InvertNChannelController 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 <invertnchannelcontroller.h>

Inherits InvertController.

Inheritance diagram for InvertNChannelController:

[legend]Collaboration diagram for InvertNChannelController:

[legend]List of all members.

Public Member Functions
	InvertNChannelController (int _buffersize, bool _update_only_1=false)
virtual void	init (int sensornumber, int motornumber, RandGen *randGen=0)
	initialisation of the controller with the given sensor/ motornumber Must be called before use.
virtual	~InvertNChannelController ()
virtual paramkey	getName () const
	returns the name of the object (with version number)
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. Calulates motor commands from sensor inputs.
virtual bool	store (FILE *f) const
	stores the controller values to a given file.
virtual bool	restore (FILE *f)
	loads the controller values from a given file.
virtual std::list< ILayer >	getStructuralLayers () const
	Specifies which parameter vector forms a structural layer (in terms of a neural network) The ordering is important.
virtual std::list< IConnection >	getStructuralConnections () const
	Specifies which parameter matrix forms a connection between layers (in terms of a neural network) The orderning is not important.
Protected Member Functions
virtual double	calculateE (const matrix::Matrix &x_delay, const matrix::Matrix &y_delay)
virtual void	learn (const matrix::Matrix &x_delay, const matrix::Matrix &y_delay)
	learn values h,C
virtual void	learnmodel (const matrix::Matrix &y_delay)
virtual matrix::Matrix	calculateDelayedValues (const matrix::Matrix *buffer, unsigned int number_steps_of_delay_)
	calculate delayed values
virtual matrix::Matrix	calculateSmoothValues (const matrix::Matrix *buffer, unsigned int number_steps_for_averaging_)
matrix::Matrix	calculateControllerValues (const matrix::Matrix &x_smooth)
	calculate controller outputs
void	putInBuffer (matrix::Matrix *buffer, const matrix::Matrix &vec)
Static Protected Member Functions
static double	g (double z)
	neuron transfer function
static double	g_s (double z)
static double	squash (double z)
	squashing function, to protect against to large weight updates
Protected Attributes
unsigned short	number_channels
unsigned short	buffersize
bool	update_only_1
matrix::Matrix	A
matrix::Matrix	C
matrix::Matrix	h
matrix::Matrix	L
matrix::Matrix *	x_buffer
matrix::Matrix *	y_buffer
int	t
paramkey	name

---

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

InvertNChannelController	(	int	_buffersize,
		bool	_update_only_1 = false
	)

~InvertNChannelController

(

)

[virtual]

---

Member Function Documentation

Matrix calculateControllerValues

(

const matrix::Matrix &

x_smooth

)

[protected]

calculate controller outputs

Parameters:

x_smooth

Matrix(number_channels,1)

Matrix calculateDelayedValues	(	const matrix::Matrix *	buffer,
		unsigned int	number_steps_of_delay_
	)			[protected, virtual]

calculate delayed values

double calculateE	(	const matrix::Matrix &	x_delay,
		const matrix::Matrix &	y_delay
	)			[protected, virtual]

Matrix calculateSmoothValues	(	const matrix::Matrix *	buffer,
		unsigned int	number_steps_for_averaging_
	)			[protected, virtual]

static double g

(

double

z

)

[inline, static, protected]

neuron transfer function

static double g_s

(

double

z

)

[inline, static, protected]

virtual int getMotorNumber

(

)

const [inline, virtual]

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

Implements AbstractController.

virtual paramkey getName

(

)

const [inline, virtual]

returns the name of the object (with version number)

Reimplemented from Configurable.

virtual int getSensorNumber

(

)

const [inline, virtual]

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

Implements AbstractController.

list< Inspectable::IConnection > getStructuralConnections

(

)

const [virtual]

Specifies which parameter matrix forms a connection between layers (in terms of a neural network) The orderning is not important.

Returns:

: list of layer names with dimension

Reimplemented from Inspectable.

list< Inspectable::ILayer > getStructuralLayers

(

)

const [virtual]

Specifies which parameter vector forms a structural layer (in terms of a neural network) The ordering is important.

The first entry is the input layer and so on.

Returns:

: list of layer names with dimension

Reimplemented from Inspectable.

void init	(	int	sensornumber,
		int	motornumber,
		RandGen *	randGen = 0
	)			[virtual]

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

The random generator is optional.

Implements AbstractController.

void learn	(	const matrix::Matrix &	x_delay,
		const matrix::Matrix &	y_delay
	)			[protected, virtual]

learn values h,C

void learnmodel

(

const matrix::Matrix &

y_delay

)

[protected, virtual]

void putInBuffer	(	matrix::Matrix *	buffer,
		const matrix::Matrix &	vec
	)			[protected]

bool restore

(

FILE *

f

)

[virtual]

loads the controller values from a given file.

Implements Storeable.

static double squash

(

double

z

)

[inline, static, protected]

squashing function, to protect against to large weight updates

void step	(	const sensor *	,
		int	number_sensors,
		motor *	,
		int	number_motors
	)			[virtual]

performs one step (includes learning).

Calulates motor commands from sensor inputs.

Implements AbstractController.

void stepNoLearning	(	const sensor *	,
		int	number_sensors,
		motor *	,
		int	number_motors
	)			[virtual]

performs one step without learning. Calulates motor commands from sensor inputs.

Implements AbstractController.

bool store

(

FILE *

f

)

const [virtual]

stores the controller values to a given file.

Implements Storeable.

---

Member Data Documentation

matrix::Matrix A [protected]

unsigned short buffersize [protected]

matrix::Matrix C [protected]

matrix::Matrix h [protected]

matrix::Matrix L [protected]

paramkey name [protected]

Reimplemented from Configurable.

unsigned short number_channels [protected]

int t [protected]

bool update_only_1 [protected]

matrix::Matrix* x_buffer [protected]

matrix::Matrix* y_buffer [protected]

---

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

• invertnchannelcontroller.h
• invertnchannelcontroller.cpp

---