SlideShare a Scribd company logo
1 of 50
Download to read offline
TEAM IIT JODHPUR
BOSCH's Route Optimization Algorithm
INTERIIT-TECHMEET2K19
UNDERSTANING OF
PROBLEM STATEMENT
2
3
Develop a algorithm to serve the need for
finding route for Buses to Bosch Office on a
permanent bases.
4
There are some buses which reach at Bosch
office and we need to find the route of these
buses.
5
We need to find the route such that total cost
is minimized and require the minimum number
of buses.
6
We further need to assign each person a bus
to commute to office.
7
We already know location of each customer.
Solution approach-
(Exact Solution) 18
Linear Integer
Programming
9
ASSUMPTIONS
◉ There exists a path between any two parts of city.
◉ Data for each point is presnet in System.
◉ Maximimum number of buses available are bounded by N.
◉ There is are N imagirary passangers at DEPOT.
10
11
is a Boolean Variable it is 1 if and only if bus b goes to point j from point
i in rth step else it is 0.
denotes the member of distance matrix i,j
12
EACH BUS MUST START !!!
13
14
WHAT IS NUMBER OF PEOPLE IN EACH BUS?
15
denotes the number of passengers in bus b.
16
FINALLY EACH BUS MUST REACH DEPOT
17
18
EACH PERSON CAN TAKE ONLY 1 BUS
19
20
EACH UNUSED BUS DIRECTLY REACHES THE
DEPOT
21
22
OBVIOUSLY NUMBER OF PASSANGERS IN EACH
VECHICLE MUST BE LESS THAN ITS CAPACITY
23
24
BUSSES DO NOT TELEPORT!!!!
25
26
Time interval on Running of Busses
27
28
OBJECTIVE TO MINIMIZE
29
min(α×Total Distance +
β×(N−Number of Busses Not
Used))
Evolving Solutions !!
A heuristic
30
31
The Fittest Survives!!!!
32
The fitness function determines how fit an individual is (the ability
of an individual to compete with other individuals). It gives a fitness
score to each individual. The probability that an individual will be
selected for reproduction is based on its fitness score.
Crossover
33
Mutation
34
Reinforcement Learning
-learn from your mistakes
35
Overview of Reinforcement Learning
◉ Based on Markov Decision Process mathematical framework.
◉ Consist of agent which takes certain actions in the
environment according to a policy and gets reward or
punishment for a certain action.
◉ The policy function is optimized by training over and over
again through the process of policy gradient descent.
36
Heuristic Solution – Reinforcement Learning
◉ NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT
LEARNING –
Irwan Bello , Hieu Pham , Quoc V. Le, Mohammad Norouzi, Samy Bengio
37
Overview of Neural Combinatorial Optimization with
Reinforcement Learning
◉ This paper presents a framework to tackle combinatorial
optimization problems using neural network and
reinforcement learning.
◉ Solves a TSP that given a set of city coordinates predicts a
distribution over different city permutations.
◉ Using negative tour length as the reward function and
optimize the network using policy gradient method.
38
Overview of Neural Combinatorial Optimization with
Reinforcement Learning
◉ Supervised learning is not applicable to combinatorial
optimization problem because one does not have access to
optimal labels.
◉ RL is based on exploration and learning in an environment.
39
Neural Network Architecture for TSP
◉ Given an input graph represented as a sequence of n cities in
a two dimensional space s={xi}n. Total length is given by
below equation which is also the loss function of the neural
network.
40
Network Architecture-Pointer Network
◉ Using pointer network allows model to effectively point to a
specific position in the input sequence .
◉ Pointer network consist of an encoder network which
transforms input into a predicted sequence.
41
Algorithm for training
42
Network Optimization using Policy gradient
◉ Training a neural network involves using a supervised loss
function which involves the difference between predicted
path and the path found by policy function.
◉ Thus the model gets trained from the policy function of RL as
the training set and learns to find a TSP given a set of input.
43
Reinforcement Learning + Neural Network for VRP Problem
◉ Modifying the Bello et. al. paper for solving VRP Problem.
◉ Using the pointer Network model proposed by Bello to use it
in the VRP model.
44
Our solution for solving Vehicle Routing Problem
◉ We represent each state by a sequence of tuple {xi(t)=(si,di(t)},
where s(i) are the distance coordinates and di(t) is the
demand at point i at time t. set of all inputs is denoted by X(t) .
◉ We start from an arbitrary input X0 and at every step, our
pointer model predicts an output y0 of the next customer to
be picked.
45
Our solution for solving Vehicle Routing Problem
◉ We are interested in finding a stochastic policy pi which generates a
sequence Y in such a way which minimizes a loss while satisfying the
problem constraint.
◉ After training the bus over an environment, We find the policy
function pi and then use that policy function to train out network
model for predicting the optimal path.
◉ Using Reinforcement Learning in VRP involves multiple agents acting
on an environment optimizing the total distance covered.
46
Results after training over DGX2 for 10 million cycles
47
Algorithm Comparison
48
Time on
vpr10
Time on
vpr50
Time on
vpr100
Training
Time
Accuracy
Integer
Programm
ing
5 minutes 54 hours Approx.
300 days
Nil 100%
Genetic
Programm
ing
1 min 1.5
minutes
2 minutes Nil 20%
Reinforce
ment
Learning
0.1 min 0.2 min 0.5 min 6 hours 61%
Conclusion
◉ We finally propose 3 solutions for solving the required problem.
◉ The algorithm can be chosen depending on the given dataset, test time,
training time, hardware etc.
◉ Integer Programming solution is NP-Hard hence takes exponential time.
◉ Hence , for real life application it is important to develop a heuristic
solution .
◉ Genetic Algorithms looks for best possible solution through the principle
of evolution.
◉ Reinforcement learning helps create a policy function which helps in
training a neural network for predicting outcome.
49
THANKS!
Any questions?
50

More Related Content

What's hot

Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...journalBEEI
 
2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrasesJAEMINJEONG5
 
Travelling Salesman Problem
Travelling Salesman ProblemTravelling Salesman Problem
Travelling Salesman ProblemShikha Gupta
 
M.sc. presentation t.bagheri fashkhami
M.sc. presentation t.bagheri fashkhamiM.sc. presentation t.bagheri fashkhami
M.sc. presentation t.bagheri fashkhamitaherbagherif
 
Evolving Universal Hash Function using Genetic Algorithms
Evolving Universal Hash Function using Genetic AlgorithmsEvolving Universal Hash Function using Genetic Algorithms
Evolving Universal Hash Function using Genetic AlgorithmsMustafa Safdari
 
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITION
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITIONSEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITION
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITIONcscpconf
 
Solving the traveling salesman problem by genetic algorithm
Solving the traveling salesman problem by genetic algorithmSolving the traveling salesman problem by genetic algorithm
Solving the traveling salesman problem by genetic algorithmAlex Bidanets
 
Guided image filter
Guided image filterGuided image filter
Guided image filterssuser456ad6
 
Performance analysis of image compression using fuzzy logic algorithm
Performance analysis of image compression using fuzzy logic algorithmPerformance analysis of image compression using fuzzy logic algorithm
Performance analysis of image compression using fuzzy logic algorithmsipij
 
Random Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural NetworksRandom Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural Networksjoisino
 
Fast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a TreeFast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a Treejoisino
 
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...IJERA Editor
 
1-s2.0-S092523121401087X-main
1-s2.0-S092523121401087X-main1-s2.0-S092523121401087X-main
1-s2.0-S092523121401087X-mainPraveen Jesudhas
 
Reducting Power Dissipation in Fir Filter: an Analysis
Reducting Power Dissipation in Fir Filter: an AnalysisReducting Power Dissipation in Fir Filter: an Analysis
Reducting Power Dissipation in Fir Filter: an AnalysisCSCJournals
 
Object Elimination and Reconstruction Using an Effective Inpainting Method
Object Elimination and Reconstruction Using an Effective Inpainting MethodObject Elimination and Reconstruction Using an Effective Inpainting Method
Object Elimination and Reconstruction Using an Effective Inpainting MethodIOSR Journals
 
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...IJERA Editor
 
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...A Combined Voice Activity Detector Based On Singular Value Decomposition and ...
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...CSCJournals
 

What's hot (20)

Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...
 
2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases
 
Travelling Salesman Problem
Travelling Salesman ProblemTravelling Salesman Problem
Travelling Salesman Problem
 
M.sc. presentation t.bagheri fashkhami
M.sc. presentation t.bagheri fashkhamiM.sc. presentation t.bagheri fashkhami
M.sc. presentation t.bagheri fashkhami
 
D111823
D111823D111823
D111823
 
Evolving Universal Hash Function using Genetic Algorithms
Evolving Universal Hash Function using Genetic AlgorithmsEvolving Universal Hash Function using Genetic Algorithms
Evolving Universal Hash Function using Genetic Algorithms
 
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITION
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITIONSEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITION
SEARCH TIME REDUCTION USING HIDDEN MARKOV MODELS FOR ISOLATED DIGIT RECOGNITION
 
Lecture16 xing
Lecture16 xingLecture16 xing
Lecture16 xing
 
Solving the traveling salesman problem by genetic algorithm
Solving the traveling salesman problem by genetic algorithmSolving the traveling salesman problem by genetic algorithm
Solving the traveling salesman problem by genetic algorithm
 
Guided image filter
Guided image filterGuided image filter
Guided image filter
 
Performance analysis of image compression using fuzzy logic algorithm
Performance analysis of image compression using fuzzy logic algorithmPerformance analysis of image compression using fuzzy logic algorithm
Performance analysis of image compression using fuzzy logic algorithm
 
Random Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural NetworksRandom Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural Networks
 
Fast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a TreeFast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a Tree
 
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...
Compressive Sensing in Speech from LPC using Gradient Projection for Sparse R...
 
1-s2.0-S092523121401087X-main
1-s2.0-S092523121401087X-main1-s2.0-S092523121401087X-main
1-s2.0-S092523121401087X-main
 
Reducting Power Dissipation in Fir Filter: an Analysis
Reducting Power Dissipation in Fir Filter: an AnalysisReducting Power Dissipation in Fir Filter: an Analysis
Reducting Power Dissipation in Fir Filter: an Analysis
 
Object Elimination and Reconstruction Using an Effective Inpainting Method
Object Elimination and Reconstruction Using an Effective Inpainting MethodObject Elimination and Reconstruction Using an Effective Inpainting Method
Object Elimination and Reconstruction Using an Effective Inpainting Method
 
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...
 
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...A Combined Voice Activity Detector Based On Singular Value Decomposition and ...
A Combined Voice Activity Detector Based On Singular Value Decomposition and ...
 
H046014853
H046014853H046014853
H046014853
 

Similar to Inter IIT Tech Meet 2k19, IIT Jodhpur

自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用Ryo Iwaki
 
Black-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX modelBlack-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX modelIJECEIAES
 
Mb0048 operations research
Mb0048 operations researchMb0048 operations research
Mb0048 operations researchsmumbahelp
 
Keynote at IWLS 2017
Keynote at IWLS 2017Keynote at IWLS 2017
Keynote at IWLS 2017Manish Pandey
 
Combinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learningCombinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learning민재 정
 
Reinforcement learning
Reinforcement learningReinforcement learning
Reinforcement learningDongHyun Kwak
 
Trajectory Transformer.pptx
Trajectory Transformer.pptxTrajectory Transformer.pptx
Trajectory Transformer.pptxSeungeon Baek
 
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...Amir Ziai
 
Reinforcement Learning
Reinforcement LearningReinforcement Learning
Reinforcement LearningDongHyun Kwak
 
Machine learning Module-2, 6th Semester Elective
Machine learning Module-2, 6th Semester ElectiveMachine learning Module-2, 6th Semester Elective
Machine learning Module-2, 6th Semester ElectiveMayuraD1
 
Lexically constrained decoding for sequence generation using grid beam search
Lexically constrained decoding for sequence generation using grid beam searchLexically constrained decoding for sequence generation using grid beam search
Lexically constrained decoding for sequence generation using grid beam searchSatoru Katsumata
 
Introduction of Deep Reinforcement Learning
Introduction of Deep Reinforcement LearningIntroduction of Deep Reinforcement Learning
Introduction of Deep Reinforcement LearningNAVER Engineering
 
Optimal buffer allocation in
Optimal buffer allocation inOptimal buffer allocation in
Optimal buffer allocation incsandit
 
Introduction to algorithmic aspect of auction theory
Introduction to algorithmic aspect of auction theoryIntroduction to algorithmic aspect of auction theory
Introduction to algorithmic aspect of auction theoryAbner Chih Yi Huang
 
Unsupervised Feature Learning
Unsupervised Feature LearningUnsupervised Feature Learning
Unsupervised Feature LearningAmgad Muhammad
 
Mb0048 operations research
Mb0048 operations researchMb0048 operations research
Mb0048 operations researchsmumbahelp
 
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHM
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHMJOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHM
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHMmailjkb
 
Pedestrian dead reckoning indoor localization based on os-elm
Pedestrian dead reckoning indoor localization based on os-elmPedestrian dead reckoning indoor localization based on os-elm
Pedestrian dead reckoning indoor localization based on os-elmAlwin Poulose
 
WK3 - Multi Layer Perceptron networks of neural multilayer perceptron
WK3 - Multi Layer Perceptron networks of neural multilayer perceptronWK3 - Multi Layer Perceptron networks of neural multilayer perceptron
WK3 - Multi Layer Perceptron networks of neural multilayer perceptronjohnberkmanst
 

Similar to Inter IIT Tech Meet 2k19, IIT Jodhpur (20)

自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用
 
Black-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX modelBlack-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX model
 
Mb0048 operations research
Mb0048 operations researchMb0048 operations research
Mb0048 operations research
 
Keynote at IWLS 2017
Keynote at IWLS 2017Keynote at IWLS 2017
Keynote at IWLS 2017
 
Combinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learningCombinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learning
 
Reinforcement learning
Reinforcement learningReinforcement learning
Reinforcement learning
 
Trajectory Transformer.pptx
Trajectory Transformer.pptxTrajectory Transformer.pptx
Trajectory Transformer.pptx
 
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...
On the Performance of the Pareto Set Pursuing (PSP) Method for Mixed-Variable...
 
Reinforcement Learning
Reinforcement LearningReinforcement Learning
Reinforcement Learning
 
Machine learning Module-2, 6th Semester Elective
Machine learning Module-2, 6th Semester ElectiveMachine learning Module-2, 6th Semester Elective
Machine learning Module-2, 6th Semester Elective
 
Genetic Algorithms
Genetic AlgorithmsGenetic Algorithms
Genetic Algorithms
 
Lexically constrained decoding for sequence generation using grid beam search
Lexically constrained decoding for sequence generation using grid beam searchLexically constrained decoding for sequence generation using grid beam search
Lexically constrained decoding for sequence generation using grid beam search
 
Introduction of Deep Reinforcement Learning
Introduction of Deep Reinforcement LearningIntroduction of Deep Reinforcement Learning
Introduction of Deep Reinforcement Learning
 
Optimal buffer allocation in
Optimal buffer allocation inOptimal buffer allocation in
Optimal buffer allocation in
 
Introduction to algorithmic aspect of auction theory
Introduction to algorithmic aspect of auction theoryIntroduction to algorithmic aspect of auction theory
Introduction to algorithmic aspect of auction theory
 
Unsupervised Feature Learning
Unsupervised Feature LearningUnsupervised Feature Learning
Unsupervised Feature Learning
 
Mb0048 operations research
Mb0048 operations researchMb0048 operations research
Mb0048 operations research
 
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHM
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHMJOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHM
JOB SCHEDULING USING ANT COLONY OPTIMIZATION ALGORITHM
 
Pedestrian dead reckoning indoor localization based on os-elm
Pedestrian dead reckoning indoor localization based on os-elmPedestrian dead reckoning indoor localization based on os-elm
Pedestrian dead reckoning indoor localization based on os-elm
 
WK3 - Multi Layer Perceptron networks of neural multilayer perceptron
WK3 - Multi Layer Perceptron networks of neural multilayer perceptronWK3 - Multi Layer Perceptron networks of neural multilayer perceptron
WK3 - Multi Layer Perceptron networks of neural multilayer perceptron
 

More from niveditJain

BTP Learning Outcome.pdf
BTP Learning Outcome.pdfBTP Learning Outcome.pdf
BTP Learning Outcome.pdfniveditJain
 
BTP Presentation.pdf
BTP Presentation.pdfBTP Presentation.pdf
BTP Presentation.pdfniveditJain
 
Super Resolution with OCR Optimization
Super Resolution with OCR OptimizationSuper Resolution with OCR Optimization
Super Resolution with OCR OptimizationniveditJain
 
Super Resolution with OCR Optimization
Super Resolution with OCR OptimizationSuper Resolution with OCR Optimization
Super Resolution with OCR OptimizationniveditJain
 
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur niveditJain
 
Analysis Of MGNREGA on people of Mandor Region on Caste Basis
Analysis Of MGNREGA on people of Mandor Region on Caste BasisAnalysis Of MGNREGA on people of Mandor Region on Caste Basis
Analysis Of MGNREGA on people of Mandor Region on Caste BasisniveditJain
 
Essentialize Extreme Programming practices
Essentialize Extreme Programming practicesEssentialize Extreme Programming practices
Essentialize Extreme Programming practicesniveditJain
 
Context Free Grammar
Context Free GrammarContext Free Grammar
Context Free GrammarniveditJain
 
NFA DFA Equivalence theorem
NFA DFA Equivalence theorem NFA DFA Equivalence theorem
NFA DFA Equivalence theorem niveditJain
 
Maximum weighted edge biclique problem on bipartite graphs
Maximum weighted edge biclique problem on bipartite graphsMaximum weighted edge biclique problem on bipartite graphs
Maximum weighted edge biclique problem on bipartite graphsniveditJain
 
Tesla aquisition of maxwell
Tesla aquisition of maxwellTesla aquisition of maxwell
Tesla aquisition of maxwellniveditJain
 
Literature club Introduction 2k19
Literature club Introduction 2k19Literature club Introduction 2k19
Literature club Introduction 2k19niveditJain
 
Jargons eCell IIT Jodhpur
Jargons eCell IIT JodhpurJargons eCell IIT Jodhpur
Jargons eCell IIT JodhpurniveditJain
 

More from niveditJain (17)

BTP Learning Outcome.pdf
BTP Learning Outcome.pdfBTP Learning Outcome.pdf
BTP Learning Outcome.pdf
 
BTP Presentation.pdf
BTP Presentation.pdfBTP Presentation.pdf
BTP Presentation.pdf
 
BTP Report.pdf
BTP Report.pdfBTP Report.pdf
BTP Report.pdf
 
Project muZiK
Project muZiKProject muZiK
Project muZiK
 
Bucket Sort
Bucket SortBucket Sort
Bucket Sort
 
Super Resolution with OCR Optimization
Super Resolution with OCR OptimizationSuper Resolution with OCR Optimization
Super Resolution with OCR Optimization
 
Super Resolution with OCR Optimization
Super Resolution with OCR OptimizationSuper Resolution with OCR Optimization
Super Resolution with OCR Optimization
 
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur
Caste Wise Analysis of MGNREGA in Mandor Block of Jodhpur
 
Analysis Of MGNREGA on people of Mandor Region on Caste Basis
Analysis Of MGNREGA on people of Mandor Region on Caste BasisAnalysis Of MGNREGA on people of Mandor Region on Caste Basis
Analysis Of MGNREGA on people of Mandor Region on Caste Basis
 
Essentialize Extreme Programming practices
Essentialize Extreme Programming practicesEssentialize Extreme Programming practices
Essentialize Extreme Programming practices
 
Context Free Grammar
Context Free GrammarContext Free Grammar
Context Free Grammar
 
NFA DFA Equivalence theorem
NFA DFA Equivalence theorem NFA DFA Equivalence theorem
NFA DFA Equivalence theorem
 
Maximum weighted edge biclique problem on bipartite graphs
Maximum weighted edge biclique problem on bipartite graphsMaximum weighted edge biclique problem on bipartite graphs
Maximum weighted edge biclique problem on bipartite graphs
 
Carmeet
CarmeetCarmeet
Carmeet
 
Tesla aquisition of maxwell
Tesla aquisition of maxwellTesla aquisition of maxwell
Tesla aquisition of maxwell
 
Literature club Introduction 2k19
Literature club Introduction 2k19Literature club Introduction 2k19
Literature club Introduction 2k19
 
Jargons eCell IIT Jodhpur
Jargons eCell IIT JodhpurJargons eCell IIT Jodhpur
Jargons eCell IIT Jodhpur
 

Recently uploaded

Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...
Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...
Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...EADTU
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文中 央社
 
e-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi Rajagopale-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi RajagopalEADTU
 
The Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDFThe Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDFVivekanand Anglo Vedic Academy
 
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptxAnalyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptxLimon Prince
 
MOOD STABLIZERS DRUGS.pptx
MOOD     STABLIZERS           DRUGS.pptxMOOD     STABLIZERS           DRUGS.pptx
MOOD STABLIZERS DRUGS.pptxPoojaSen20
 
Improved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio AppImproved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio AppCeline George
 
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...Nguyen Thanh Tu Collection
 
SURVEY I created for uni project research
SURVEY I created for uni project researchSURVEY I created for uni project research
SURVEY I created for uni project researchCaitlinCummins3
 
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUM
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUMDEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUM
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUMELOISARIVERA8
 
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...Nguyen Thanh Tu Collection
 
How To Create Editable Tree View in Odoo 17
How To Create Editable Tree View in Odoo 17How To Create Editable Tree View in Odoo 17
How To Create Editable Tree View in Odoo 17Celine George
 
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjjStl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjjMohammed Sikander
 
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSAnaAcapella
 
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading RoomSternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading RoomSean M. Fox
 
ANTI PARKISON DRUGS.pptx
ANTI         PARKISON          DRUGS.pptxANTI         PARKISON          DRUGS.pptx
ANTI PARKISON DRUGS.pptxPoojaSen20
 
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...Nguyen Thanh Tu Collection
 
Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...EduSkills OECD
 

Recently uploaded (20)

OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...
 
Supporting Newcomer Multilingual Learners
Supporting Newcomer  Multilingual LearnersSupporting Newcomer  Multilingual Learners
Supporting Newcomer Multilingual Learners
 
Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...
Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...
Transparency, Recognition and the role of eSealing - Ildiko Mazar and Koen No...
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
 
e-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi Rajagopale-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi Rajagopal
 
The Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDFThe Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDF
 
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptxAnalyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
 
MOOD STABLIZERS DRUGS.pptx
MOOD     STABLIZERS           DRUGS.pptxMOOD     STABLIZERS           DRUGS.pptx
MOOD STABLIZERS DRUGS.pptx
 
Improved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio AppImproved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio App
 
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
 
SURVEY I created for uni project research
SURVEY I created for uni project researchSURVEY I created for uni project research
SURVEY I created for uni project research
 
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUM
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUMDEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUM
DEMONSTRATION LESSON IN ENGLISH 4 MATATAG CURRICULUM
 
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
 
How To Create Editable Tree View in Odoo 17
How To Create Editable Tree View in Odoo 17How To Create Editable Tree View in Odoo 17
How To Create Editable Tree View in Odoo 17
 
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjjStl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjj
 
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
 
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading RoomSternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
 
ANTI PARKISON DRUGS.pptx
ANTI         PARKISON          DRUGS.pptxANTI         PARKISON          DRUGS.pptx
ANTI PARKISON DRUGS.pptx
 
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
TỔNG HỢP HƠN 100 ĐỀ THI THỬ TỐT NGHIỆP THPT TOÁN 2024 - TỪ CÁC TRƯỜNG, TRƯỜNG...
 
Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...
 

Inter IIT Tech Meet 2k19, IIT Jodhpur

  • 1. TEAM IIT JODHPUR BOSCH's Route Optimization Algorithm INTERIIT-TECHMEET2K19
  • 3. 3 Develop a algorithm to serve the need for finding route for Buses to Bosch Office on a permanent bases.
  • 4. 4 There are some buses which reach at Bosch office and we need to find the route of these buses.
  • 5. 5 We need to find the route such that total cost is minimized and require the minimum number of buses.
  • 6. 6 We further need to assign each person a bus to commute to office.
  • 7. 7 We already know location of each customer.
  • 10. ASSUMPTIONS ◉ There exists a path between any two parts of city. ◉ Data for each point is presnet in System. ◉ Maximimum number of buses available are bounded by N. ◉ There is are N imagirary passangers at DEPOT. 10
  • 11. 11 is a Boolean Variable it is 1 if and only if bus b goes to point j from point i in rth step else it is 0. denotes the member of distance matrix i,j
  • 12. 12 EACH BUS MUST START !!!
  • 13. 13
  • 14. 14 WHAT IS NUMBER OF PEOPLE IN EACH BUS?
  • 15. 15 denotes the number of passengers in bus b.
  • 16. 16 FINALLY EACH BUS MUST REACH DEPOT
  • 17. 17
  • 18. 18 EACH PERSON CAN TAKE ONLY 1 BUS
  • 19. 19
  • 20. 20 EACH UNUSED BUS DIRECTLY REACHES THE DEPOT
  • 21. 21
  • 22. 22 OBVIOUSLY NUMBER OF PASSANGERS IN EACH VECHICLE MUST BE LESS THAN ITS CAPACITY
  • 23. 23
  • 24. 24 BUSSES DO NOT TELEPORT!!!!
  • 25. 25
  • 26. 26 Time interval on Running of Busses
  • 27. 27
  • 30. Evolving Solutions !! A heuristic 30
  • 31. 31
  • 32. The Fittest Survives!!!! 32 The fitness function determines how fit an individual is (the ability of an individual to compete with other individuals). It gives a fitness score to each individual. The probability that an individual will be selected for reproduction is based on its fitness score.
  • 36. Overview of Reinforcement Learning ◉ Based on Markov Decision Process mathematical framework. ◉ Consist of agent which takes certain actions in the environment according to a policy and gets reward or punishment for a certain action. ◉ The policy function is optimized by training over and over again through the process of policy gradient descent. 36
  • 37. Heuristic Solution – Reinforcement Learning ◉ NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT LEARNING – Irwan Bello , Hieu Pham , Quoc V. Le, Mohammad Norouzi, Samy Bengio 37
  • 38. Overview of Neural Combinatorial Optimization with Reinforcement Learning ◉ This paper presents a framework to tackle combinatorial optimization problems using neural network and reinforcement learning. ◉ Solves a TSP that given a set of city coordinates predicts a distribution over different city permutations. ◉ Using negative tour length as the reward function and optimize the network using policy gradient method. 38
  • 39. Overview of Neural Combinatorial Optimization with Reinforcement Learning ◉ Supervised learning is not applicable to combinatorial optimization problem because one does not have access to optimal labels. ◉ RL is based on exploration and learning in an environment. 39
  • 40. Neural Network Architecture for TSP ◉ Given an input graph represented as a sequence of n cities in a two dimensional space s={xi}n. Total length is given by below equation which is also the loss function of the neural network. 40
  • 41. Network Architecture-Pointer Network ◉ Using pointer network allows model to effectively point to a specific position in the input sequence . ◉ Pointer network consist of an encoder network which transforms input into a predicted sequence. 41
  • 43. Network Optimization using Policy gradient ◉ Training a neural network involves using a supervised loss function which involves the difference between predicted path and the path found by policy function. ◉ Thus the model gets trained from the policy function of RL as the training set and learns to find a TSP given a set of input. 43
  • 44. Reinforcement Learning + Neural Network for VRP Problem ◉ Modifying the Bello et. al. paper for solving VRP Problem. ◉ Using the pointer Network model proposed by Bello to use it in the VRP model. 44
  • 45. Our solution for solving Vehicle Routing Problem ◉ We represent each state by a sequence of tuple {xi(t)=(si,di(t)}, where s(i) are the distance coordinates and di(t) is the demand at point i at time t. set of all inputs is denoted by X(t) . ◉ We start from an arbitrary input X0 and at every step, our pointer model predicts an output y0 of the next customer to be picked. 45
  • 46. Our solution for solving Vehicle Routing Problem ◉ We are interested in finding a stochastic policy pi which generates a sequence Y in such a way which minimizes a loss while satisfying the problem constraint. ◉ After training the bus over an environment, We find the policy function pi and then use that policy function to train out network model for predicting the optimal path. ◉ Using Reinforcement Learning in VRP involves multiple agents acting on an environment optimizing the total distance covered. 46
  • 47. Results after training over DGX2 for 10 million cycles 47
  • 48. Algorithm Comparison 48 Time on vpr10 Time on vpr50 Time on vpr100 Training Time Accuracy Integer Programm ing 5 minutes 54 hours Approx. 300 days Nil 100% Genetic Programm ing 1 min 1.5 minutes 2 minutes Nil 20% Reinforce ment Learning 0.1 min 0.2 min 0.5 min 6 hours 61%
  • 49. Conclusion ◉ We finally propose 3 solutions for solving the required problem. ◉ The algorithm can be chosen depending on the given dataset, test time, training time, hardware etc. ◉ Integer Programming solution is NP-Hard hence takes exponential time. ◉ Hence , for real life application it is important to develop a heuristic solution . ◉ Genetic Algorithms looks for best possible solution through the principle of evolution. ◉ Reinforcement learning helps create a policy function which helps in training a neural network for predicting outcome. 49