Specialization in Robotics and Machine Learning

Sr. No. Subjects Semester Credit

1 Fundamentals of Robotics 3rd 3
2 Artificial Intelligence 4th 3
3 Robot Sensing and Vision 5th 3
4 Introduction to Machine Learning 6th 2
5 Machine Learning using Python Lab 6th 1
6 Machine Learning with Robotics 7th 3
7 Automation in Manufacturing Systems 8th 3
 FUNDAMENTALS OF ROBOTICS L T P C

Version 1.1 Date of Approval: 3 0 0 3

Pre-requisites/ KOM, DOM, CAD, CAM &CNC

Exposure
Co-requisites

Catalog Description
In this course the concepts of definition of robots, law of robotics, robot joints, classification of
robots, robot architecture, robot transformation, direct and inverse kinematics, tool configuration
of robots are discussed in detail. Concept of different types of grippers, end effectors, LVDT,
robot controls and robot sensors are also discussed in detail. The aim of this course is to make
the students familiar with the fundamental knowledge of robotics.

Course Objectives
The objective of this course is to
1. Enlighten the students about the fundamentals of robotic systems.
2. Understand the basics of robot, Robot Transformations and Sensors, Micro/Nano robotic systems and
to program them for functioning.

Course Outcomes
On completion of this course, the students will be able to
CO1: Explain about definition of robots, law of robotics, robot joints, classification of robots,
and robot architecture.
CO2: Explain about 2D, 3D transformations- Scaling, Rotation, Translation.
CO3: Describe about link coordinates, direct kinematics and inverse kinematics.
CO4: Discuss about the types of grippers, end effectors, robot controls and robot sensors.

Blooms Number
Modules
level* of hours
MODULE 1: INTRODUCTION L1, L2 8
Robot anatomy-Definition, law of robotics, History and Terminology of Robotics-
Accuracy and repeatability of Robotics-Simple problems- Specifications of Robot-Speed
of Robot-Robot joints and links-Robot classifications-Architecture of robotic systems-
Robot Drive systems- Hydraulic, Pneumatic and Electric system.
MODULE 2: ROBOT TRANSFORMATIONS
Robot kinematics-Types- 2D, 3D Transformation-Scaling, Rotation, Translation- L1, L2 6
Homogeneous coordinates, multiple transformation-Simple problems.
MODULE 3: DIRECT& INVERSE KINEMATICS
Link coordinates D-H Representation, The ARM equation. Direct kinematic analysis for
Four axis, SCARA Robot and three, five and six axis Articulated Robots, The inverse L1, L2 8
kinematics problem, General properties of solutions. Tool configuration, Inverse
kinematics of four axis SCARA robot and three and five axis, Articulated robot.
MODULE 4: END EFFECTORS AND ROBOT CONTROLS
Mechanical grippers-Slider crank mechanism, Screw type, Rotary actuators, cam type-
Magnetic grippers, Vacuum grippers-Air operated grippers-Gripper force analysis-
L1, L2 8
Gripper design-Simple problems-Robot controls-Point to point control, Continuous path
control, Intelligent robot-Control system for robot jointControl actions-Feedback devices-
Encoder, Resolver, LVDT-Motion Interpolations-Adaptive control.
MODULE 5: ROBOTICS SENSORS
Sensors in robot – Touch sensors,Tactile sensor, Proximity and range sensors, Robotic L1, L2 6
vision sensor-Force sensor-Light sensors, Pressure sensors.
*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4:Analysis; L5:Synthesis, L6:Evaluation

Text Books
1. Craig. J. J. “Introduction to Robotics mechanics and control”, Addison- Wesley,1999.
2. S.R. Deb, Robotics Technology and flexible automation, Tata McGraw-Hill Education., 2009
3. Mikell P Groover & Nicholas G Odrey, Mitchel Weiss, Roger N Nagel, Ashish Dutta, Industrial
Robotics, Technology programming and Applications, McGraw Hill, 2012
Reference Books
1. Ganesan, V. (2017). Internal Combustion Engine, New-Delhi: Tata McGraw Hill.
2. Richard D. Klafter, Thomas .A, Chri Elewski, Michael Negin, Robotics Engineering an
Integrated Approach, Phi Learning., 2009.
3. Deb. S. R. “Robotics technology and flexible automation”, Tata McGraw Hill
publishing company limited, 1994
4. Mikell. P. Groover, “Industrial Robotics Technology”, Programming and Applications,
 McGraw Hill Co, 1995.
5. Klafter. R.D, Chmielewski.T.A. and Noggin’s., “Robot Engineering : An Integrated
Approach”, Prentice Hall of India Pvt. Ltd.,1994.

Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance
CO, PO and PSO mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO2 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO3 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO4 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

1: strongly related, 2: moderately related and 3: weakly related

 ARTIFICIAL INTELLIGENCE L T P C

Version 1.1 Date of Approval: 3 0 0 3

Pre-requisites/ Decision making and programming Technique

Exposure
Co-requisites

Catalog Description
In this course concept of games, theorem proving, vision and speech processing, state space
search and knowledge representation are discussed. Elementary concept of natural language and
expert system are discussed in detail. The basic aim of this course is to make the students
familiar with artificial intelligence.

Course Objective:

The objective of this course is to

1. Introduce artificial intelligence (AI) principles and approaches.

2. Develop a basic understanding of the expert system of AI.

Course Outcomes
On completion of this course, the students will be able to
CO1: Demonstrate the awareness of intelligent agents and problem solving using different
search algorithms

CO2: Interpret the use of different knowledge representation methods.

CO3: Demonstrate the use of language system in artificial intelligence.

CO4: Explain the basic of expert system and handling uncertainties.

CO5: Discuss the robot kinematics and level of robot programming.

Blooms Number
Modules
level* of hours

Module I: Problem solving and Scope of AI L1, L2 and 8

Introduction to Artificial Intelligence. Applications- Games, theorem
proving, natural language processing, vision and speech processing,
robotics, expert systems. AI techniques- search knowledge, abstraction.
State space search; Production systems, search space control: depth-first,
L3
breadth-first search. Heuristic search - Hill climbing, best-first search,
branch and bound. Problem Reduction, Constraint Satisfaction, End,
Means-End Analysis. LA* Algorithm, L(AO*) Algorithm.
.
Module II: Knowledge Representation
Knowledge Representation issues, first order predicate calculus, Horn L1, L2 and
7
Clauses, Resolution, Semantic Nets, Frames, Partitioned Nets, Procedural L3
Vs Declarative knowledge, Forward Vs Backward Reasoning.

Module III: Understanding Natural Languages

Introduction to NLP, Basics of Syntactic Processing, Basics of Semantic
Analysis, Basics of Parsing techniques, context free and transformational L1, L2 and
7
grammars, transition nets, augmented transition nets, Shanks Conceptual L3
Dependency, Scripts ,Basics of grammar free analyzers, Basics of sentence
generation, and Basics of translation.

Module IV: Expert System

Need and justification for expert systems, knowledge acquisition, Case
studies: MYCIN, R1 Learning: Concept of learning, learning automation,L1, L2 and
7
genetic algorithm, learning by inductions, neural nets. L3
Handling Uncertainties: Non-monotonic reasoning, Probabilistic
reasoning, use of certainty factors.

Module V: Introduction to Robotics

Fundamentals of Robotics, Robot Kinematics: Position Analysis, Dynamic
Analysis and Forces, Robot Programming languages & systems: L1, L2 and
7
Introduction, the three levels of robot programming, requirements of a L3
robot programming language, problems peculiar to robot programming
languages.

*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4: Analysis; L5:Synthesis, L6:Evaluation

Text & Reference books:

Text:
 E. Rich and K. Knight, “Artificial intelligence”, TMH, 2nd ed., 1992.
 N.J. Nilsson, “Principles of AI”, Narosa Publ. House, 1990.
 John J. Craig, “Introduction to Robotics”, Addison Wesley publication
 Richard D. Klafter, Thomas A. Chmielewski, Michael Negin, “Robotic Engineering – An
integrated approach”, PHI Publication
 Tsuneo Yoshikawa, “Foundations of Robotics”, PHI Publication.
Reference:
 D.W. Patterson, “Introduction to AI and Expert Systems”, PHI, 1992.
 Peter Jackson, “Introduction to Expert Systems”, AWP, M.A., 1992.
 R.J. Schalkoff, “Artificial Intelligence - an Engineering Approach”, McGraw Hill Int. Ed.,
Singapore, 1992.
 M. Sasikumar, S. Ramani, “Rule Based Expert Systems”, Narosa Publishing House, 1994.

Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance

CO, PO and PSO mapping

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO2 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO3 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO4 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

CO5 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

1: strongly related, 2: moderately related and 3: weakly related

ROBOTICS SENSING AND VISION L T P C

Version 1.1 Date of Approval: 3 0 0 3

Pre-requisites/ Fundamental of Robotics

Exposure
Co-requisites

Catalog Description
In this course the concepts of various sensors, transducers, smart & AI sensing, robot vision,
need and application of robot vision, image acquisition, picture coding techniques and different
element of image processing techniques are discussed in detail. Concept of computer controlled
robot assembly, vision sensor modules, robot programming, gripper and gripping methods are
also discussed in detail. The aim of this course is to make the students familiar with the
knowledge of robotic sensing, robotic vision and their applications.

Course Objectives
The objective of this course is to
1. Equip the students with concept of robot sensors, robot vision, need and application of
robot vision, image acquisition and processing techniques.
2. Provide an overview of computer controlled robot assembly, vision sensor modules and
robot programming.

Course Outcomes
On completion of this course, the students will be able to
CO1: Explain about concepts of transducers, smart & AI sensing and history of sensing in
robotics.
CO2: Explain definitions and working of different types of sensors and their applications.
CO3: Describe the robot vision, need, robot guidance and applications of robot vision.
CO4: Discuss the elements of image processing techniques and multisensor controlled robot
assembly.

Blooms Number
Modules
level* of hours
MODULE 1: INTRODUCTION
An Introduction to sensors and Transducers, History and definitions, Smart Sensing, AI L1, L2 6
sensing, Need of sensors in Robotics.
MODULE 2: SENSORS IN ROBOTICS
Position sensors – optical, non-optical, Velocity sensors, Accelerometers, Proximity
Sensors – Contact, non-contact, Range Sensing, touch and Slip Sensors, Force and
L1, L2 8
Torque Sensors. Different sensing variables – smell, Heat or Temperature, Humidity,
Light, Speech or Voice recognition Systems, Telepresence and related technologies,
Application of sensors
MODULE 3: VISION IN ROBTICS
The Nature of Vision- Robot vision – Need, Applications - image acquisition –
illumination techniques- Point sensor, line sensor, planar sensor, camera transfer
L1, L2 8
characteristic, Raster scan, Image capture time, volume sensors, Image representation,
picture coding techniques. Robot Control through Vision sensors, Robot vision locating
position, Robot guidance with vision system, End effector camera Sensor.
MODULE 4: ELEMENTS OF IMAGE PROCESSING TECHNIQUES
Discretization, Neighbors of a pixel-connectivity, Distance measures, Preprocessing
L1, L2 8
Neighborhood averaging, Median filtering. Smoothening of binary Images, Image
Enhancement, Histogram Equalization & Specification.
MODULE 5: MULTISENSOR CONTROLLED ROBOT ASSEMBLY
Computer control for robot assembly, Vision Sensor modules, Introduction to Robot L1, L2 6
programming, Handling, Gripper and Gripping methods, accuracy.
*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4:Analysis; L5:Synthesis, L6:Evaluation

Text Books
1. Paul W Chapman, “Smart Sensors”, an Independent Learning Module Series, 1996.
2. Richard D. Klafter, Thomas .A, Chri Elewski, Michael Negin, Robotics Engineering an
Integrated Approach, Phi Learning., 2009.
3. Mikell P Groover & Nicholas G Odrey, Mitchel Weiss, Roger N Nagel, Ashish Dutta, Industrial
Robotics,Technology programming and Applications, Tata McGraw-Hill Education, 2012.
4. Sabrie Soloman, Sensors and Control Systems in Manufacturing, McGraw-Hill Professional
Publishing, 2nd Edition, 2009.

Reference Books
1. John Iovice, “Robots, Androids and Animatrons”, Mc Graw Hill, 2003.
2. K.S. Fu, R.C. Gonzalez, C.S.G. Lee, “Robotics – Control Sensing, Vision and Intelligence”, Tata
McGrawHill Education, 2008.
Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance

CO, PO and PSO mapping

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO2 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO3 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO4 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

1: strongly related, 2: moderately related and 3: weakly related

INTRODUCTION TO MACHINE LEARNING L T P C

 2 - - 2

Pre-requisites/Exposure Basic Knowledge of Programming

Co-requisites Nil

Catalog Description

Python is a general-purpose high level programming language that is being increasingly used in
data science and in designing machine learning algorithms. This course introduces Python and its
libraries like numpy, pandas, matplotlib and explains how it can be applied to develop machine
learning algorithms that solve real world problems.

This course starts with Python language followed by machine learning and covers concepts of
python and all important concepts such as exploratory data analysis, data preprocessing, data
visualization and clustering, classification, regression and model performance evaluation etc.
This course covers all three types of machine learning algorithms including Supervise,
Unsupervised and Reinforcement learning.

Course Objectives

The objective of this course is to

 Equip the students with concepts of programming and problem solving and develop
proficiency in creating applications using the Python Programming Language.
 Provide knowledge of various types of machine learning models, its algorithms and
development of the models using Python programming language.

Course Outcomes

On completion of this course, the students will be able to

CO1: Develop programs in Python to develop algorithmic solutions to computational problems.

CO2: Manage data in python using available data structures such as string, list, and dictionary
and file handling operations.

CO3: Apply functions to decompose python program and develop modules and packages.

CO4: Preprocess and analyze data before applying suitable machine learning models.

Modules Blooms Number

 level* of hours

Module-I
Python basis: Installing Anaconda, Basics of Python: basic syntax,
interactive shell, editing, saving, and running a script. Working with
L1, L2 and
jupyter notebook, data types, operators, conditional statements, String, 6
functions, Lists, tuples, and dictionaries; basic list operators, replacing, L3
inserting, removing an element; searching and sorting lists; dictionary
literals, adding and removing keys, accessing, and replacing values;
traversing dictionaries. modules and packages.
Module-II
Arrays and Matrices: The NumPy Module, Creating Arrays and
Matrices, Copying, Arithmetic Operations, Cross product & Dot
product, Saving and Restoring, Matrix inversion, Vectorized
Functions. L1, L2 and
6
Data Visualization: The Matplotlib Module, Histograms, Bar charts L3
Density Plots, Box Plots, Scatter Plots, Heat Maps etc.
Data Frames: Pandas, loading data from different sources, Concept of
Data Frames, Working with Data frames such as selecting, filtering,
grouping, joining etc. Dealing with missing values
Preprocessing and Scaling, Different Kinds of Preprocessing
Module-III
Introduction to Machine Learning: Introduction, Applications,
Framework for developing machine learning models
Supervised Learning: Linear regression, ridge and lasso regressionL2, L3 and
Multiple linear regression, logistic regression, classification and 6
L4
regression trees, decision tree, Ensemble techniques, Support Vector
Machines, K-nearest neighbors, naive bayes classifier.
Representing Data and Engineering Features. Categorical Variables,
confusion matrix

Module-IV
Unsupervised Learning: Introduction to Clustering, k-means clustering
6
Hierarchical clustering, Dimensionality Reduction, Feature Selection,L2, L3 and
PCA, factor analysis, manifold learning. L4

*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4: Analysis; L5: Synthesis, L6: Evaluation

Text Books

1. Pilgrim, Dive, “Introduction to Python”, 3rd Edition, Apress, 2009.

2. Allen Downey, Jeffrey Elkner, Chris Meyers, “How to Think Like a Computer Scientist
Learning with Python” 2nd Edition Green Tea Press,2002.
3. Manaranjan Pradhan and U Dinesh Kumar, “Machine Learning using Python” , Wiley
Publication
 4. Andreas C. Müller & Sarah Guido “Introduction to Machine Learning using python”,Oreilly
Publications.

Reference Books

1. John V. Guttag, “Introduction to Computation and Programming using Python”, Prentice

Hall of India, 2014.
2. Mark Lutz, “Learning Python: Powerful Object-Oriented Programming‖”, Fifth Edition,
O‘Reilly, Shroff Publishers and Distributors, 2013.
3. Michale Bowles “Machine Learning in Python: Essential Techniques for Predictive
Analysis” Wiley Publication.

Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance

CO, PO and PSO mapping

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 3 2 2 -- -- -- -- -- -- -- -- 1 1 2 --

CO2 1 3 2 2 -- -- -- -- -- -- -- -- 1 1 2 --

CO3 1 3 2 1 2 -- -- -- -- -- -- -- 1 1 2 --

CO4 1 1 1 1 1 2 -- -- -- -- -- -- 1 -- 1 --

CO5 1 1 1 1 1 2 -- -- -- -- -- -- 1 -- 1 ---

1: strongly related, 2: moderately related and 3: weakly related

MACHINE LEARNING USING PYTHON LAB L T P C

Version: 2020.1 0 - 2 1
 Pre-requisites/Exposure Basic Knowledge of Programming

Co-requisites Nil

Catalog Description

Python is a language with a simple syntax, and a powerful set of libraries. It is an interpreted
language, with a rich programming environment, including a robust debugger and profiler. While
it is easy for beginners to learn, it is widely used in many scientific areas for data exploration.
This course is an introduction to the Python programming language for students without prior
programming experience. We cover data types, control flow, object-oriented programming, and
graphical user interface-driven applications. The examples and problems used in this course are
drawn from diverse areas such as text processing, simple graphics creation and image
manipulation, HTML and web programming. 

Course Objectives

The objective of this course is to

 Equip the students with concepts of programming and problem solving and develop
proficiency in creating applications using the Python Programming Language.
 Provide an overview of various control statements, data structures, object oriented
programming, packages related to image processing, graphics, event driven programming,
socket applications.

Course Outcomes

On completion of this course, the students will be able to

CO1: Explain various operators and control structures in python and their uses to develop
algorithmic solutions to simple computational problems.

CO2: Describe string, python packages and related functions for various file handling operations.

CO3: Apply functions to decompose python program and represent compound data using Python
lists, tuples, and dictionaries.

CO4: Analyze graphics, image processing and object oriented programming concept to create
applications and analyze exceptions during program execution.

CO5: Create GUI based applications using python packages and network client/server
programming.
 Blooms Number
Modules level* of hours

Module-I

1. Write a program to read the radius of a circle and print the area of
circle.
2. Write a program to reverse a four digit number using % and //
operators.
3. Apply control statements of python to create following pattern.
1
12
123
1234
12345
4. Apply control statement in python to construct a program to
prompt a user to read the marks of five different subjects. L3,L5 3
Calculate the total marks and percentage of the marks and display
the message according to the range of percentage given table.
Percentage Message

Per>=90 Distinction

Per>=80 && per<90 First Class

Per>=70 && per<80 Second Class

Per>=60 && per<70 Third Class

Per<60 Fail
Module-II

1. Write the function replacevowels(word) which removes all the

vowels (‘a’,’e’,’i’,’o’,’u’) in a word and returns the remaining
letters in the word.
2. Generate 50 random numbers within a range 500 to 1000 and write
them to file using function.
3. Creating 1-D, 2-D , 3-D numpy arrays and performing arithmetic
L3,L5 3
on them.
4. Stacking and reshaping array
5. Plotting simple plots in matplotlib: line, scatter, boxplot, bar,
6. Working with various parameters available in plot function
7. Working with series and data frames in pandas
8. Reading and writing CSV and excel files
9. Adding and removing columns in DataFrame
10. Cleaning data columns using regular expressions

Module-III

1. Write python program for following image processing operations

 Convert image in to grayscale image
 Display size of image
 Rotate an image
 Paste one image on another image.
 Crop an image.
2. Implement logistic regression and knn classification on iris dataset
using scikit-learn
3. Perform linear regression and multiple feature linear regression on
any dataset using scikit-learn L3,L5 3
4. Implement gradient descent algorithm to optimize linear regression
and logistic regression algorithm
5. Apply various evaluation metrics on breast cancer data set from
scikit learn after performing logistic regression.
6. In exercise 5 plot decision boundary using matplotlib
7. Implement RandomForest and Decision tree algorithms on
external and internal data sets
8. Show use of Scalers techniques available in scikit-learn
Module IV

1. Implement feature scaling in scikit learn

2. Implement PCA on breast cancer dataset using scikit learn 3
3. Draw two-dimensional scatter plot of the Breast Cancer dataset L3,L5
using the first twoprincipal components as done in exercise 2.
4. Apply TSNE algorithm to mnist dataset (manifold learning)
5. Implement MDP and Q-learning in python.

*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4: Analysis; L5: Synthesis, L6: Evaluation

Text Books

1. Pilgrim, Dive, “Introduction to Python”, 3rd Edition, Apress, 2009.

2. Allen Downey, Jeffrey Elkner, Chris Meyers, “How to Think Like a Computer Scientist
Learning with Python” 2nd Edition Green Tea Press,2002.
3. Manaranjan Pradhan and U Dinesh Kumar, “Machine Learning using Python” , Wiley
Publication

Reference Books

1. John V. Guttag, “Introduction to Computation and Programming using Python”, Prentice

Hall of India, 2014.
2. Mark Lutz, “Learning Python: Powerful Object-Oriented Programming‖”, Fifth Edition,
O‘Reilly, Shroff Publishers and Distributors, 2013.
3. Michale Bowles “Machine Learning in Python: Essential Techniques for Predictive
Analysis” Wiley Publication.

Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

IA EE

Components A PR LR V

Weightage 5 10 10 5 70
(%)

Note: IA –Internal Assessment, A – Attendance, PR – Performance, LR – Lab Record, V – Viva,

EE- External Exam
CO, PO and PSO mapping
1: strongly related, 2: moderately related and 3: weakly related

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 3 2 2 -- -- -- -- -- -- -- -- 1 1 2 --

CO2 1 3 2 2 -- -- -- -- -- -- -- -- 1 1 2 --

CO3 1 3 2 1 2 -- -- -- -- -- -- -- 1 1 2 --

CO4 1 1 1 1 1 2 -- -- -- -- -- -- 1 -- 1 --

CO5 1 1 1 1 1 2 -- -- -- -- -- -- 1 -- 1 ---

Machine Learning with Robotics L T P C

Version 1.1 Date of Approval: 3 0 0 3

Pre-requisites/ Basics of Algorithms, Basics of Linear Algebra & Robotics

Exposure
Co-requisites

Catalog Description
In this course the concepts of artificial intelligence, machine learning, probability theory,
generative model, regression and its classification are discussed in detail. Concept of neural
network, Bayes tool box, general learning machine, reinforcement learning and supervised
learning are also discussed in detail. The aim of this course is to make the students familiar with
the knowledge of machine learning with robotics and their applications.
Course Objectives
The objective of this course is
1. To understand various scalable machine learning algorithms to solve robotics problem.
2. To implement Machine Learning algorithms using MATLAB.
3. To understand the principles of reinforcement learning which is one of the key learning
techniques for robots.
Course Outcomes
On completion of this course, the students will be able to

CO1: Understand basic probabilistic principles behind Robotics intelligence

CO2: Demonstrate the concept of control theory and logistics regression.
CO3: Apply the Bayes network and perceptron concept in robotics.
CO4: Understand POMDP, neural network, Backpropagation algorithm and its significance for
robotics

Blooms Number
Modules
level* of hours
Module I: Introduction
Some history of AI and machine learning, Machine Learning and the
probabilistic framework, Robotics and control theory, Sensing and acting,
Probability theory, Vector and matrix notations, Basic calculus, MATLAB L1, L2 7
programming environment, Main programming constructs, Creating
MATLAB programs, Graphics.

Module II: Basic robotics with LEGO NXT and Regression

Building a basic robot with LEGO NXT, Basic MATLAB NXT toolbox
commands, Classical control theory, Adaptive Controle, Configuration
space, Planning as search, Regression of noisy data, Probabilistic models L1, L2 7
and maximum likelihood, Minimization procedures, Gradient Descent,
Logistic regression, Generative models.

Module III: Graphical models and learning machines

Causal models, Bayes Net toolbox, Temporal Bayesian networks: Markov
Chains and Bayes filters, Application and generalization: Localisation
example, General learning machines: The Perceptron, MultilayerL1, L2 8
perceptron (MLP), LIP regression, Support Vector Machines (SVM), SV-
Regression and implementation.

Module IV: Reinforcement Learning L1, L2 7

Learning from reward and the credit assignment problem, Markov
Decision Process, Bellman equation, Temporal Difference learning, Robot
exercise with reinforcement learning, POMDP, Model-based RL.

Module V:  Supervised learning

Concept of neural network (NN) and main block, Intuitive understanding
of NN, Backpropagation algorithm, NN model in ROS and run L1, L2 ,L3 7
applications

*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4:Analysis; L5:Synthesis, L6:Evaluation

Text & Reference books:

Text

 E. Alpaydin, Introduction to Machine Learning, 3rd Edition, Prentice Hall (India) 2015.
 R. O. Duda, P. E. Hart and D. G. Stork, Pattern Classification, 2nd Edn., Wiley India,
2007.
 Craig. J. J. “Introduction to Robotics mechanics and control”, Addison- Wesley,1999.
 S.R. Deb, Robotics Technology and flexible automation, Tata McGraw-Hill Education., 2009
 Mikell P Groover & Nicholas G Odrey, Mitchel Weiss, Roger N Nagel, Ashish Dutta, Industrial
Robotics, Technology programming and Applications, McGraw Hill, 2012
Reference
 Sebastian Thrun, Wolfram Burgard, Dieter Fox, Probabilistic Robotics, MIT Press 2005
 Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: An Introduction”, Second
edition, MIT Press, 2018
 Jens Kober, Jan Peters, Learning Motor Skills: From Algorithms to Robot Experiments,
Springer, 2014 4. Francis X. Govers, Artificial Intelligence for Robotics, Packt, 2018
Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance
CO, PO and PSO mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4
 CO1 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO2 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO3 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO4 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

1: strongly related, 2: moderately related and 3: weakly related

AUTOMATION IN MANUFACTURING SYSTEMS L T P C

Version 1.1 Date of Approval: 3 0 0 3

Pre-requisites/ CAD, CAM, CNC & Robotics

Exposure
Co-requisites

Catalog Description
In this course the concepts of various types of automation, automation principles and strategies,
level of automation, hardware components of automation, material handling and identification
technologies and different types of automated production lines are discussed in detail. Concept of
cellular manufacturing, group technology and flexible manufacturing systems are discussed in
detail. Concept of quality control, automated inspection and quality function deployment are also
discussed in detail. The aim of this course is to make the students familiar with the automation
applications in manufacturing systems.

Course Objectives
The objective of this course is to
1. Equip the students with concept of automation in production systems, material handling and
automated production lines.
2. Provide an overview of quality control, cellular manufacturing, group technology and flexible
manufacturing systems.

Course Outcomes
On completion of this course, the students will be able to

CO1: Explain automation in production systems, automation principles and strategies, and level
of automation.
CO2: Explain working of material handling systems, automated storage system and automatic
identification methods.
CO3: Describe the manual assembly lines, automated assembly lines and its applications.
CO4: Discuss the concept of quality control, cellular manufacturing, group technology and
flexible manufacturing systems.
Blooms Number
Modules
level* of hours
MODULE 1: OVER VIEW OF MANUFACTURING AND AUTOMATION
Production systems, Automation in production systems, Automation principles and
strategies, Manufacturing operations, production facilities. Basic elements of an L1, L2 7
automated system, levels of automation; Hardware components for automation and
process control, 3D printer, classification and application of 3D printers.
MODULE 2: MATERIAL HANDLING AND IDENTIFICATION
TECHNOLOGIES
Material handling, equipment, Analysis. Storage systems, performance and location L1, L2 7
strategies, Automated storage systems, AS/RS, types. Automatic identification methods,
Barcode technology, RFID.
MODULE 3: MANUFACTURING SYSTEMS AND AUTOMATED
PRODUCTION LINES
Manufacturing systems: components of a manufacturing system, Single station
L1, L2 8
manufacturing cells; Manual Assembly lines, line balancing Algorithms, Mixed model
Assembly lines, Alternative Assembly systems. Automated production lines,
Applications, Analysis of transfer lines.
MODULE 4: AUTOMATED ASSEMBLY SYSTEMS L1, L2 7
Fundamentals, Analysis of Assembly systems, Cellular manufacturing, part families,
cooling, production flow analysis. Group Technology and flexible Manufacturing
systems, Application of robots in medical and other fields.
MODULE 5: QUALITY CONTROL AND SUPPORT SYSTEMS
Quality in Design and manufacturing, inspection principles and strategies, Automated
L1, L2 7
inspection, contact Vs non contact, CMM. Manufacturing support systems. Quality
function deployment.
*Bloom’s Level:
L1-Knowledge; L2-Comprehension; L3-Application; L4:Analysis; L5:Synthesis, L6:Evaluation

Text Books
1. Automation, production systems and computer integrated manufacturing/ Mikell.P
Groover/PHI/3 rd edition/2012.
2. Manufacturing and Automation Technology / R Thomas Wright and Michael Berkeihiser /
Good Heart/Willcox Publishers.

Reference Books
1. CAD/CAM/CIM/ P. Radha Krishnan & S. Subrahamanyarn and Raju/New Age International
Publishers/2003.
2. System Approach to Computer Integrated Design and Manufacturing/ Singh/John Wiley /96.
3. Computer Aided Manufacturing/Tien-Chien Chang, Richard A. Wysk and Hsu-Pin Wang/
Pearson/ 2009.

Modes of Evaluation: Quiz/Assignment/ Seminar/Written Examination

Examination Scheme:

Components A CT S/V/Q HA EE
Weightage (%) 5 10 8 7 70

CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester
Examination; Att: Attendance
CO, PO and PSO mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3 PSO4

CO1 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO2 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO3 1 1 -- -- -- -- -- -- -- -- -- -- 1 1 -- --

CO4 1 1 -- -- -- -- -- -- -- -- -- -- 2 1 -- --

1: strongly related, 2: moderately related and 3: weakly related