DISSERTATION

“EXPLORING THE DEVELOPMENT OF

ROBOTICS : A THEMATIC
LITERATURE REVIEW”
Submitted in the partial fulfillment of the requirement
for the award of degree
of
Master of Library and Information Science
Submitted By
Purvi Mishra
Roll No: 200120
Enrollment No: 676/19

Under the supervision of

Dr. Vinit Kumar
Assistant Professor

DEPARTMENT OF LIBRARY AND INFORMATION SCIENCE

(SCHOOL FOR INFORMATION SCIENCE AND TECHNOLOGY)

BABASAHEB BHIMRAO AMBEDKAR UNIVERSITY

(A Central University)
VidyaVihar, Rae Bareli Road, Lucknow-226025, U.P.
2021
 DECLARATION

I hereby declare that this review of literature entitled “Exploring The Development Of
Robotics: A Thematic Literature Review” submitted by me in the partial fulfillment for the
degree of Master of Library and Information Science to the Department of Library and
Information Science, Babasaheb Bhimrao Ambedkar University (A Central University),
Vidya Vihar, Rae BareliRoad, Lucknow is an outcome of my own effort and is an original
work.

Date: 2021
Place: Lucknow

(Purvi Mishra)
Roll No: 200120
Enrollment No:676/19
 BABASAHEB BHIMRAO AMBEDKAR UNIVERSITY
(A CENTRAL UNIVERSITY)
Vidya Vihar, Raebareli Road, Lucknow-226025

Letter No………..
Dated…………..

Dr. Vinit Kumar

(Assistant Professor)
Department of Library and Information Science
(School for Information Science and Technology)
Babasaheb Bhimrao Ambedkar University
Lucknow-226025

CERTIFICATE
This is to certify that this review of literature work entitled “Exploring The
Development Of Robotics: A Thematic Literature Review” submitted by Purvi
Mishra in partial fulfillment for the degree of Master of Library and Information
Science to the Department of Library & Information Science, (School for
Information Science & Technology), Babasaheb Bhimrao Ambedkar University,
Lucknow.Vidya Vihar, RaeBareli Road, Lucknow-226025 has been prepared by her
under my guidance.

Date: /06/2021
Place: LUCKNOW

(Vinit Kumar)
 ACKNOWLEDGEMENT

This dissertation entitled “Exploring The Development Of Robotics: A Thematic

Literature Review” in partial fulfillment for the degree of Master of Library and
Information Science to the Department of Library & Information Science, (School for
Information Science & Technology), Babasaheb Bhimrao Ambedkar University,
Lucknow. I have the privilege and honor to express my deep sense of gratitude to Prof. Shilpi
Verma (HOD), Prof. K.L. Mahawar, Prof. M.P. Singh, Prof. S.K. Sonkar and Prof.
Somipam R. Shimray, Department of Library& Information Science, (School for Information
Science & Technology), Babasaheb Bhimrao Ambedkar University, Lucknow for their kind
help and support.

I wish to acknowledge my thanks to all those authors and writers whose works have
been consulted during the preparation for this dissertation.

Thanks

Date: 2021
Place: Lucknow
(Purvi Mishra)
 INTRODUCTION

1. Robotics is a branch of engineering and science that includes electronics engineering,

mechanical engineering and computer science and so on. This branch deals with the
design, construction, use to control robots, sensory feedback and information processing.
These are some technologies which will replace humans and human activities in coming
years. These robots are designed to be used for any purpose but these are using in sensitive
environments like bomb detection, deactivation of various bombs etc. Robots can take any
form but many of them have given the human appearance. The robots which have taken
the form of human appearance may likely to have the walk like humans, speech, cognition and
most importantly all the things a human can do. Most of the robots of today are inspired by
nature and are known as bio-inspired robots.

It deals with conception, design, operation, and manufacturing of robots. There was an
author named Issac Asimov, he said that he was the first person to give robotics name in a
short story composed in 1940’s. In that story, Issac suggested three principles about how to
guide these types of robotic machines. Robots are used for various purposes in day-today life.
With ever growing technology and competition there is a desire for doing work in less time,
also considering economy in the equation. Keeping this into consideration this project aims at
minimizing the efforts required to arrange books in a library. A library generally consists of
thousands of books and there are two or three employees to arrange them. The Library
Management Robot (LMR) will mitigate the problems by collecting the books from library
counter and then arranging the books, one by one, into shelves. With the advancement of
robotics, automation in various industries and processes has become widespread. Robotics,
design, construction, and use of machines (robots) to perform tasks done traditionally by
human beings. ... Robots are widely used in such industries as automobile manufacture to
perform simple repetitive
tasks, and in industries where work must be performed in environments hazardous to
humans. Robotics develops machines that can substitute for humans and replicate human
actions. Robots can be used in many situations and for many purposes, but today many are
used in dangerous environments (including inspection of radioactive materials,
manufacturing processes, or where humans cannot survive (e.g. in space, underwater, in high
heat, and clean up and containment of hazardous materials and radiation). Robots can take on
any form but some are made to resemble humans in appearance. This is said to help in the
acceptance of a robot in certain replicative behaviors usually performed by people. Such
robots attempt to replicate walking, lifting, speech, cognition, or any other human activity.
Many of today's robots are inspired by nature, contributing to the field of bio inspired robotics.
All robots contain some level of code. A program is how a robot decides when or how to do
something. In the caterpillar track example, a robot that needs to move across a muddy road
may have the correct mechanical construction and receive the correct amount of power from
its battery, but would not go anywhere without a program telling it to move. Programs are the
core essence of a robot, it could have excellent mechanical and electrical construction, but if
its program is poorly constructed its performance will be very poor (or it may not perform at
all). There are three different types of robotic programs: remote control, artificial
intelligence and hybrid. A robot with programming has a preexisting set of commands
that it will only perform if and when it receives a signal from a control source, typically a
human being with a remote control. It is perhaps more appropriate to view devices controlled
primarily by human commands as falling in the discipline of automation rather than robotics.
Robots that use interact with their environment on their own without a control source, and can
determine reactions to objects and problems they encounter using their preexisting
programming. Hybrid is a form of programming that incorporates both AI and RC functions in
them.
METHODOLOGY
This study would applied to know about research productivity of development of
robotics in this world this study will use the time periods of 10 Years (2010 -2020)
because it’s the time of technological advancement of use robotics. It used google
Scholor data based it is one of the best data based for research paper and have
maximum coverage of scholarly publication with Authors
OBJECTIVES

 To find out the most fruitful authors in the robotics field

 To find out the most productive countries in robotics technology

 Most frequent used language of paper published in related field

 Countries that are using this (robotics) technology in various

 Finding out the growth of robotics

SCOPE
The study covers all the research papers available in the robotics research field of
the various countries worldwide. The time period using in this investigation
between 2010-2020 because it’s the time of technological advancement in term of
used robotics
Robotics in Library

“Robot is “An automatically controlled, reprogrammable, multi-purpose

manipulator programmable in three or more axes, which may be either fixed in
place or mobile for use in automation applications.” The robots are scrambling,
rolling, flying, and climbing. They are figuring out how to get here on their own.
As libraries provide a growing array of digital library services and resources, they
continue to acquire large quantities of printed materials. This combined pressure of
providing electronic and print-based resources and services has led to severe space
constraints for many libraries, especially academic research libraries. The goal of
the Comprehensive Access to Printed Material (CAPM) is to build a robotic, on-
demand and batch scanning system that will allow for real-time browsing of
printed material through a web interface. The user will engage the CAPM system
that, in turn, will initiate a robot that will retrieve the requested item. The robot
will deliver this item to another robotic system that will open the item and turn the
pages automatically. By using existing scanners, optical character recognition
(OCR) software, & indexing software developed by the Digital Knowledge Centre,
the CAPM system will not only allow for browsing of images of text, but also for
searching and analyzing of full-text generated from the images. “–Researchgate;
Dr. S. Mogali

It is interesting to note that, as the monkey selfie case has underlined, only human
beings can claim copyright. Potentially, the programmer behind the AI could claim
an interest, but with robots having the ability to write, create new works, etc.,
librarians will need to think about this.

Robots, visible like Robbie in Lost in Space, or a disembodied voice in the air or
communications device, will once again change the way people look for
information, at the expense of librarians—just as consumer search engines have
already gone a long way to replicating the traditional role of libraries in helping
find basic information. As robots become smarter, and emerge with more nuanced,
smarter responses, we ignore them at our peril. Realistically, just as Google and
their ilk have become our assistants, there is a wide range of opportunities for our
field by exploiting technology interventions such as robots in libraries.
 REVIEW OF LITERATURE

Literature review is the most important and the second step in the process of any research.
First of all literature review is to do find out and to understand the main background of the
particular subject or research which is taken by the researcher. It is a record which showing
what had done in this regard in the recent past. Thus it is the current trend in the selected
subject when the review of literature made by the researcher. He/she will become expert in
his/her subject and he/she will become Master. It shows what had already done and what type
of work yet to be carried out. It shows the direction is which the research direction must go.
Research work clearly showing there should not be duplication of work. It also indicated
what type of methodology was adopted by various experts researcher. When review of
literature is done one should remember that Textbooks and encyclopedic document must not
be taken into consideration. The researcher must question from himself what kind of research
he has to do. What points must be consider while preparing on studying review of literature.
From the literature the researcher must percolate down specific problem to general problem.

A various types of research studies have been conducted on various aspects of on exploring
the development of robotics in library, which is relevant for this research. Some of the
terms related robotics development, Artificial intelligence and robotics, robot modeling and
control discussed. Some worthwhile studies relating to the present study viewed here.

The researcher has done studies the review on the basis of National and International level
Journals, Articles and thesis.
1. Development of Robotics

Ekaterina Nezhnikovaet. al., (2020)

In their research the position of the Russian robotics market in relation to the
matrix of approaches to the development of national programs. At this stage,
Russian robotics is based more on foreign basic research with a focus on the
external market, since the capacity of the domestic Russian market is still
insignificant and for the sustainable development of domestic developers and
manufacturers of robotic systems it is necessary to focus on foreign markets.
Robotics is traditionally divided by the international robotics Federation (IFR) into
service and industrial robotics. Currently, the first type of robotics prevails in
Russia, which can be seen by the number of companies belonging to these types:
80 companies developing service robots against 10 industrial ones. Thanks to the
SWOT analysis of the robotics market in Russia conducted in the second part of
the article, the main competitive advantages of the country were identified, among
which, for example, one can note the huge territories and small population. Due to
this situation, the use of unmanned transport (air, land, sea and river) in our
country can be justified and cost-effective.

The study additionally reveals the result, driverless transport on our routes can be
used for commercial purposes a little earlier than in countries with higher
population density. It is also worth noting the threats that arise in the way of the
development of domestic robotics. In the first place among the main ones are
geopolitical barriers: the current sanctions regime against the Russian Federation
puts barriers on scientific and technical cooperation with foreign specialists,
prevents the import of technologies and blocks access to international investment.
It is also worth noting the increase in the trend.

Carmel Majidi (2013)

In their analysis, the researcher concentrated on the findings the Soft robots are
primarily composed of easily deformable matter such as fluids, gels, and
elastomers that match the elastic and rheological properties of biological tissue and organs.
Like an octopus squeezing through a narrow opening or a caterpillar rolling through uneven
terrain, a soft robot must adapt its shape and locomotion strategy for a broad range of tasks,
obstacles, and environmental conditions. This emerging class of elastically soft, versatile, and
biologically inspired machines represents an exciting and highly interdisciplinary paradigm in
engineering that could revolutionize the role of robotics in healthcare, field exploration, and
cooperative human assistance.

SanjeeviChitikeshi (2020)

The study analyses With a growing need for a more skilled workforce, providing industry-
driven and employment- centric training services is an important national priority. Over 3.4
million manufacturing jobs will need to be filled across the United Sates over the next decade.
The skills gap is becoming greater based on the statistics provided by the Global Robotics
Technology Market: Forecast, 2014- 2020 published by Research and Markets, reporting that
the worldwide robotics market is forecast to grow from the 2015 level of $26.98B to
$82.78B in 2020. This 11 % compounded average growth in the next five years is
unprecedented. Given the anticipated growth of the robotics industry, the number of jobs
that will be required to meet the demand will grow exponentially as well. The future is bright
for careers in STEM fields; today, the average annual salary for a STEM worker is $33,200
higher than the average of all U.S. workers, making the need for a novel robotics credential
imperative.

This study shows the development of the area of Advanced Robotics for Manufacturing was
carried out broadly in two phases: Phase I of the project focused on investigating and
compiling the curricula offered by different community colleges, work force education
programs in universities and other
industry certificate programs in the Commonwealth of Virginia and then in other states. Phase
II of this project focused on curriculum development at CCAM (Commonwealth Center for
Manufacturing, VA) that improves/adds the topics, compliments and fills the gap from the
data gathered in the first stage. Phase II was not only based on the data generated in Phase I,
but also was informed by data gathered from industry needs and new technologies that are
required in the manufacturing robotics area. The next phase include implementing the
developed curriculum at Community College level and at 4-year degree colleges.

LópezPeláezet. al., (2014)

The research analyses on their books how robotics will shape our societies in the twenty-first
century; a time when industrial and service robotics, particularly for military and aerospace
purposes, will become an essential technology.

Examines an emerging divide: the “robotics divide”; a phenomenon linked to the model to
integrate advanced robotics in economic, social and military spheres

Focuses on the main technological trends in the field of robotics, and the impact that robotics
will have on different facets of social life.

HinYan Liu et. al., (2017)

In their study titled “From responsible robotics towards a human rights regime oriented
to the challenges of robotics and artificial intelligence” The aims of their study of the
responsible robotics initiative is to ensure that responsible practices are inculcated within each
stage of design, development and use, this impetus is undergirded by the alignment of ethical
and legal considerations towards sociallybeneficial ends. While every effort should be
expended to ensure that issues of responsibility are addressed at each stageof technological
progression, irresponsibility (meaning a lack of responsibility) is inherent within
the nature of roboticstechnologies from a theoretical perspective that threatens to thwart the
endeavour. This is because the concept of responsibility,despite being treated as such, is not
monolithic: rather this seemingly unified concept consists of converging andconfluent
concepts that shape the idea of what we colloquially call responsibility. From a different
perspective, robotics willbe simultaneously responsible and irresponsible depending on the
particular concept of responsibility that is foregrounded:an observation that cuts against the
grain of the drive towards responsible robotics. This problem is further compounded
byresponsible design and development as contrasted to responsible use. From a different
perspective, the difficulty in definingthe concept of responsibility in robotics is because
human responsibility is the main frame of reference. Robotic systemsare increasingly expected
to achieve the human-level performance, including the capacities associated with
responsibilityand other criteria which are necessary to act responsibly. This subsists within a
larger phenomenon where the differencebetween humans and non-humans, be it animals or
artificial systems, appears to be increasingly blurred, thereby disruptingorthodox
understandings of responsibility. This paper seeks to supplement the responsible robotics
impulse by proposinga complementary set of human rights directed specifically against the
harms arising from robotic and artificial intelligence(AI) technologies. The relationship
between responsibilities of the agent and the rights of the patient suggest that a rightsregime is
the other side of responsibility coin. The major distinction of this approach is to invert the
power relationship: whilehuman agents are perceived to control robotic patients, the prospect
for this to become reversed is beginning. As robotictechnologies become ever more
sophisticated, and even genuinely complex, asserting human rights directly against
roboticharms become increasingly important. Such an approach includes not only developing
human rights that ‘protect’ humans(in a negative, defensive, sense) but also ‘strengthen’
people against the challenges introduced by robotics and AI (in a
positive,empowering, manner) [This distinction parallels Berlin’s negative and
positive concepts of liberty (Berlin, in Liberty,Oxford University Press, Oxford,
2002)], by emphasising the social and reflective character of the notion of
humanness aswell as the difference between the human and nonhuman. This will
allow using the human frame of reference as constitutiveof, rather than only
subject to, the robotic and AI technologies, where it is human and not technology
characteristics thatshape the human rights framework in the first place.

Guido Bugmannet. al., (2011)

In their research entitled “A role for robotics in sustainable development” the

study analyses in a sustainable economic model, energy and material resources are
limited. How would robotics need to be adapted to this model in order to play a
useful role? The study attempt and explore the concepts for the role for robotics in
sustainable development. Industrial robotics is often associated with an
unsustainable economic model. However, robotics also provides qualitative
benefits through its precision, strength, sensing capabilities and computing power.
New applications and deployment models can be devised that improve
sustainability and quality of life. These may require new approaches to the design
of robots, robot-using systems and IT systems that employ methods of robotics and
AI. Robotics for sustainable development is an exciting challenge where research,
education and industry in both developed and developing countries can equally
contribute and benefit.

2. Robotics with Artificial

Intelligence Luca Iocchiet. al., (2013)

Their study entitled “Development of intelligent service robots” considered the

creation of intelligent robots has been a major goal of Artificial Intelligence since
the early days and has provided many motivations to Artificial Intelligence researchers.
Therefore, a large body of research has been done in this field and many relevant results have
shown that integration of Artificial Intelligence and Robotics techniques is a viable approach
towards this goal.

This article summarizes the efforts and the achievements of several Italian research groups in
the development of intelligent robotic systems characterized by a suitable integration of
Artificial Intelligence and Robotic techniques. The contributions collected in this article show
the long history of this research stream, the impact of the developed approaches in the
scientific community, and the efforts towards actual deployment of the developed systems.

Vikram Singh Bisen (2020)

In their article “AI in Robotics: Use of Artificial Intelligence in Robotics”, the study analyze
How AI is Used in Robotics? The articles revealed AI in robotics helps robots perform the
crucial tasks with a human-like vision to detect or recognize the various objects.

Nowadays, robots are developed through machine learning training. A huge amount of
datasets is used to train the computer vision model, so that robotics can recognize the various
objects and carry out the actions accordingly with right results. There are various functions
integrated into robots like computer vision, motion control, grasping the objects, and training
data to understand physical and logistical data patterns and act accordingly.

Manav Raj and Robert Seamans (2019)

In their research the study entitled “Primer on artificial intelligence and robotics” provides an
introduction to artificial intelligence, robotics, and research streams that examine the
economic and organizational consequences of these and related
technologies. We describe the nascent research on artificial intelligence and robotics in the
economics and management literature and summarize the dominant approaches taken by
scholars in this area. The researcher discuss the implications of artificial intelligence,
robotics, and automation for organizational design and firm strategy, argue for greater
engagement with these topics by organizational and strategy researchers, and outline
directions for future research.

The study revealed the result Artificial intelligence and robotics have experienced dramatic
increases in performance, and this has led to greater funding for artificial intelligence and
robotics start-ups, more popular press articles on how these technologies will change the
world, and a recent increase in academic research around the consequences of these
technologies for firms, workers, and economies. In this Primer, we define the key concepts,
review the existing literature, identify implications for organizational design, and describe
opportunities for organizational and strategy scholars.

Much of the literature that has been undertaken in this area focuses on how the adoption of
robotics and artificial intelligence technologies affects economic growth and labor markets.
This is still a prime area for further research given the important implications for social
welfare. In addition, a lack of comprehensive data on the adoption and use of artificial
intelligence and robots means that much of the existing work relies on expert or crowd-
sourced opinions rather than empirical evidence (e.g., Frey and Osborne 2017; Brynjolfsson et
al. 2018b; Felten et al. 2018). In the future, better collection and organization of data will
allow for more direct empirical studies and will allow scholars to examine adjacent
questions, such as differences in terms of performance and labor market consequences for
different types of robotics or artificial intelligence technologies. We need evidence-based
research on how artificial intelligence affects firm-level productivity, employment, and
wages, as well as research on how artificial
intelligence may affect economic outcomes with distributional consequences, such as
innovation, business dynamism, and inequality.

Anusha Reddy et. al., (2017)

In their research they consider the under lying concepts of Artificial Intelligence (AI) and
Robotics is presented with the main emphasis on the how the present day robots and the future
of Artificial Intelligence and Robotics would impact the society and the social life at large.
Their study revealed Future research will be based on Artificial Intelligence with Deep
Architectures and Deep Learning Algorithms. Presently, the problem with this is that
training takes a long time. This approach should help machines think like humans, and thus
making Strong AI a reality. Further research is required in the areas of sensors, where touch
and feel need to be perfected, since building Robots resembling humans would require them.
So, with the present technology at hand, can we really build Humanoids that represent a
human being? And, will robots take over the world? Who knows? Only time will tell.

MORIKAWA Masayuki (2016)

This study presents new evidence on firms’ attitudes toward artificial intelligence (AI) and
robotics, as well as their attitude toward the impacts of these new technologies on future
business and employment prospects. The data used in this paper are the results of our original
survey of more than 3,000 Japanese firms. The major findings can be summarized as follows.

First, firms operating in the service industry have a positive attitude on the effects of AI-
related technologies, suggesting the importance of paying attention to “AI-
using industries.” Second, we observe complementarity between AI-related technologies and
the skill level of employees.

Their finding suggests that in order to accelerate the development and diffusion of AI and to
maintain employment opportunities, it will be necessary to upgrade human capital. Third,
firms that engage in global markets tend to have a positive attitude toward the impacts of AI-
related technologies, indicating that globalization of economic activities will facilitate the
development and diffusion of these new technologies.

Malkit Singh et. al., (2016)

Their research on “Artificially Intelligent Maze Solver Robot” The study showsRobotics is
very important now days, especially due to its increasing practice in many industries. It was
recently observed that there is a great difficulty being faced in the separation of the articles in
the industries, like Textiles. Being a manual job it was also time consuming and boring.
Therefore, for giving this problem a technological perspective, automation in such field was
required. When a robot having its own sense of judgment to the path which it follows, would
be introduced then a high efficiency in performance could be achieved along with increase in
reliability and affordability of the manufacturers could be seen. The robot would be
selfsufficient to take a note the paths through which it is moving, hence executing some
complex maze-solving algorithms in its CPU core and taking its own decision on turnings
and reaching its goal. It would certainly be a proof of a robot having its own “Brain-like”
structural methodology having an access to the real-time inputs, making the prototype an
Artificially Intelligent Robot.
3. Navigation and Motion
Planning

Benjamin Arnold et. al., (2017)

In their research entitled “Design, Manufacturing and Test of a High-Precision MEMS
Inclination Sensor for Navigation Systems in Robot-Assisted Surgery”. The research analyse
the Robot supported minimally invasive interventions are state of the art in operating
theatres. To increase the accuracy of surgical instrument positioning, high-precision motion
tracking systems are required.

The objective of their research was to achieve very accurate instrument positioning, high
precision motion tracking systems are essential to get for example the actual tilt of an
endoscope. Due to miniaturization of MEMS, the placing of orientation detection sensors
close to the endoscope is possible. Furthermore, the integration of MEMS tilt sensors into the
surgical instrument near the mounting can facilitate the measurement of vibrations and their
compensation. The developed capacitive MEMS sensor complies with the requirements of
small size and high-precision inclination measurement.

The miniaturization of microelectromechanical systems (MEMS) facilitates the placing of

orientation detection sensors close to the mounting of the surgical instrument to enhance
positioning accuracy. A high resolution inclination sensor was developed using the innovative
approach of laser-micro-welding. Trench sizes down to 800 nm are fabricated with more than
6-fold increase in aspect ratios (structure depth to electrode gap) compared to sensors without
gap reduction. Electrical and physical tests as well as finiteelement- simulations were
performed. An increased sensitivity from 7.2 fF/° up to 60 fF/° was verified for the sensor
with reduced electrode gap and a customized ASIC.
4. Machine Learning
Jean Gallier (2020)
In their research entitled “Linear Algebra for Computer Vision, Robotics, and Machine
Learning” The study analyzein recent years, computer vision, robotics, machine learning, and
data science have been some of the key areas that have contributed to major advances in
technology. Anyone who looks at papers or books in the above areas will be based by a
strange jargon involving exotic terms such as kernel PCA, ridge regression, lasso regression,
support vector machines (SVM), Lagrange multipliers, KKT conditions, etc. Do support
vector machines chase cattle to catch them with some kind of super lasso? No! But one will
quickly discover that behind the jargon which always comes with a new field (perhaps to keep
the outsiders out of the club), lies a lot of “classical” linear algebra and techniques from
optimization theory. And there comes the main challenge: in order to understand and use tools
from machine learning, computer vision, and so on, one needs to have a firm background in
linear algebra and optimization theory. To be honest, some probablity theory and statistics
should also be included, but we already have enough to contend with. Many books on machine
learning struggle with the above problem. How can one understand what are the dual variables
of a ridge regression problem if one doesn’t know about the Lagrangian duality framework?
Similarly, how is it possible to discuss the dual formulation of SVM without a firm
understanding of the Lagrangian framework?

The easy way out is to sweep these diculties under the rug. If one is just a consumer of the
techniques we mentioned above, the cookbook recipe approach is probably adequate. But this
approach doesn’t work for someone who really wants to do serious research and make
significant contributions. To do so, we believe that one must have a solid background in linear
algebra and optimization theory.
This is a problem because it means investing a great deal of time and energy studying these
fields, but we believe that perseverance will be amply rewarded. The research main aim is to
present fundamentals of linear algebra and optimization theory, keeping in mind applications
to machine learning, robotics, and computer vision. Their research consists of two volumes,
the first one being linear algebra, the second one optimization theory and applications,
especially to machine learning. This first volume covers “classical” linear algebra, up to and
including the primary decomposition and the Jordan form.

Markus Nowak et. al., (2017)

In their study they consider match machine learning (ML) and interactive machine learning
(iML) with radical constructivism (RC) to build a tentative radical constructivist framework
for iML; we then present a pilot study in whichRC- framed iML is applied to assistive
robotics, namely upper-limb prosthetics (myocontrol). The problem of their researchwas
despite morethan 40 years of academic research, myocontrol is stillunsolved, with rejection
rates of up to 75%. This is mainly due toits unreliability – the inability to correctly predict the
patient’s intent in daily life. The methodology of the research is a proposeof descriptionof
the typical problems posed by ML-basedmyocontrol through the lingo of RC, highlighting the
advantages of sucha modelisation. We abstract some aspects of RC and project them onto
the concepts of ML, to make itevolve into theconcept of RC-framed iML. The study showed
the result such a projection leads to the design and development of a myocontrol systembased
upon RC-framed iML, used to foster the co-adaptation of human and prosthesis. The iML-
based myocontrol system is then compared to a traditional ML-based one in a pilot study
involving human participants in a goal-reachingtask mimicking the control of a prosthetic
hand and wrist.
Suenderhaufet. al., (2018)
Their study considered the application of deep learning in robotics leads to very specific
problems and research questions that are typicallynot addressed by the computer vision and
machine learning communities. In this paper they discuss a number ofrobotics-specific
learning, reasoning, and embodiment challenges for deep learning. The paper explained the
need for betterevaluation metrics, highlight the importance and unique challenges for deep
robotic learning in simulation, andexplore the spectrum between purely data-driven and
model-driven approaches. The hope this research provides amotivating overview of important
research directions to overcome the current limitations, and help fulfill the promisingpotentials
of deep learning in robotics.

5. Machine Vision And Image Processing Techniques

Michael et.al [13]

The study discussed the performance of FastSLAM over the EKF (Extended Kalman Filter)
technique in the open environment for the data association. FastSLAM, an approach uses Rao-
Blackwellized Particle Filter, shown to scale logarithmic number of landmarks on the map
[14]. Simultaneous Localization And Mapping (SLAM) is used to building a map of unknown
environment with a moving robot. SLAM is an additional feature in the autonomous robots
working in environment where accurate maps are not available [15, 16].

Davison A.J et.al [17]

In their paper has worked on a real time algorithm which can retrieve the movement of a
freely moving camera as an only data source. In MonoSLAM the main assumption are
probabilistic mapping, motion modeling & active measurement and mapping of a sparse
map of high quality feature. The efficiency
is ensured by the active feature search resulting in no waste of image processing
effort. The algorithm, with its experimental result, has an impact on advance
robotics, wearable technology and user interface. The work majorly deals with the
high frame rate real time performance (~30 Hz). As localization and mapping is an
extremely inter-related issue and requires attention on both to solve the problems,
hence the author worked on localization as their main output of the interest.

Hussin R. et.al [18]

In the paper discussed about an algorithm that can be used to detect/recognize

object from intricate environment by using edge detection, color processing and
mathematical morphology. Author in his experiment detects the shape of Mangoes
from the mango tree using CHT (Circular Hough Transform)[19] with the help of
MATLAB program. The CHT algorithm detects the object (Mango) by detecting
the circular pattern with the help of joining maximum voting points around the
given radius. It prepares the image of the object then the image RGB adjustment is
done which is followed by the detection of the color of each pixel to compare the
object and the background and finally the deleting the unwanted region by
changing RGB pixel value to 0.

Pal Nikhil R & Pal Sankar K [20]

The paper discussed analytically discussed and summarized different image

segmentation techniques such as Gray Level histogram, Spatial Details, fuzzy sets,
Thresholding, Edge detection, Clustering, Markov Random Field (MRF) and
compared the results obtained. For different types of images viz. light intensity
(visual), range image, nuclear magnetic resonance image (MRI), thermal images,
there is no single segmentation technique that can hold good for all the images.
Author also tried to survey on the fuzzy sets and neural network based model
algorithms which generate accurate output in real time as these methods are robust enough to
process magnetic resonance images (MRI) [21].

The paper concluded with the finding of objective evaluation of segmentation results.

Robert Sim, James J. Little [22]

Their research addressed the issue of navigation of robot in an unknown environment with the
help of Rao-Blackwellised particle filter (RBPF) which has an added advantages over active
range-finding devices such as laser or sonic transducers. Author clarified autonomous
exploring and mapping issue with stereo camera and an odometry sensor and trot out a
consistent, convergent simultaneous localization and mapping solution with the generation of
accurate localization and collision free navigation. The paper determines a system which
holds a capability of accurate mapping a large and complex environment, can analyze and
navigate fully autonomously using exact localization (visual landmarks).

Ahmad Z. A et. al [23]

Their research has proposed an advanced distributed computing technology for Image
processing applications. This technology uses an integrated multi- processing unit that work
together to execute the task simultaneously [24] where the size of the data of processing is
huge such as Image Processing Applications. The experiment was done using ARM processor
connected to another processor using RS 232 cable and a DB 9 sub connectors using shortest
cable length in order to avoid any signal loss. The firmware was C ARM language using Kiel
uVision3 Integrated Development Environment (IDE).In this experiment author has used 8
bit data bus whereas ARM processor has 32 bit [25] data line by implying a 32 bit data bus the
speed can be further improved up to 4 times theoretically.
Kazuhiro Fukui and Osamu Yamaguch [26]

Their paper has proposed a novel technique of pattern matching which is fast and extract exact
feature in order to provide accurate results. The facial point extraction majorly affects the
template matching based face recognition methods. The proposed method combines shape
information and pattern information to root out the conventional pattern information method
issues. It basically determines the feature points which are based on the shape information and
authenticate it the pattern matchinginformation to produce high position accuracy, robust to
feature point shape variations and brightness. It also reduces the volume of the computation
as the pattern matching will be done only for the objects which are sorted by the separability
filter and hence increases the speed.

PATH PLANNING TECHNIQUES

Lumelskyet. al [27]

The paper discussed the path planning problem of a mobile robot which is working in an
environment filled with obstacles of unknown shape and position. In the algorithm used, the
motion palnning has been done dynamically, based on the automaton’s current position and
feedback.

Emilio Frazzoliet. al [28]

Their paper discussed proposed a randomized path planning architecture for dynamical
systems. The architecture is closed loop which enables the vehicle guidance from any
point/state to any configuration at rest and motion in presence of obstacles. After starting
the from the initial conditions, the algorithm incrementally builds a tree of feasible trajectories
and adds a new branch and a noode to the tree. The randomized motion-planning algorithm
based on obstacle- free guidance systems in probabilistic roadmap framework was presented
which is
having a main advantage of its capability to address in an efficient and natural fashion the
dynamics of the system.

Giebrecht J [29]

In his paper discussed the global path planning method for unmanned ground vehicles which
gives an overview of high-level planning methods used in mobile robotisespacialy in outdoor
planning. The survey was done on all portion of the path planning process and investigated
the recently developed and popular algorithms such as Potential Fields, Wavefront Planning,
Probablistic Roadmaps etc.

Vu T Minh et. al [30]

Their paper discussed the feasible path planning of nonholonomic vehicles subjected to real
vehicle dynamic constraints. The paper presents theperformance of the path planning
methods along with the simulations and comparison for evaluation of more realistic and
smoother generated trajectories. The system automatically generates a optimal path and
control and track the vehicle exactly on the path from any given start to destination points
from the map restricting vehicle physical constraints on obstacles, speed, steering anlges etc.
The paper concludes the analysis which shows the symmetric polynomial algorithm will have
the smoothest trajectory.
 REFERENCES

Anusha Reddy &Ajit Reddy, Artificial Intelligence, Robotics and Its Impact on Society,
International Journal of Science and Engineering Investigations, Volume 6, Issue 61,
February 2017

Malkit Singh1, Rajnish Kumar2, Vaibhav Giradkar3, Pallavi Bhole4, Minu Kumari5,
ARTIFICIALLY INTELLIGENT MAZE SOLVER ROBOT,
Department of Electronics and Telecommunication Engineering, 2016 MORIKAWA
Masayuki (RIETI), The Effects of Artificial Intelligence and Robotics on Business
and Employment: Evidence from a survey on Japanese firms, RIETI Discussion Paper
Series 16-E-066

Niko S ¨underhauf1, Oliver Brock2, Walter Scheirer3, Raia Hadsell4, Dieter Fox5, J
¨urgenLeitner1, Ben Upcroft6, Pieter Abbeel7, Wolfram Burgard8, Michael Milford1, Peter
Corke1, The Limits and Potentialsof Deep Learning for Robotics,International Journal of
Robotics Research, 2018

https://medium.com/vsinghbisen/ai-in-robotics-use-of-artificial-intelligence-in- robotics-
726a4e9ade18

Markus Nowak, German Aerospace Center (DLR), Germany, markus.nowak/at/dlr.de,

Claudio Castellini German Aerospace Center(DLR), Germany, claudio.castellini/at/dlr.de
Carlo Massironi, Istituto di Psicologia e PsicoterapiaInterazionistaPsicopraxis, Italy,
carlo.massironi/at/gmail.com

Benjamin Arnold, Daniel Wohlrab, ChristophMeinecke, Danny Reuter, Jan Mehner. Design,
Manufacturing and Test of a High-Precision MEMS Inclination Sensor for Navigation
Systems in Robot-Assisted Surgery.International Journal of
Biomedical Science and Engineering. Vol. 6, No. 1, 2018, pp. 1-6. doi:
10.11648/j.ijbse.20180601.11

Jean Gallier and Jocelyn Quaintance, Department of Computer and Information Science,
University of Pennsylvania, Philadelphia, PA 19104, USA
https://www.seas.upenn.edu/~cis515/linalg-I.pdf