Study On Artificial Intelligence And Virtual Reality Computer Science Essay

Virtual world earlier was merely a plaything for kids but now simulations are used in about every field. For military preparation, Medicine, Engineering, Architecture design. Simulations are being used to fix for exigencies ( e.g. bomb blast, inundations, terrorist onslaughts etc ) . And besides to analyse natural philosophies of simple motorcycle engine to complex projectile engine. For illustration now before a aircraft is built it should turn out its art in fake environments.

Virtual world which is a immature research country in computing machine scientific discipline. Early yearss we saw merely little simulations with limited capablenesss and limited pragmatism. In early yearss such limited pragmatism was indispensable because of restrictions of computational power. But now a twenty-four hours ‘s computing machines are much more power full and progress. So scientists are believing of investing more pragmatism for their simulations. But there are still some restrictions in computational power. So it is possible to convey some considerable pragmatism to the simulation under bing hardware powers and restrictions

Over the old ages unreal intelligence has been a absorbing thought for world in their pursuit for a human like machine. Virtual world which is endeavoring for better pragmatism is easy but certainly been inspired by Artificial Intelligence. AI is dominated by constructs such as Artificial Neural Networks, Genetic Algorithms, Fuzzy Logic, Ant Colony Optimization.

Many of these AI constructs requires batch of treating so if it is used in a practical world simulation it will finally decelerate down simulation velocity which will non delight the users. But out of the Fuzzy Logic requires relatively a really light weight procedure. Because of that usage of fuzzed logic is turning quickly in practical world research.

This papers chiefly consists of cognition I gained by reading the research documents I found approximately may topic and some inside informations about documents that describe the usage of fuzzed logic in practical world simulations and some inside informations about documents which describe about usage of fuzzed logic in control systems.

Chapter 01.


Virtual World

This is a conjectural 3D universe generated by the computing machine. Here user can interact with the 3D universe and if the pragmatism is really powerful user will experience that he is interacting with the existent universe. These fake environments are chiefly based on practical experience which is usually displayed on computing machine screens or other stereoscopic shows. But sometimes it supports some other centripetal information such as sounds and on occasion sense of touch as good.

Interaction with practical environments is done by many ways and agencies. It is normally done by keyboard, mouse, joy stick and in progress simulations devices such as wired baseball mitt and omnidirectional treadmills. Theoretically see user addition from interacting these environments should be precisely similar to the presently the experience user addition by interacting with these practical objects is really far from world. This inability is occurred due to restrictions of treating power of current computing machine systems.Virtual world application countries

* Entertainment

* Aircraft design- ( Virtual world simulation is used by McDonnell-Douglas Corporation for F-18 aircraft design besides lockheed Martins use VR for F-22 progress combatant plan. In add-on Russian Sukhoi design agency is utilizing VR for their SU-37 and advanced SU-PAK-DA combatant plans. )

* Medical simulations- Mainly in surgery simulations

* Medical treatments- Mainly in phobic disorder interventions

* Engineering and architecture

* Archeology- For Reconstruction of artefacts

* Film industry

* For instruction intent

Chapter 02.

2. Fuzzy Logic

2.1 History of fuzzy logic

The theory of Fuzzy Logic was foremost presented by professor Lofti Zadeh. In add-on the term “ Fuzzy ” number one was used by the Dr. Lotfi Zadeh.Dans in the journel of technology “ proceedings of IRE “ .Mainly fuzzed logic is to a great extent used in control systems. This new one attack considers about non holding sets with stiff boundary lines as the conventional sets. But fuzzed logic was non used a batch practically merely because of the deficiency of computing machine strength until the last old ages 70. Normally the people do non see the universe in the precise mode. But practically they are highly adaptative. Therefore if the systems can be programed in an imprecise mode the end point system will be highly adaptative and effectual.

2.2 How does fuzzy logic work

Normally in a conventional system we attempt to pattern a system mathematically. But it is non the instance with fuzzed logic. Normally FL uses a regulation based if and else method to decide jobs. For illustration Lashkar-e-Taibas consider the temperature. In the conventional mode we say that if the temperature is bigger than some value we consider it as a hot reading. Suppose if the temperature is higher than 50 Celsius one it is hot or it is hot. If of this mode a temperature is 50.1 grades it is hot but if the temperature is 49.9 it is cold. Truly that is a really bad construct and this non to be flexible. In the fuzzed attack of logic usage us footings as if ( this is excessively fresh ) AND ( the procedure obtains colder ) THEN ( heats the procedure ) and it brings us more better consequence

Normally in a conventional system we attempt to pattern a system mathematically. In contrast fuzzed logic works different than conventional job work outing methods. Normally FL uses a regulation based if and else method to work out jobs. For illustration Lashkar-e-Taibas assume temperature. In conventional manner we say if the temperature is greater than some value we say that the country is hot. Lashkar-e-taibas assume if the temperature is higher than 50 Celsius it is hot or it is hot. So in this manner a temperature is 50.1 grades it is hot but if the temperature is 49.9 it is cold. Truly that is a really bad design and it is non flexible. In fuzzed logic attack we use footings like if ( it is excessively cool ) AND ( procedure is acquiring colder ) THEN ( heat the procedure ) and it brings us better consequences

2.3 Fuzzy Linguistic variables

In fuzzed logic these variables are called nouns other than these variables are treated as words instead than Numberss. Normally input class is a noun eg: – “ temperature ” , ” monetary value ” , “ height ” etc. Mistake is the difference between given end product and expected end product. Mistake is besides stated in the same manner. In fuzzed logic we use footings like “ big positive mistake ” , “ nothing mistake ” .

2.4 Fuzzy regulation matrix

Fuzzy lingual variables can be efficaciously used in control systems. Earlier we saw that fuzzed parametric quantities of the mistake can be modified with adjectives such as “ negative ” , “ nothing ” and positive etc. First we need to map the existence of all possible inputs to the system. In this illustration simplest solution is to utilize a 3*3 matrix. Columns of this matrix is names as “ negative mistake ” “ zero mistake ” and “ positive mistake ” . Rows represent the negative positive and mistake rate inputs. This matrix is called regulation matrix. Here we have nine possible logical AND merchandises end product of the matrix.

1.5 Fuzzy rank maps

After we created the regulation matrix we need to use these regulations to the system. This is where the construct of fuzzed member ship map comes in to play. In rank map is graphical representation of magnitude of each input. It is used to find the end product. In add-on it shows functional convergence between inputs ad good. Graphic representation of a rank map has some form. Some are triangular. It is the most common form. In add-on bell. harversine and exponential forms besides can be seen.

Infernecing with fuzzed regulation base

In the regulation base we can see batch of regulations. We need to deduce the logical merchandise of each of these values. So several illation methods are used.

1. Max-min regulation

This method tests the magnitude of each regulation and selects the highest value

2. Max-dot regulation

In every rank map take the horizontal extremum value in threspectiveposition and acquire the complex of horizontal peak country under each map.

Chapter 03.

3. Use of Fuzzy logic in VR environments

Artificial intelligence is a really powerful techniques which gives any application powerful human like capablenesss. Normally intelligent behaviours make any application really smart and adaptable to any environment. Now we need adaptative smart application which can response good unpredictable state of affairs. in such scenarios unreal intelligence is really critical.

In a practical world simulation unreal intelligence can play a major function. Because the fake environment in the practical world simulation demand to be really near to the existent natural environment. For illustration if an agent in practical world environment demand to voyage in the practical environment it should be smart plenty to make its end by hedging all obstructions he faces on the manner. In these state of affairss unreal intelligence can play a immense function

There are many attacks of unreal intelligence. Such as Artificial Neural Networks, Genetic Algorithms, Ant Algorithms, Fuzzy Logic, Hidden Markov theoretical accounts and many more. Biggest job with these unreal intelligence attacks is that they require batch of treating power. For illustration if a Neural Network is used for some procedure in existent clip practical world simulation it will necessitate batch of clip to the Neural web to develop and bring forth the end product. So Artificial Intelligence attacks which will necessitate really heavy weight procedure is really hard to be used in existent clip practical world simulations. So if we are utilizing Neural Networks we will hold to develop the Neural Network and utilize the trained ANN in the simulation.

But in comparing to the other Artificial Intelligence approaches execution of fuzzed logic can be achieved by comparatively really light weight procedure which is a important plus point over other Artificial Intelligence attacks. So because of being really light weight Fuzzy Logic can be used in existent clip Virtual Reality simulations. For illustration if two agent in a Virtual Reality environment battle with each other we can utilize fuzzed logic to do their more realistic.

Because of being really light weight usage of fuzzed logic in Virtual Reality research is increasing twenty-four hours by twenty-four hours.

Chapter 04.

Fuzzy Model for practical agent controll in practical world environments

In fact every entity in practical world simulation can be considered as an agent in practical world environments. But because of computing machine public presentation grounds every entity in a practical world environment is non modeled as entities. This research done by S. Vosinakis of Department of Informatics University of Piraeus proposes to Better the public presentation of these practical agents utilizing fuzzed logic accountants


Fuzzy logic is already used in electronic control such as electronic motor control systems. So fuzzed logic has the possible to be used in control system for practical world agents.

In Virtual Reality simulations a practical agent is considered as an independent entity in the 3D infinite. These agent s are considered as man-made characters which interact with their practical environments through their practical detectors. For illustration a auto or some sort of animate being in our simulation can be considered as an agent in our Virtual Reality simulation. Just like their opposite numbers we see in our twenty-four hours to twenty-four hours life these practical agents besides shows some complex behaviours. So researches has made these agent intelligent so they behave smarter

There are many attacks for these agent control. The simplest attack is to utilize scripting. Here for control purpose batch of “ if and else “ statements are used. This is the most simplest and widely used method. Main advantage of this scripting attack is its good directional control. IMPROV is such popular scripting system. But the biggest disadvantages of this attack is its inflexibleness which means we need to predefine everything.

In add-on we have sensor driven control which is derived from AI research. Here incoming stimulation is coupled to ongoing reaction. These agents are normally equipped with an AI contriver. This AI contriver uses symbolic concluding attack and takes determinations harmonizing to agents purposes. In comparative to scripting attack this attack is much more flexible in altering environments. But the job in this attack is its logical thinking on which based on symbolic description of the environment. This description is stored in planetary database and alterations harmonizing to predefined effects of agent ‘s actions. Although this attack is comparatively flexible than earlier discussed scripting attack this attack besides have the job of deficiency of flexibleness. Here the job is in some dynamic environments the effects of some actions may non be known a priori ( e.g. athleticss such as football ) , In these state of affairss we need a spacial logical thinking engine that can ground about object dealingss in a higher degree and dynamically update the universe ‘s symbolic representation.

Fuzzy logic is efficaciously being used in electronic control systems. Later it is used in robot pilotage and obstruction turning away. This paper presents manner of utilizing fuzzed logic to specify inter object spacial logical thinking. This paper introduces a fluctuation of fuzzed sets for the exceptional instance of the 2D plane called Fuzzy Region. It besides defines a several rule-based system for covering with spacial jobs in Virtual Reality environments

4.1 Fuzzy Regions

This construct is based on the construct that utilizing fuzzed logic we can stand for spacial relationships like “ near ” , “ in forepart of ” , “ beside ” which can be represented in fuzzed sets with some grade of member of. Here fuzzed part is considered as a particular instance of fuzzy set. Here universe revelation U is a second country and rank map gives us the rank grade of a the peculiar point in our part. Here the cosmopolitan revelation ( U ) can be uninterrupted or discreet.

Figure 1.1

Here the country is shaded harmonizing to the rank values. By utilizing these fuzzed countries we can specify fuzzed set operations.

4.2 Proposed fuzzy regulation base

The fuzzed parts are used to build the fuzzy regulation base. Fuzzy regulations have two parts.

A premiss consists of one or more ancestors

A decision consists of one or more effects

Here ancestors have following signifier. Reason for utilizing a technique like this is that the agent logic can non be based on whether some point is in an country of involvement. It truly depends on whether the whole object satisfies such status

4.3 Object part IN Fuzzy Region

This value will be calculated by acquiring the mean of rank values of the points of the whole object

Then these ancestors are so combined in to premises utilizing NOT, AND or OR maps. Consequences are besides Fuzzy sets which are assigned with some end product variables. A effect of a regulation may hold several effects. A fuzzed regulation fires in to some sort of grade depending on belief degrees of each ancestors of the premises. These ancestors are evaluated utilizing rank maps which produce belief degrees. These belief values modifies the fuzzed end product part.

The decisions of fuzzy regulations are so combined in to the concluding determination. Then each fuzzed part should be defuzzified to bring forth the concluding consequence here a 2D point. Here centroid and the norm of upper limit. In the first instance we calculates the centroid of the volume defined in the fuzzed part and undertakings it on the 2D plane to happen the defuzzyfication point. In the 2nd instance we find the norm of the points in the part that have the maximal rank value. There is another 3rd method which is suited chiefly for pilotage. This is called nearest upper limit method. This method returns defuzzyfication point. This point is the maximal rank value in the part and besides it has nearest distance to a given point or mention. So this method can be applied to agent ‘s current location as a point mention. This will return the nearest mark point which satisfies the fuzzy regulations. Depending on the job the defuzzification method could besides be used in a smaller part around the mention point and non to the whole existence of revelation.

4.4 Execution

Alternatively of utilizing arrays for fuzzed 2D infinite usage of ordered set of points are proposed. The system assumes that there is a additive connexion between each point to following. In add-on Al points except first and last, takes the value of their nearest extreme. Here a fuzzed part is defined by X and Y fuzzed sets. Whenever a rank value of some point is to be calculated i??X and i??Y value of peculiar set is calculated. Then they are combines to bring forth the coda to the finale value. Although this method is less computationally expensive

but this method curtail the part to some signifier. We ca n’t declare arbitrary points.

Chapter 05.

A Fuzzy Action Selection Method for Virtual Agent Navigation in Unknown Virtual Environments

5.1 Introduction

Behavior based control is dominant portion in agent control. This paper presents a new Action choice method based on fuzzed alpha degrees and Huwicz standards.

5.2 Background

In a behavior base vitamin D system behaviours are considered as procedures to accomplish chief end of the agent. Here the end of the system is achieved by subdividing the overall undertakings by little subtasks. Normally a action choice method computes which action should be executed by BBS.

Normally action choice methods ( ASM ) classified in to two groups. That is arbitration and merger. Arbitration ASM allow one behaviour or set of behaviours at the same clip to take the control for a period of clip until another set of behaviours is activated. This procedure can be one of the following

* Priority- Action is selected by a cardinal faculty based on a priori assigned

* State based – Choose a set of behaviours which are competent to manage the state of affairs

* winner-takes-all – Set of behaviours compete with each other behaviour with maximal response will take over the control.

* Voting- The action with upper limit leaden amount is calculated by sing the end product of each behaviour

* Fuzzy – Similar to vote but uses fuzzed internecine mechanism

Here Fuzzy Logic is used to this intent. Architecture of fuzzed accountant is comprised of three behaviours that is path planning, end seeking and obstruction turning away

Overall architecture

IF x is Y AND Y is B THEN is z is C

This is a fuzzed regulation where ten, Y, omega are lingual variables. A fuzzed associatory memory ( FAM ) is used as a procedure of encoding and mapping input fuzzed sets into fuzzed end product sets. For illustration a set of fuzzy regulations R=R1: R2: : : : : Rhode island: : : Rk.. The regulation Ri is defined as follows

If X1 is A1m AND X2 is a2m and: : : age-related macular degeneration xN is Amn THEN Z is Cmn… … . ( 2 )

The undermentioned relation will implement Ri

Ri ( X1, X2… … … … .Xn: Omega ) = ( A1m*A2m*A3m* … … .Anm & gt ; Cnm ) ( X1.X2.X3… … … … … .Xn, Z ) … … .. ( 3 )

We can rewrite equation ( 3 ) below

Ri ( X1: X2: : : : : :Xn: Omega ) = [ A1m ( X1 ) ^A2m ( X2 ) … … .. ^ ] & gt ; Cnm… … … … … ( 4 )

Where X1: X2… … … … .Xn are input variables which are sensor informations of the practical agent A1m: A2m: : : : : : : :Anm are the input fuzzed sets. Cnm is the end product fuzzy set Z is the end product variable, n is the dimension of the input vector and m is the figure of fuzzed sets

In order to make an n fuzzy input vector X =X10: X20: : : : : : : : : : : : : : : : : : : Xnm… … . ( 5 )

The system needs to compose the input vector Ten with the deliberate fuzzed relation Ri to bring forth the undermentioned input C

Where Xmn is the fuzzed chip value Xmn into fuzzed end product category Cj ( Z ) . The end product of the ith regulation

The system needs to compose the input vector Ten with the deliberate fuzzed relation Ri to bring forth the undermentioned input C

Where Xmn is the fuzzed chip value Xmn into fuzzed end product category Cj ( Z ) . The end product of the ith regulation

Ci= [ A1m ( X1 ) ^A2m ( X2 ) … … .. ^ ] & gt ; Ci

Here mamdani method is used to defuzzyfication

C= SwiCii

C= SwiCii [ A1m ( X1 ) ^A2m ( X2 ) … … .. ^ ] & gt ; Cnm

Wi is a non negative value.

Defuzzyfication response= SwiCii/Swi… … … … … … … … … … … … … … ( 6 )

Equation four and six used to deduce Fuzzy Action Selection method

The action choice method

This method uses fuzzed alpha degrees and fuzzed minus operation to cipher the country of a new fuzzed figure. Here it is produced by the comparing two fuzzed Numberss. This research uses a cut down redundancy of this computation.

Let i??X~ ( X ) be the rank map of a fuzzed figure X~ behaviour end product defined on R. Here n premise about the normalcy of i??X~ ( X ) are made based on the left and right of the fuzzy alpha cut of the fuzzed figure, X~ , are i??L X~ a ( ten ) and i??R X~ a ( ten ) and 0 & lt ; a & lt ; h X~ .

Here H is the tallness.

degree Celsiuss and vitamin D are at the minimal value of the left and right spread of all fuzzed Numberss. Interval minus is used to simplify the minus between fuzzed Numberss


Let X~1, X~2, X~3… … … … … X~m be thousand arbitrary edge fuzzed Numberss produced by each behaviour.

1. Put the tallness mercury ( x ) , common maximising barrier and degree Celsius for referential rectangle R~

2. Determine the subtracted interval Numberss

3. Determine behavior weight for each fuzzy figure

4. Repeat measure 2 and 3 for every interval

5. For every W use the minmax ( maxmin ) standard which select the lowest value for fuzzed Numberss

6. Determine the index optimism a. Then the finale behaviour is selected by the huwicz standard

Chapter 06.

Modeling human behaviour at work utilizing fuzzed logic

6.1 Introduction

Correct choice of single workers to undertakings is a really difficult undertaking. So AI can be used to imitate the human behaviour. This research paper propose a Fuzzy Logic based method to stand for the people and some of the people features. This research focal point on the fuzzed features and how the squad behaviour can be modeled with agents ( people ) and undertaking features.

6.2 Modeling human capablenesss at work

Modeling human behaviour has been a major job. Because human are unstable, unpredictable and capable of taking their ain determination. In add-on in a on the job environment public presentation of each person will change depending on their experience, ability, instruction and their current physiological provinces.

This paper suggests that there are three challenges in human behaviour mold

* Human are non limited to one individuality or any common set of emotions

* Human are non limited to moving in conformity with preset regulations

* Human are non limited to moving on local forms

As imitating human behaviour as a whole is about impossible this paper proposes that it is possible to imitate some parts of human behaviour. Here this paper proposes to imitate behaviour of a on the job squad. First thing is to place the set of relevant human features that affects the public presentation of individual in a squad. These features can be groped in to four classs

* Cognitive capabilities- This involves complex encephalon procedures

In these paper these cognitive capablenesss were defined by the grade of expertness of some person in some field.

* Personality trends- CLEAVER technique is used for this intent ( This is a questionnaire which give a numerical value about personality tendency parametric quantities )

* Emotional trends- This research expression at two tendencies that is positive emotion and negative emotion

* Social characteristics- Here features such as good communicating and co-ordination is considered.

6.3 Fuzzy logic to pattern human behaviour

After parametric quantities of internal features are measured, these features are represented and measured as follows. All the features are linked together. The behaviour of a individual is generated by uniting above mentioned features.

But it is fascinating that a simple numerical value can stand for human emotions and

Complex behaviours. Here three qualitative properties are used they are low, medium and high.

Fuzzy logic can be used to pattern this three features.

6.4 Identification of fuzzy parametric quantities

First measure of this theoretical account is to place fuzzed parametric quantities. And besides their scopes need to be found. Fuzzy sets are used to parameterize the chief facets in the mold which includes following

* Agent internal features.

* Undertakings

* Agent public presentation

* Modeling of the human behaviour

6.5 Internal features

Internal features are fuzzified by utilizing a Gaussian rank rank map. For emotion, cognitive and societal features three strength fuzzed sets are defined. Range of the values of these fuzzed sets range from 0 to 100.

Low intensity- 0 to 35

Medium strength -25 to 75

High strength -60 to 100

In add-on fuzzed sets were besides used for

Increase/ lessening fuzzy sets besides defined for the emotion strength. It is calculated as a consequence of as a consequence of firing behaviour regulations in the simulation procedure.

Fuzzy sets used to increase/decrease the emotional and stress strength

6.6 Undertaking parametric quantities

The behaviour of the work is modeled through interaction between squad members. Undertakings patterning puting values to 11 parametric quantities.

1. Number of participants in the undertaking.

2. Estimated continuance ( measured in yearss ) .

3. Sequence ( consecutive or in parallel ) .

4. Precedence within the undertaking.

5. Deadline.

6. Cost.

7. Quality.

8. Application sphere.

9. Task description

10. Trouble.

11. Type ( required specialisation degree ) .

Last two parametric quantities are fuzzed parametric quantities. This parametric quantities shoe required specialisation degree to accomplish some undertaking.

6.7 Agent public presentation parametric quantities

Following parametric quantities are proposed to used to mensurate the public presentation of the each single agent in the theoretical account

1. Goals accomplishment.

2. Seasonableness.

3. Quality of the undertaking performed

4. Team coaction degree.

5. Contribution of each person

6. Required supervising degree.

The research workers has used this three parametric quantity because these are the parametric quantities used by undertaking leaders of some crude oil companies. Here besides the public presentation parametric quantities value scope from 0 to 100. In is divided in to five fuzzed sets. Very low ( 0-30 ) , minimal ( 45-75 ) , acceptable ( 65-95 ) and satisfactory ( 90-100 )

Fuzzy sets to pattern human behaviour

In this research fuzzy regulations are used to imitate how workers might execute in some state of affairs. The fuzzy values which fire from -20 to 20 modify the seasonableness parametric quantities. The fuzzed values of them are high_advance ( -20 to -5 ) , medium progress ( -10 to 0 ) , normal ( -5mto 5 ) meduum hold ( 0 to 10 ) and high_delay ( 5 to 20 ) . When all these values are deffuzyfied sharp values are calculated and delegate to matching parametric quantities.

Fuzzy regulations for patterning human behaviour

After fuzzed parametric quantities are identified and defined, it is needed to construct the fuzzy regulation base required to construct the simulation. In this research it is done three stairss

Here there are three sets of fuzzy regulations are used.

1. Fuzzy regulations to modify the agent internal province

2. Fuzzy regulations to acquire the agent public presentation

3. Fuzzy regulations update the agent internal province.

Modifying the internal province of the agent

In this research the undertaking director selects initial set of possible squad members. Besides assign undertakings to each members. After that the simulation begins. Then emotion and emphasis values are set for the internal province of the agent. For the research it is assumed that

All squad members have medium strength values for the emotions at the beginning. Harmonizing to the internal and external factors the corresponding fuzzy regulations are triggered. strengths of the agent ‘s emotion and emphasis are modified in the simulation.

IF T1 presents a high_delay AND A1 has a driver personality with high_intensity


The desire emotion will hold a high_increase

The involvement emotion will hold a high_increase

The disgust emotion volitions stay_equal

The anxiousness emotion will hold a low_increase

The emphasis will hold a low_increase

IF A1 is introverted AND in T1 must interact with other people THEN

The desire emotion will hold high_decrease

The involvement emotion will hold a low_decrease

The disgust emotion will hold a high_increase

The anxiousness emotion will hold a low_increase

The emphasis will hold a low_increase

Generating agents public presentation

Nest set of fuzzed regulations involves the mold of agent public presentation. Because of that the regulations settings the agent public presentation parametric quantities for each assigned undertaking are triggered.

Given the agent A1 in charge of undertaking T1,

IF A1 has a high creativeness degree ; A1 has a driver personality with high_intensity AND

T1 requires a high specialization degree THEN

The ends accomplishment is normal

The seasonableness has a medium_advance

The quality has a medium_increase

The squad coaction degree is normal

The single part has a medium_increase

The needed supervising degree is normal

IF A1 has a low experience degree AND T1 is a high hard undertaking THEN

The ends accomplishment has a medium_decrease

The seasonableness has a high_delay

The quality has a medium_decrease

The squad coaction degree has a medium_decrease

The single part is normal

The needed supervising degree has a medium_increase

6.8 Execution inside informations

JADE model is used to construct the multi agent system

* The package agents do non work to work out any existent undertaking but they merely simulate

their interaction with other agents and with their assigned undertaking ( s ) .

* A plausible set of planetary behaviours of a squad is obtained by averaging its behaviour

over a statistically important figure of simulations.

* degree Celsius ) The most suited squad constellation can be obtained by comparing the sets of

planetary behaviours for several possible squad constellations.

* vitamin D ) We can non anticipate the hereafter, so we can non vouch that the squad will act

precisely as the simulations suggest, but we aim to bring forth information about

possible public presentation forms. This information can be peculiarly utile in the

designation of unwanted public presentation forms and their relation to the squad

constellation and undertaking assignment.

Chapter 07.

Fuzzy Logic based method for practical surgery simulations

7.1 Introduction

This research is based on utilizing fuzzed logic for surgical simulations. As this is a existent clip procedure Fuzzy Logic can be efficaciously used.

7.2 Design of Fuzzy Logic system

Cuting of a practical surgery depend on two parametric quantities force on the practical tool

and stiffness on the practical tissue. These parametric quantities are fuzzified to acquire rank values matching measured parametric quantity values. Then they are fed to obtain fuzzed regulation base

Specifying fuzzed rank maps

Fuzzy accountants based on the experience of the expert inspired by existent people. The maps for rank Inputs and end products must be defined by the experience of experts. The rank map defines the fuzzed sets in each input and end product variable. In our practical surgery system, the rank maps defined for the input variable ( force and stiffness ) and the end product size ( deepness ) as shown in Figure 2. Each member Ship map is divided into several fuzzed parts ( little, medium, etc. ) . The x-axis of Figure 2 ( a ) provides Input force and the normalized y-axis quantifies the partial rank values of a peculiar group in any Fuzzy part. The x-axis of Figure 2 ( B ) represents the normalized stiffness of the soft tissues while the y-axis Teachings of partial rank values of a given stiffness in each fuzzed part

Constructing fuzzed regulation base

The fuzzy regulation base transforms the input maps given merchandises. To make the regulation base, a

Correspondence tabular array is defined. The search tabular array defines the appropriate actions are taken for each combination Input fuzzed sets. To accomplish this end, a 3-dimensional array is constructed. The input maps are represented in the axes X and Y. The end product map is represented in the Z-axis in the practical surgery system

Input map of the force in the x-axis and Y-axis stiffness of the end product map of deepness

represented in the Z-axis, the mention tabular array for practical operations of this fuzzy system is given in Table 1.

Membership map for force factor

Membership map for stiffness

7.3 Appling Fuzzy regulations

The rank value of each fuzzy set in the input maps determined. It is calculated from

Definition of the map member. For each combination of input rank values, the combination of fuzzed logic determined by fuzzed mathematics. This is because the regulations we have written regulations. All values each class of members are collected and added end product. De fuzzification is achieved by the minutes about the beginning, including all members Output Values. This method is normally referred to as the centroid method of de-fuzzificatiion.


The fuzzed practical surgery system has been used to do the cut tissue ( Fig. 3 ) on the footing of bing

the user and the stuff belongingss. The experiments were conducted to find the cogency of the estimation of the fuzzy


Chapter 08.

Fuzzy logic base 3D hit sensing algoritm 3D hit sensing

8.1 Components of a surgical simulation

Simulation rhythm of proposed surgical simulator

8.2 Proposed hit sensing algorithm

We define two vectors stand foring the province of the scene. First, the gesture vector normalized VM the way of motion of the tool on the Body between two stairss a simulation. Second, a vector represents the surface of this organic structure. Collisions may impact several vertices the deformable theoretical account. It was adopted in the preliminary working with all the corners to cover in struggle, because the aspect

Crossings can be prevented in this manner. However, if the Collision of two aspects oppsosite the tool, all corners move frontward together to accomplish one of them and the tool is. This consequence may look in scenes of the simulation as the basic film editing. So independent vertex use has been accepted. Each outer normal the facet J around the corner I must be considered,

. These two vectors are normalized. In add-on, three instances of interactions are distinguished,

all facets of around a fortress Vertex, the system is fuzzed feedbacked. The end products of the system

Tuple I = ( IP, IS, IE ) , weighing the grade of similarity the state of affairs on a instance by instance interaction, and it is besides an application input to the following loop. Therefore, the supplanting vectors

every corner collided deformable theoretical account is obtained as follows. Finally, Figure 2 shows the rank maps IC lingual variables and the tuple I. It is apparent in this figure. Here its S represents a threshold between the interaction Cases. These instances are considered every bit likely

( a ) Fuzzy rank maps

( B ) Fuzzy lingual variables


Robotic association football with Fuzzy Logic

9.1 Introduction.

Traditionally, we think of automatons as a really independent person They interact with their environment. On the other side of the automaton ‘s environment may be another automaton, and if there is any sort of communicating between robot interaction must be societal. In this instance, we see the automaton system as a group of persons, and take attention of their single outgrowth behaviours. Good tool for development and testing of single behaviour and societal automatons is robot association football. It allows easy coevals of different state of affairss and comparing of the effects of their control mechanism by playing against each other. Robot association football is a game between two squads of robotic association football participants. Capable to the

the accountant is a robot association football squad with five members. A two-wheeled automaton that conveyance equipment, wireless senders for communicating and 16-bit accountant used for basic control of electric motors Micro ( Fig. 2 ) . The automaton does non even does non acknowledge the input component, is the lone entry in the robotic system, camera with image acknowledgment ( Fig. 1 ) . Part of the system is besides home Personal computer

machine for high degrees of control and image acknowledgment

Fig- 1

Fig – 2

9.2 Fuzzy expert system

Expert cognition is frequently covering with unsure cognition. This particular

applied to information in the field of robot association football, where we wok with footings such as

“ Near ” , “ left ” and the similar. Fuzzy logic enables us, with this type of work

Information. Soccer game contains more than one individual by definition, In robotic association football there are more robotic participants and each has its ain undertaking and requires different attack and cognition base.

It is clear that we do non believe the football squad, merely how to travel object. Multi-agent theory allows us to this job in several organisations and fade out. Think of all the parties individually relevant cognition. Design of multi-agent system consists of several types of agents together. Each it was his function in the decision-making. Their independency enables a good decomposition of the job and secondly, working together, once more creative activity, and their parts to command up to a complete system. In the multi-agent system control robot football we need more types of logical thinking and agents a sort of broker-agents have to guarantee communicating, synchronism Information and caching. Definition states that the independent agents in a system and is Part of an environment that believes that the environment and acts on it over clip pursues its ain docket and give consequence to the way in the hereafter. Our Cases, the independent agents the agent with fuzzy expert system for concluding

General information about agent agents can be found in. However, in this

work we use term ‘broker agent ‘ more intuitively. Purpose of agent agent in our apprehensiveness is to roll up informations from other beginnings and supply them for other agents. They do non execute any logical thinking by themselves.

9.3 Components of the system

We have stated undermentioned definition: System utilizing multi-agent distributed architecture, expert system and fuzzed illation mechanism we call multi-agent. When we are looking for theoretical accounts for multi-agent system for association football automatons have control, which was ideal for the true football game created by existent people football lucifer together. The game is packed with participants on the field, but even managers, referees, witnesss, even those who work in telecasting transmittal it allows us to see the game at place are involved throughout the procedure. Taking

given these facts, our revenue enhancement system contains the undermentioned entities: agent participants Agent managers, agents and agents telecasting mailman.

Player Agent represents a individual that has contact with the ball. It emulates human abilities to acquire to the best place, get ball, base on balls to other participant or shoot to the

end. Player can play function of goalkeeper, onslaught or defence. Player ‘s ability to see in Player Agent is implemented as Ocular Module. Purpose of the Visual Module is to have absolute co-ordinates from agent Cameraman, transform them into radial signifier and insert fuzzified information into illation system. Every object, seeable to the Player is transformed into radial co-ordinates which are more close to human perceptual experience.

Ability to have messages to other participants and functionaries can entrainer compared to the abilities to hear from existent people. This sort of agents can be used for input take the purposes of the head and the provinces of other agents. For case, if robots the ball can be and it announced the remainder of the squad can retrieve his proclamation and concentrate on obtaining better places in the tribunal received Agent of the trainer. Strategic storage for the provinces of the game. We can utilize it to remember the informations non that with each bend of the determination rhythm, such as purposes of the automaton to alter its The strategic nonsubjective relevant ads or other agents. In contrast to experts Database system to keep the memory contents of the strategic game

Appraisals reflect the strategic state of affairs. Memory contents are changed from strategic having messages from other participant ( person from the squad received the ball ) , or if the alteration of Game state of affairs is realized in the justification procedure.

Player ‘s accomplishment to play association football is apprehended as ability to treat ocular information and decide it into action. When we take ocular and hearing input, concluding utilizing participant cognition should take into infering desired participant ‘s action. This action is so executed by the illation system and velocity vector is produced. This vector so can be sent to other agents for farther processing

Each participant besides has a memory that contains critical information about current games

Situation and policies of the last lap. Memory content is added strategic illation engine. This measure is called perceptual experience. Then takes the concluding measure system declaration information from the database and included Action decided that the participant has to carry through. The determination may be deterministic, where Actions must happen at a clip, or stochastic, where the participant can take

several possible actions. Stochastic determination may be influenced by the control

parametric quantities, so we can put the penchant for certain steps. These parametric quantities can

single features drive express ( team game, agile… ) . Part of the Player ‘s

cognition base in footings of declaration measure is like a tree of the determination represented on

Image. Last measure is called executing. In this measure, it will be the resulting action and its mark ( ball

or the halfway place ) is taken in order by agencies of fuzzed illation Madani, velocity besides obtained. The vector is the consequence of the illation procedure together.

Agent coach- Stand as the manager of the squad. These agents does non play the game but focal point on the scheme of the squad. It sees the resort area in birds position. Here agent ‘s ocular faculty takes absolute carbon monoxide ordinates. Coach usage fuzzed lingual variables like “ punishment country ” “ centre of the field ” etc. These lingual footings insert in to he inference engine. Which consequence in recommended places for the agent type “ participant ” .

Agent cameraman- This agent sends a message with the co-ordinates of all objects seeable

All employees, which contain a sort of perceptual experience of ocular information. These messages can besides function as synchronism signal for the whole System. Whenever the independent agent is replaced by new ocular information, it begins a new rhythm can run in its reasoning.. Purpose of agent camera operator is the ocular information to the resort area for agents who need them. It has no determination has accomplishments, his end merely hoarding and bringing of ocular information.

Agent mailmans – Mailman is merely acts as a buffer to roll up information on the consequences of the determination taken by the participants. It processes and sends out synchronized with the outside universe. But this agent is really simple and contains about no logic


Execution of this was done utilizing JADE agent model

10. Decision

As discussed in this papers Fuzzy logic is doing immense impact on practical world simulations. First paper talked about utilizing a particular fuzzy set called fuzzed 2D part. Second paper I discussed which besides talks about practical agent pilotage usage fuzzed alpha values and Huwicz map. Sing the overall public presentation in the two attacks the method usage fuzzed alpha values is much efficient because it significantly cut down figure of comparing which consequences greater efficiency.

Then I discussed about utilizing fuzzy for human behaviour mold. But harmonizing to the research they have put batch of restrictions and premises in their research. In add-on many complex human behaviours and complex human encephalon activities were non yet to the full understood ( It is interesting whether a human encephalon can understand itself! ) . So I do n’t believe that modern computing machine scientific discipline is matured plenty to pattern human behaviours. But Fuzzy Logic has surely has shown batch of promise in this country but still there are batch of restriction and premises which make bing research theoretical accounts place themselves really far from useable human behaviour theoretical account. I think batch of research and promotion of computing machine difficult ware will give more promise. In add-on merely fuzzed logic may non be plenty for this intent. Fuzzy Logic in coaction with Artificial Neural Networks will be more effectual. May be new AI attacks such as new Ant Colony Optimization ( ACO ) and Artificial Immune Systems besides can be considered

Following I discussed about usage of fuzzed logic in surgical simulations fuzzy logic in this country has shown batch of promise. There fuzzed logic has shown batch of promise and adulthood. Following I discussed how fuzzed logic can be used in robotic association football. Fuzzy logic which needs really light weight procedure has shown batch of promise in this country.

As a whole I think for existent clip simulations fuzzy logic is the ideal Artificial Intelligence

technique available today. Because it non merely heavy plenty to bring forth good AI it is besides light plenty to suit with modern hardware. So Fuzzy Logic will be to a great extent used in orderly coevals VR research and simulations.