FFNNController Class Reference

class for robot controller with a fixed neural network More...

#include <ffnncontroller.h>

Collaboration diagram for FFNNController:

Public Member Functions
	FFNNController (const std::string &networkfilename, int history, bool input_only_x, unsigned int init_wait=0)
	FFNNController (MultiLayerFFNN *net, int history, bool input_only_x, unsigned int init_wait=0)
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	~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.
void	notifyOnChange (const paramkey &key)
	Is called when a parameter was changes via setParam().
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
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
virtual matrix::Matrix	assembleNetworkInputXY (matrix::Matrix xbuffer, matrix::Matrix ybuffer) const
virtual matrix::Matrix	assembleNetworkInputX (matrix::Matrix xbuffer, matrix::Matrix ybuffer) const
virtual matrix::Matrix	assembleNetworkOutput (const matrix::Matrix &output) const
Protected Attributes
unsigned short	number_motors
unsigned short	number_sensors
unsigned short	history
unsigned short	buffersize
bool	input_only_x
int	s4avg
unsigned int	t
unsigned int	init_wait
matrix::Matrix *	x_buffer
matrix::Matrix *	y_buffer
matrix::Matrix	x_smooth
MultiLayerFFNN *	net
bool	initialised

Detailed Description

class for robot controller with a fixed neural network

Constructor & Destructor Documentation

FFNNController	(	const std::string &	networkfilename,
		int	history,
		bool	input_only_x,
		unsigned int	init_wait = `0`
	)

Parameters:

	networkfilename	file to load the network
	history	number of time steps the network gets input (in sense of dimension of input)
	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: $(x_{t}, y_{t-1}, x_{t-1},y_{t-2},...,x_{t-history})^T$
	init_wait	number of timesteps to wait before controlling

FFNNController	(	MultiLayerFFNN *	net,
		int	history,
		bool	input_only_x,
		unsigned int	init_wait = `0`
	)

Parameters:

	net	pointer to network (it must have the right dimensions)
	history	number of time steps the network gets input (in sense of dimension of input)
	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: $(x_{t}, y_{t-1}, x_{t-1},y_{t-2},...,x_{t-history})^T$
	init_wait	number of timesteps to wait before controlling

~FFNNController ( ) [virtual]

Member Function Documentation

matrix::Matrix assembleNetworkInputX	(	matrix::Matrix *	xbuffer,
		matrix::Matrix *	ybuffer
	)			const `[protected, virtual]`

matrix::Matrix assembleNetworkInputXY	(	matrix::Matrix *	xbuffer,
		matrix::Matrix *	ybuffer
	)			const `[protected, virtual]`

matrix::Matrix assembleNetworkOutput ( const matrix::Matrix & output ) const [protected, virtual]

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

Reimplemented from Inspectable.

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

Returns:: : list of values

Reimplemented from Inspectable.

virtual int getMotorNumber ( ) const [inline, virtual]

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

Implements AbstractController.

virtual int getSensorNumber ( ) const [inline, virtual]

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

Implements AbstractController.

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 notifyOnChange ( const paramkey & key ) [virtual]

Is called when a parameter was changes via setParam().

Note that it is not called of parameters of childs are changed, then there notifyOnChange() method is called. The key and of the changed parameter (use getParam() to retrieve its actual value). Overload this function when special actions have to be taken on parameter changes.

Reimplemented from Configurable.

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.

void step	(	const sensor *	sensors,
		int	sensornumber,
		motor *	motors,
		int	motornumber
	)			`[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