InvertMotorController Class Reference

Abstract class (interface) for robot controller that use direct matrix inversion and a time loop in motor domain. More...

#include <invertmotorcontroller.h>

Inherits AbstractController.

Inherited by InvertMotorNStep, and InvertMotorSpace.

Inheritance diagram for InvertMotorController:

[legend]Collaboration diagram for InvertMotorController:

[legend]List of all members.

Public Member Functions
	InvertMotorController (unsigned short buffersize, const std::string &name, const std::string &revision)
virtual paramval	getParam (const paramkey &key) const
virtual bool	setParam (const paramkey &key, paramval val)
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)
virtual matrix::Matrix	calculateDelayedValues (const matrix::Matrix *buffer, int number_steps_of_delay_)
	calculate delayed values
virtual matrix::Matrix	calculateSmoothValues (const matrix::Matrix *buffer, int number_steps_for_averaging_)
	calculate time-smoothed values
virtual double	calcErrorFactor (const matrix::Matrix &e, bool loga, bool root)
	calculates the error_factor for either logarithmic (E=ln(e^T*e)) or square (E=sqrt(e^t*e)) error
Static Protected Member Functions
static double	g (double z)
	neuron transfer function
static double	g_s (double z)
	first dervative
static double	g_s_inv (double z)
	inverse of the first derivative
static double	g_s (double z, double xsi)
	an exact formula for inversion if neuron.
static double	g_2s_div_s (double z, double xsi)
	an exact formula for g''/g'
static double	squash (double z)
	squashing function (-0.1 to 0.1), to protect against to large weight updates
static double	squash (void *d, double z)
	squashing function with adjustable clipping size, to protect against too large weight updates
Protected Attributes
paramval	epsC
paramval	desens
paramval	s4delay
paramval	s4avg
paramval	steps
paramval	epsA
paramval	factorB
paramval	zetaupdate
paramval	dampA
short	logaE
short	rootE
short	relativeE
paramval	squashSize
paramval	adaptRate
paramval	nomUpdate
paramval	noiseB
paramval	noiseY
paramval	teacher
int	t
unsigned short	buffersize
std::string	name
bool	initialised

---

Detailed Description

Abstract class (interface) for robot controller that use direct matrix inversion and a time loop in motor domain.

Implements standart configureable interface for some useful parameters like epsC, epsA, s4avg ...

---

Constructor & Destructor Documentation

InvertMotorController	(	unsigned short	buffersize,
		const std::string &	name,
		const std::string &	revision
	)			[inline]

---

Member Function Documentation

virtual double calcErrorFactor	(	const matrix::Matrix &	e,
		bool	loga,
		bool	root
	)			[inline, protected, virtual]

calculates the error_factor for either logarithmic (E=ln(e^T*e)) or square (E=sqrt(e^t*e)) error

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

calculate delayed values

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

calculate time-smoothed values

static double g

(

double

z

)

[inline, static, protected]

neuron transfer function

static double g_2s_div_s	(	double	z,
		double	xsi
	)			[inline, static, protected]

an exact formula for g''/g'

static double g_s	(	double	z,
		double	xsi
	)			[inline, static, protected]

an exact formula for inversion if neuron.

static double g_s

(

double

z

)

[inline, static, protected]

first dervative

static double g_s_inv

(

double

z

)

[inline, static, protected]

inverse of the first derivative

virtual paramval getParam

(

const paramkey &

key

)

const [inline, virtual]

virtual paramlist getParamList

(

)

const [inline, virtual]

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

Returns:

list of key-value pairs

Reimplemented from Configurable.

void putInBuffer	(	matrix::Matrix *	buffer,
		const matrix::Matrix &	vec,
		int	delay = 0
	)			[inline, protected]

virtual bool setParam	(	const paramkey &	key,
		paramval	val
	)			[inline, virtual]

static double squash	(	void *	d,
		double	z
	)			[inline, static, protected]

squashing function with adjustable clipping size, to protect against too large weight updates

static double squash

(

double

z

)

[inline, static, protected]

squashing function (-0.1 to 0.1), to protect against to large weight updates

---

Member Data Documentation

paramval adaptRate [protected]

unsigned short buffersize [protected]

paramval dampA [protected]

paramval desens [protected]

paramval epsA [protected]

paramval epsC [protected]

paramval factorB [protected]

bool initialised [protected]

short logaE [protected]

std::string name [protected]

Reimplemented from Configurable.

paramval noiseB [protected]

paramval noiseY [protected]

paramval nomUpdate [protected]

short relativeE [protected]

short rootE [protected]

paramval s4avg [protected]

paramval s4delay [protected]

paramval squashSize [protected]

paramval steps [protected]

int t [protected]

paramval teacher [protected]

paramval zetaupdate [protected]

---

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

• invertmotorcontroller.h

---