SlideShare una empresa de Scribd logo
1 de 20
Thongam Khelchandra

Jie Huang

Information systems Department,
The University of Aizu, Japan

Somen Debnath
Department of Information Technology,
Mizoram University, India
1. Introduction
• Problem Definition
• Previous Work
• Tools Used
• Advantage
• Diagram showing whole process
2. Path Planning using Artificial Neural Network
3. Fuzzy Logic System for Obstacle Avoidance
4. Results
5. Conclusion
2
Problem definition


a robot with an initial location and orientation, a goal
location and orientation



a set of obstacles located in workspace (static or moving)



compute a collision-free path for the robot



intelligent control of the robot which should move safely in
the environment.
3

-




Computational geometry
potential functions, roadmap methods, cell
decompositions, sampling based algorithms
unfeasible in real time
Artificial neural network
solves the problem
use of parallel algorithm by ANN
Hybrid system (Neuro-Fuzzy, Genetic-Fuzzy)
4
• Artificial Neural Network
- Multilayer
Perceptron with BP learning
algorithm
- Classification task
- Trained to choose a path from n set of paths
• Fuzzy Logic System
- FL is use for obstacle avoidance








The difficulties of traditional method in
creating the configuration space with
expensive computation are solved by using
neural networks
This method realizes a considerable increase in
performance and speed
If some of the neurons do not work due to lack
of information, still the system will work and
get the output
the combination ANN and fuzzy system is
computationally efficient by helping each other
to eliminate their individual limitations.
Schematic Diagram of the whole process

FUZZY
SYSTEM

Distances to
obstacles

INPUT

If all
paths
blocked
by
obstacles

NEURAL
NETWORK

OUTPUT

Collision free
path
• ANN is trained with some

training samples initially
• xi is the input which is the
distance in n directions to the
first obstacle
• Vij is the weight connecting
the ith input to the jth hidden
neuron
• wjk is the weight connecting
the jth hidden neuron to the
kth output neuron
• ok is the output, 0 or 1

MLP Network
TRAINING PHASE
•x1, x2, x3 are inputs to ANN

•

if obstacle in the path, then
desired output di = 0 else di = 1

• in the figure, d = [ 0, 1, 1]
i

• error between the actual output

oi and desired output di is
minimized by adjusting the
connecting weights

•w

jk

(n+1) = wjk(n) + η*δk(n)*yj(n)

Robot choosing
direction
OPERATION PHASE

•Use

the weights vij and
wjk to find the outputs

•

eg: oi = [0,1,0] will
choose the center path

•

if all paths block by
obstacle i,e oi = [0,0,0]
then FL system is use to
avoid the obstacles

Path of the robot
• At position 5, all the
3 paths are blocked by
obstacles
• In such situation, FL
is applied

All paths blocked by obstacles
•

Input
1. Variable : angle
- Angle between the left obstacle edge and the
robot centre
Values : {small, medium, large}
2. Variable : distance
- Distance between the robot and the obstacle
blocking the middle path
Values : {near, far, very far}
3. Variable : left_obstacle_dist
- Distance between critical obstacle and nearest
obstacle on the left side
4. Variable : right_obstacle_dist
- Distance between critical obstacle and nearest
obstacle on the right side
Values : {near, far}
• Output
1. Variable : adjustment angle
- Adjustment Angle of the robot to avoid
possible collisions with obstacles on left or
right side of the critical obstacle
Values : {small_left, normal_left, big_left,
small_right, normal_right, big_right}
•

angle,
distance,
left_obstacle_dist,
right_obstacle_dist are the
input variables
• adjustment angle is the
output variable
• the robot avoids the
obstacles O’s when
moving from point c
• the rule base consist
of 36 rules of the form
if(angle == S) and (distance ==
F) and (left_obstacle_dist
== F) and (right_obstacle_dist ==
F) then adjustment
angle = SL

Avoiding obstacles
Rule Evaluation

Calculation for degree of membership of the input values
• Use Trapezoidal membership function with max-min composition
T1 = (input - a) / (b - a)
T2 = (d - input) / (d - c)
T1 = Min(T1, Min(1, T2))
T= Max(T1, 0)

15
Defuzzification


Weight of a rule is calculated by

W = angle(angle-input) * distance(distance-input) * left_obs_dist(left_obs_dist-input) *
right_obs_dist(right_obs_dist-input)


The function angle( ), distance( ), left_obs_dist( ), right_obs_dist( ) will
give the value of degree of membership

Actual output is calculated by equation
Crisp output= [(w1 * v1) + (w2 *v2) + (w3 *v3) + (w4 *v4) +(w5
*v5) + ………......+ (wn * vn)]/ [w1+w2+w3+w4+w5+……wn]


16
 the robot chooses the
middle path for the first,
second and third motion
using neural network
 in the fourth motion, the
robot chooses the right path
 from fifth to seven, it
chooses the middle path
 in eight motion, it
chooses the left path
 at the ninth motion, all the
3 paths are blocked by
obstacle A
 the obstacle at the ninth
motion is avoided using
fuzzy logic

Robot path upto ninth motion
 The values of the input
variables of the fuzzy system of
the robot ninth motion are 1. angle
= M 2. distance = F 3.
left_obstacle_dist
=
N
4.
right_obstacle_dist = N.
 The degree of membership for
variable angle with linguistic value:
(1) small = 0.000000 (2) medium =
0.386667 (3) large = 0.226667.
 The degree of membership for
variable distance with linguistic
value: (1) near = 0.000000 (2) far =
0.750000 (3) very far = 0.500000.
 The degree of membership for
variable left_obstacle_dist with
linguistic value: (1) near =
1.000000 (2) far = 0.500000.
 The degree of membership for
variable right_obstacle_dist with
linguistic value: (1) near =
0.666667 (2) far = 0.750000.

Robot reaching the goal











Proposed a new method of path planning of a mobile
robot using ANN and Fuzzy system
ANN is used to choose a path from a set of paths
The fuzzy system is used when all the paths are
blocked by obstacles
Results show that the combination of these features is
computational efficient by helping each other to
eliminate their individual limitations
increase in performance and speed as compared to
traditional method with computational geometry
Future work can be path planning in dynamic
environments containing moving obstacles
Thank you very much !

Más contenido relacionado

La actualidad más candente

Conjugate Gradient method for Brain Magnetic Resonance Images Segmentation
Conjugate Gradient method for Brain Magnetic Resonance Images SegmentationConjugate Gradient method for Brain Magnetic Resonance Images Segmentation
Conjugate Gradient method for Brain Magnetic Resonance Images SegmentationEL-Hachemi Guerrout
 
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVES
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVESSURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVES
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVESZac Darcy
 
Fuzzy c-means clustering for image segmentation
Fuzzy c-means  clustering for image segmentationFuzzy c-means  clustering for image segmentation
Fuzzy c-means clustering for image segmentationDharmesh Patel
 
Full–body Tactile P300–based Brain–computer Interface Accuracy Refinement
Full–body Tactile P300–based Brain–computer Interface Accuracy RefinementFull–body Tactile P300–based Brain–computer Interface Accuracy Refinement
Full–body Tactile P300–based Brain–computer Interface Accuracy RefinementTakumi Kodama
 
Identification and Control of Three-Links Electrically Driven Robot Arm Using...
Identification and Control of Three-Links Electrically Driven Robot Arm Using...Identification and Control of Three-Links Electrically Driven Robot Arm Using...
Identification and Control of Three-Links Electrically Driven Robot Arm Using...Waqas Tariq
 
Region-based Semi-supervised Clustering Image Segmentation
Region-based Semi-supervised Clustering Image SegmentationRegion-based Semi-supervised Clustering Image Segmentation
Region-based Semi-supervised Clustering Image SegmentationOnur Yılmaz
 
The Technology Research of Camera Calibration Based On LabVIEW
The Technology Research of Camera Calibration Based On LabVIEWThe Technology Research of Camera Calibration Based On LabVIEW
The Technology Research of Camera Calibration Based On LabVIEWIJRES Journal
 
Image Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple FeaturesImage Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple Featurescsandit
 
Paris Lecture 4: Practical issues in Bayesian modeling
Paris Lecture 4: Practical issues in Bayesian modelingParis Lecture 4: Practical issues in Bayesian modeling
Paris Lecture 4: Practical issues in Bayesian modelingShravan Vasishth
 
The fourier transform for satellite image compression
The fourier transform for satellite image compressionThe fourier transform for satellite image compression
The fourier transform for satellite image compressioncsandit
 
Fingerprint Image Compression using Sparse Representation and Enhancement wit...
Fingerprint Image Compression using Sparse Representation and Enhancement wit...Fingerprint Image Compression using Sparse Representation and Enhancement wit...
Fingerprint Image Compression using Sparse Representation and Enhancement wit...Editor IJCATR
 
Tracking and counting human in visual surveillance system
Tracking and counting human in visual surveillance systemTracking and counting human in visual surveillance system
Tracking and counting human in visual surveillance systemiaemedu
 

La actualidad más candente (16)

Conjugate Gradient method for Brain Magnetic Resonance Images Segmentation
Conjugate Gradient method for Brain Magnetic Resonance Images SegmentationConjugate Gradient method for Brain Magnetic Resonance Images Segmentation
Conjugate Gradient method for Brain Magnetic Resonance Images Segmentation
 
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVES
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVESSURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVES
SURVEY ON POLYGONAL APPROXIMATION TECHNIQUES FOR DIGITAL PLANAR CURVES
 
Otsu binarization
Otsu binarizationOtsu binarization
Otsu binarization
 
Fuzzy c-means clustering for image segmentation
Fuzzy c-means  clustering for image segmentationFuzzy c-means  clustering for image segmentation
Fuzzy c-means clustering for image segmentation
 
Full–body Tactile P300–based Brain–computer Interface Accuracy Refinement
Full–body Tactile P300–based Brain–computer Interface Accuracy RefinementFull–body Tactile P300–based Brain–computer Interface Accuracy Refinement
Full–body Tactile P300–based Brain–computer Interface Accuracy Refinement
 
Identification and Control of Three-Links Electrically Driven Robot Arm Using...
Identification and Control of Three-Links Electrically Driven Robot Arm Using...Identification and Control of Three-Links Electrically Driven Robot Arm Using...
Identification and Control of Three-Links Electrically Driven Robot Arm Using...
 
Region-based Semi-supervised Clustering Image Segmentation
Region-based Semi-supervised Clustering Image SegmentationRegion-based Semi-supervised Clustering Image Segmentation
Region-based Semi-supervised Clustering Image Segmentation
 
PPT s04-machine vision-s2
PPT s04-machine vision-s2PPT s04-machine vision-s2
PPT s04-machine vision-s2
 
UFAngryBirdsC Agent
UFAngryBirdsC AgentUFAngryBirdsC Agent
UFAngryBirdsC Agent
 
The Technology Research of Camera Calibration Based On LabVIEW
The Technology Research of Camera Calibration Based On LabVIEWThe Technology Research of Camera Calibration Based On LabVIEW
The Technology Research of Camera Calibration Based On LabVIEW
 
Image Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple FeaturesImage Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple Features
 
Paris Lecture 4: Practical issues in Bayesian modeling
Paris Lecture 4: Practical issues in Bayesian modelingParis Lecture 4: Practical issues in Bayesian modeling
Paris Lecture 4: Practical issues in Bayesian modeling
 
The fourier transform for satellite image compression
The fourier transform for satellite image compressionThe fourier transform for satellite image compression
The fourier transform for satellite image compression
 
Fingerprint Image Compression using Sparse Representation and Enhancement wit...
Fingerprint Image Compression using Sparse Representation and Enhancement wit...Fingerprint Image Compression using Sparse Representation and Enhancement wit...
Fingerprint Image Compression using Sparse Representation and Enhancement wit...
 
Tracking and counting human in visual surveillance system
Tracking and counting human in visual surveillance systemTracking and counting human in visual surveillance system
Tracking and counting human in visual surveillance system
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 

Destacado

Carnevale - I costumi tradizionali dal mondo
Carnevale - I costumi tradizionali dal mondoCarnevale - I costumi tradizionali dal mondo
Carnevale - I costumi tradizionali dal mondoStylight
 
Vayishlach group 3
Vayishlach group 3Vayishlach group 3
Vayishlach group 3el9360
 
Persepsi dan pengambilan keputusan
Persepsi dan pengambilan keputusanPersepsi dan pengambilan keputusan
Persepsi dan pengambilan keputusanMuhammadIqbal169
 
De echte Mad Men & hun dubbele persoonlijkheden - BE
De echte Mad Men & hun dubbele persoonlijkheden - BEDe echte Mad Men & hun dubbele persoonlijkheden - BE
De echte Mad Men & hun dubbele persoonlijkheden - BEStylight
 
Samsung School aplikacija u 45 minuta
Samsung School aplikacija u 45 minutaSamsung School aplikacija u 45 minuta
Samsung School aplikacija u 45 minutaSonja Lusic Radosevic
 
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...AlbaInnovationCentre
 
Bodies and Buildings NYU ITP 10 20 2014
Bodies and Buildings NYU ITP 10 20 2014Bodies and Buildings NYU ITP 10 20 2014
Bodies and Buildings NYU ITP 10 20 2014Jen van der Meer
 
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...Challenges, Workflows, and Insights in the Collaboration to Preserve America'...
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...WGBH Media Library and Archives
 
MENA Purposeful Market - Product Strategy for 2014
MENA Purposeful Market - Product Strategy for 2014MENA Purposeful Market - Product Strategy for 2014
MENA Purposeful Market - Product Strategy for 2014Cole Wirpel
 
Spott invitation herremode_work_seminar0515
Spott invitation herremode_work_seminar0515Spott invitation herremode_work_seminar0515
Spott invitation herremode_work_seminar0515Anja Bisgaard Gaede
 
St patricks day
St patricks daySt patricks day
St patricks dayxyuko
 
Photo contest picts
Photo contest pictsPhoto contest picts
Photo contest pictsel9360
 
Assignment guide spring 2015
Assignment guide spring 2015Assignment guide spring 2015
Assignment guide spring 2015michael jones
 
Jeff kershner showrooming ppt
Jeff kershner showrooming pptJeff kershner showrooming ppt
Jeff kershner showrooming pptDealer ThinkTank
 
проект юніор дослідник ліза, мілана
проект юніор дослідник ліза, міланапроект юніор дослідник ліза, мілана
проект юніор дослідник ліза, міланаVlasyukA
 
Hal hal yang mempengaruhi kepuasan seorang professional
Hal hal yang mempengaruhi kepuasan seorang professionalHal hal yang mempengaruhi kepuasan seorang professional
Hal hal yang mempengaruhi kepuasan seorang professionalMuhammadIqbal169
 
Mishpatim group 3 ls
Mishpatim   group 3 lsMishpatim   group 3 ls
Mishpatim group 3 lsel9360
 
Week 4 sukkot-group 2
Week 4 sukkot-group 2Week 4 sukkot-group 2
Week 4 sukkot-group 2el9360
 

Destacado (20)

Carnevale - I costumi tradizionali dal mondo
Carnevale - I costumi tradizionali dal mondoCarnevale - I costumi tradizionali dal mondo
Carnevale - I costumi tradizionali dal mondo
 
Vayishlach group 3
Vayishlach group 3Vayishlach group 3
Vayishlach group 3
 
Persepsi dan pengambilan keputusan
Persepsi dan pengambilan keputusanPersepsi dan pengambilan keputusan
Persepsi dan pengambilan keputusan
 
De echte Mad Men & hun dubbele persoonlijkheden - BE
De echte Mad Men & hun dubbele persoonlijkheden - BEDe echte Mad Men & hun dubbele persoonlijkheden - BE
De echte Mad Men & hun dubbele persoonlijkheden - BE
 
Samsung School aplikacija u 45 minuta
Samsung School aplikacija u 45 minutaSamsung School aplikacija u 45 minuta
Samsung School aplikacija u 45 minuta
 
Audience Research
Audience Research Audience Research
Audience Research
 
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...
Glasgow university funds for academic business collaboration, Elwod Vogt, Uni...
 
Bodies and Buildings NYU ITP 10 20 2014
Bodies and Buildings NYU ITP 10 20 2014Bodies and Buildings NYU ITP 10 20 2014
Bodies and Buildings NYU ITP 10 20 2014
 
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...Challenges, Workflows, and Insights in the Collaboration to Preserve America'...
Challenges, Workflows, and Insights in the Collaboration to Preserve America'...
 
MENA Purposeful Market - Product Strategy for 2014
MENA Purposeful Market - Product Strategy for 2014MENA Purposeful Market - Product Strategy for 2014
MENA Purposeful Market - Product Strategy for 2014
 
Spott invitation herremode_work_seminar0515
Spott invitation herremode_work_seminar0515Spott invitation herremode_work_seminar0515
Spott invitation herremode_work_seminar0515
 
St patricks day
St patricks daySt patricks day
St patricks day
 
Photo contest picts
Photo contest pictsPhoto contest picts
Photo contest picts
 
Assignment guide spring 2015
Assignment guide spring 2015Assignment guide spring 2015
Assignment guide spring 2015
 
Jeff kershner showrooming ppt
Jeff kershner showrooming pptJeff kershner showrooming ppt
Jeff kershner showrooming ppt
 
проект юніор дослідник ліза, мілана
проект юніор дослідник ліза, міланапроект юніор дослідник ліза, мілана
проект юніор дослідник ліза, мілана
 
Hal hal yang mempengaruhi kepuasan seorang professional
Hal hal yang mempengaruhi kepuasan seorang professionalHal hal yang mempengaruhi kepuasan seorang professional
Hal hal yang mempengaruhi kepuasan seorang professional
 
Fungsi pengendalian
Fungsi pengendalianFungsi pengendalian
Fungsi pengendalian
 
Mishpatim group 3 ls
Mishpatim   group 3 lsMishpatim   group 3 ls
Mishpatim group 3 ls
 
Week 4 sukkot-group 2
Week 4 sukkot-group 2Week 4 sukkot-group 2
Week 4 sukkot-group 2
 

Similar a khelchandra project on ai

Brief Introduction About Topological Interference Management (TIM)
Brief Introduction About Topological Interference Management (TIM)Brief Introduction About Topological Interference Management (TIM)
Brief Introduction About Topological Interference Management (TIM)Pei-Che Chang
 
Post mission analysis noise reduction
Post mission analysis noise reductionPost mission analysis noise reduction
Post mission analysis noise reductionrohit baghel
 
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM NITISH K
 
Robot navigation in unknown environment with obstacle recognition using laser...
Robot navigation in unknown environment with obstacle recognition using laser...Robot navigation in unknown environment with obstacle recognition using laser...
Robot navigation in unknown environment with obstacle recognition using laser...IJECEIAES
 
System Monitoring
System MonitoringSystem Monitoring
System Monitoringbutest
 
Presentation on SOM
Presentation on SOMPresentation on SOM
Presentation on SOMArchiLab 7
 
Dynamic Path Planning
Dynamic Path PlanningDynamic Path Planning
Dynamic Path Planningdare2kreate
 
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNING
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNINGARTIFICIAL-NEURAL-NETWORKMACHINELEARNING
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNINGmohanapriyastp
 
Elements of Statistical Learning 読み会 第2章
Elements of Statistical Learning 読み会 第2章Elements of Statistical Learning 読み会 第2章
Elements of Statistical Learning 読み会 第2章Tsuyoshi Sakama
 
Deep learning: Mathematical Perspective
Deep learning: Mathematical PerspectiveDeep learning: Mathematical Perspective
Deep learning: Mathematical PerspectiveYounusS2
 
New microsoft office power point presentation
New microsoft office power point presentationNew microsoft office power point presentation
New microsoft office power point presentationayushdewan
 
Simulation of Crowd Evacuation scenarios using NetLogo
Simulation of Crowd Evacuation scenarios using NetLogoSimulation of Crowd Evacuation scenarios using NetLogo
Simulation of Crowd Evacuation scenarios using NetLogoFederico D'Amato
 
Artificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot NavigationArtificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot NavigationMithun Chowdhury
 

Similar a khelchandra project on ai (20)

Brief Introduction About Topological Interference Management (TIM)
Brief Introduction About Topological Interference Management (TIM)Brief Introduction About Topological Interference Management (TIM)
Brief Introduction About Topological Interference Management (TIM)
 
Post mission analysis noise reduction
Post mission analysis noise reductionPost mission analysis noise reduction
Post mission analysis noise reduction
 
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM
DESIGN AND IMPLEMENTATION OF PATH PLANNING ALGORITHM
 
Robot navigation in unknown environment with obstacle recognition using laser...
Robot navigation in unknown environment with obstacle recognition using laser...Robot navigation in unknown environment with obstacle recognition using laser...
Robot navigation in unknown environment with obstacle recognition using laser...
 
NN-Ch2.PDF
NN-Ch2.PDFNN-Ch2.PDF
NN-Ch2.PDF
 
System Monitoring
System MonitoringSystem Monitoring
System Monitoring
 
Presentation on SOM
Presentation on SOMPresentation on SOM
Presentation on SOM
 
Dynamic Path Planning
Dynamic Path PlanningDynamic Path Planning
Dynamic Path Planning
 
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNING
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNINGARTIFICIAL-NEURAL-NETWORKMACHINELEARNING
ARTIFICIAL-NEURAL-NETWORKMACHINELEARNING
 
Elements of Statistical Learning 読み会 第2章
Elements of Statistical Learning 読み会 第2章Elements of Statistical Learning 読み会 第2章
Elements of Statistical Learning 読み会 第2章
 
Deep learning: Mathematical Perspective
Deep learning: Mathematical PerspectiveDeep learning: Mathematical Perspective
Deep learning: Mathematical Perspective
 
New microsoft office power point presentation
New microsoft office power point presentationNew microsoft office power point presentation
New microsoft office power point presentation
 
Simulation of Crowd Evacuation scenarios using NetLogo
Simulation of Crowd Evacuation scenarios using NetLogoSimulation of Crowd Evacuation scenarios using NetLogo
Simulation of Crowd Evacuation scenarios using NetLogo
 
ann-ics320Part4.ppt
ann-ics320Part4.pptann-ics320Part4.ppt
ann-ics320Part4.ppt
 
ann-ics320Part4.ppt
ann-ics320Part4.pptann-ics320Part4.ppt
ann-ics320Part4.ppt
 
Glowworm Swarm Optimisation
Glowworm Swarm OptimisationGlowworm Swarm Optimisation
Glowworm Swarm Optimisation
 
Lec3
Lec3Lec3
Lec3
 
Circuitanlys2
Circuitanlys2Circuitanlys2
Circuitanlys2
 
Artificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot NavigationArtificial Neural Network based Mobile Robot Navigation
Artificial Neural Network based Mobile Robot Navigation
 
Mk slides.ppt
Mk slides.pptMk slides.ppt
Mk slides.ppt
 

Último

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESmohitsingh558521
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Generative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersGenerative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersRaghuram Pandurangan
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 

Último (20)

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Generative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersGenerative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information Developers
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 

khelchandra project on ai

  • 1. Thongam Khelchandra Jie Huang Information systems Department, The University of Aizu, Japan Somen Debnath Department of Information Technology, Mizoram University, India
  • 2. 1. Introduction • Problem Definition • Previous Work • Tools Used • Advantage • Diagram showing whole process 2. Path Planning using Artificial Neural Network 3. Fuzzy Logic System for Obstacle Avoidance 4. Results 5. Conclusion 2
  • 3. Problem definition  a robot with an initial location and orientation, a goal location and orientation  a set of obstacles located in workspace (static or moving)  compute a collision-free path for the robot  intelligent control of the robot which should move safely in the environment. 3
  • 4.  -   Computational geometry potential functions, roadmap methods, cell decompositions, sampling based algorithms unfeasible in real time Artificial neural network solves the problem use of parallel algorithm by ANN Hybrid system (Neuro-Fuzzy, Genetic-Fuzzy) 4
  • 5. • Artificial Neural Network - Multilayer Perceptron with BP learning algorithm - Classification task - Trained to choose a path from n set of paths • Fuzzy Logic System - FL is use for obstacle avoidance
  • 6.     The difficulties of traditional method in creating the configuration space with expensive computation are solved by using neural networks This method realizes a considerable increase in performance and speed If some of the neurons do not work due to lack of information, still the system will work and get the output the combination ANN and fuzzy system is computationally efficient by helping each other to eliminate their individual limitations.
  • 7. Schematic Diagram of the whole process FUZZY SYSTEM Distances to obstacles INPUT If all paths blocked by obstacles NEURAL NETWORK OUTPUT Collision free path
  • 8. • ANN is trained with some training samples initially • xi is the input which is the distance in n directions to the first obstacle • Vij is the weight connecting the ith input to the jth hidden neuron • wjk is the weight connecting the jth hidden neuron to the kth output neuron • ok is the output, 0 or 1 MLP Network
  • 9. TRAINING PHASE •x1, x2, x3 are inputs to ANN • if obstacle in the path, then desired output di = 0 else di = 1 • in the figure, d = [ 0, 1, 1] i • error between the actual output oi and desired output di is minimized by adjusting the connecting weights •w jk (n+1) = wjk(n) + η*δk(n)*yj(n) Robot choosing direction
  • 10. OPERATION PHASE •Use the weights vij and wjk to find the outputs • eg: oi = [0,1,0] will choose the center path • if all paths block by obstacle i,e oi = [0,0,0] then FL system is use to avoid the obstacles Path of the robot
  • 11. • At position 5, all the 3 paths are blocked by obstacles • In such situation, FL is applied All paths blocked by obstacles
  • 12. • Input 1. Variable : angle - Angle between the left obstacle edge and the robot centre Values : {small, medium, large} 2. Variable : distance - Distance between the robot and the obstacle blocking the middle path Values : {near, far, very far} 3. Variable : left_obstacle_dist - Distance between critical obstacle and nearest obstacle on the left side
  • 13. 4. Variable : right_obstacle_dist - Distance between critical obstacle and nearest obstacle on the right side Values : {near, far} • Output 1. Variable : adjustment angle - Adjustment Angle of the robot to avoid possible collisions with obstacles on left or right side of the critical obstacle Values : {small_left, normal_left, big_left, small_right, normal_right, big_right}
  • 14. • angle, distance, left_obstacle_dist, right_obstacle_dist are the input variables • adjustment angle is the output variable • the robot avoids the obstacles O’s when moving from point c • the rule base consist of 36 rules of the form if(angle == S) and (distance == F) and (left_obstacle_dist == F) and (right_obstacle_dist == F) then adjustment angle = SL Avoiding obstacles
  • 15. Rule Evaluation Calculation for degree of membership of the input values • Use Trapezoidal membership function with max-min composition T1 = (input - a) / (b - a) T2 = (d - input) / (d - c) T1 = Min(T1, Min(1, T2)) T= Max(T1, 0) 15
  • 16. Defuzzification  Weight of a rule is calculated by W = angle(angle-input) * distance(distance-input) * left_obs_dist(left_obs_dist-input) * right_obs_dist(right_obs_dist-input)  The function angle( ), distance( ), left_obs_dist( ), right_obs_dist( ) will give the value of degree of membership Actual output is calculated by equation Crisp output= [(w1 * v1) + (w2 *v2) + (w3 *v3) + (w4 *v4) +(w5 *v5) + ………......+ (wn * vn)]/ [w1+w2+w3+w4+w5+……wn]  16
  • 17.  the robot chooses the middle path for the first, second and third motion using neural network  in the fourth motion, the robot chooses the right path  from fifth to seven, it chooses the middle path  in eight motion, it chooses the left path  at the ninth motion, all the 3 paths are blocked by obstacle A  the obstacle at the ninth motion is avoided using fuzzy logic Robot path upto ninth motion
  • 18.  The values of the input variables of the fuzzy system of the robot ninth motion are 1. angle = M 2. distance = F 3. left_obstacle_dist = N 4. right_obstacle_dist = N.  The degree of membership for variable angle with linguistic value: (1) small = 0.000000 (2) medium = 0.386667 (3) large = 0.226667.  The degree of membership for variable distance with linguistic value: (1) near = 0.000000 (2) far = 0.750000 (3) very far = 0.500000.  The degree of membership for variable left_obstacle_dist with linguistic value: (1) near = 1.000000 (2) far = 0.500000.  The degree of membership for variable right_obstacle_dist with linguistic value: (1) near = 0.666667 (2) far = 0.750000. Robot reaching the goal
  • 19.       Proposed a new method of path planning of a mobile robot using ANN and Fuzzy system ANN is used to choose a path from a set of paths The fuzzy system is used when all the paths are blocked by obstacles Results show that the combination of these features is computational efficient by helping each other to eliminate their individual limitations increase in performance and speed as compared to traditional method with computational geometry Future work can be path planning in dynamic environments containing moving obstacles
  • 20. Thank you very much !