetworkInputX (matrix::Matrix xbuffer, matrix::Matrix ybuffer) const
Protected Attributes
unsigned short	number_motors
unsigned short	number_sensors
unsigned short	history
unsigned short	buffersize
bool	input_only_x
unsigned short	s4avg
unsigned int	t
matrix::Matrix *	x_buffer
matrix::Matrix *	y_buffer
matrix::Matrix	x_smooth
MultiLayerFFNN *	net
bool	initialised

Detailed Description

class for robot controller that uses the georg's matrixlib for direct matrix inversion for n channels (simple one layer networks)

Implements standart parameters: eps, rho, mu, stepnumber4avg, stepnumber4delay

Constructor & Destructor Documentation

FFNNController ( const std::string & networkfilename,

int history,

bool input_only_x = false

)

networkfilename is the file to load the network from, and history is the number of time steps the network gets input from (in sensce of dimension of input)

Parameters:

input_only_x if true then the input vector is
$(x_{t},x_{t-1},...,x_{t-history})^T$
if false then also the y values are used:
$(x_{t}, y_{t-1}, x_{t-1},y_{t-2},...,x_{t-history})^T$

~FFNNController ( ) [virtual]

Member Function Documentation

matrix::Matrix assembleNetworkInputX ( matrix::Matrix * xbuffer,

matrix::Matrix * ybuffer

) const [protected]

matrix::Matrix assembleNetworkInputXY ( matrix::Matrix * xbuffer,

matrix::Matrix * ybuffer

) const [protected]

matrix::Matrix calculateSmoothValues ( const matrix::Matrix * buffer,

int number_steps_for_averaging_

) const [protected]

calculate time-smoothed values

virtual std::list<iparamkey> getInternalParamNames ( ) const [inline, virtual]

The list of the names of all internal parameters given by getInternalParams().
The naming convention is "v[i]" for vectors and "A[i][j]" for matrices, where i, j start at 0.
Returns:
: list of keys

Implements Inspectable.

virtual std::list<iparamval> getInternalParams ( ) const [inline, virtual]

Returns:
: list of values

Implements Inspectable.

virtual int getMotorNumber ( ) const [inline, virtual]

returns the mumber of motors the controller was initialised with or 0 if not initialised

Reimplemented from AbstractController.

Configurable::paramval getParam ( const paramkey & key ) const [virtual]

returns the value of the requested parameter or 0 (+ error message to stderr) if unknown.

Reimplemented from Configurable.

Configurable::paramlist getParamList ( ) const [virtual]

The list of all parameters with there value as allocated lists.

Returns:
list of key-value pairs

Reimplemented from Configurable.

virtual int getSensorNumber ( ) const [inline, virtual]

returns the number of sensors the controller was initialised with or 0 if not initialised

Reimplemented from AbstractController.

void init ( int sensornumber,

int motornumber

) [virtual]

initialisation of the controller with the given sensor/ motornumber Must be called before use.

Reimplemented from AbstractController.

void putInBuffer ( matrix::Matrix * buffer,

const matrix::Matrix & vec,

int delay = 0

) [protected]

bool restore ( FILE * f ) [virtual]

loads the controller values from a given file (binary).

Implements Storeable.

bool setParam ( const paramkey & key,

paramval val

) [virtual]

sets the value of the given parameter or does nothing if unknown.

Reimplemented from Configurable.

void step ( const sensor * ,

int number_sensors,

motor * ,

int number_motors

) [virtual]

performs one step (includes learning).
Calculates motor commands from sensor inputs.
Parameters:

sensors sensors inputs scaled to [-1,1]

sensornumber length of the sensor array

motors motors outputs. MUST have enough space for motor values!

motornumber length of the provided motor array

Reimplemented from AbstractController.

void stepNoLearning ( const sensor * ,

int number_sensors,

motor * ,

int number_motors

) [virtual]

performs one step without learning.

See also:
step

Reimplemented from AbstractController.