Content uploaded by Risto Kojcev
Author content
All content in this area was uploaded by Risto Kojcev on Sep 10, 2018
Content may be subject to copyright.
Dissecting Robotics — historical overview and
future perspectives
Irati Zamalloa, Risto Kojcev, Alejandro Hern´
andez,
I˜
nigo Muguruza, Lander Usategui, Asier Bilbao and V´
ıctor Mayoral
Acutronic Robotics, April 2017
Abstract—Robotics is called to be the next technological
revolution and estimations indicate that it will trigger the fourth
industrial revolution. This article presents a review of some of
the most relevant milestones that occurred in robotics over the
last few decades and future perspectives. Despite the fact that,
nowadays, robotics is an emerging field, the challenges in many
technological aspects and more importantly bringing innovative
solutions to the market still remain open. The need of reducing the
integration time, costs and a common hardware infrastructure are
discussed and further analysed in this work. We conclude with a
discussion of the future perspectives of robotics as an engineering
discipline and with suggestions for future research directions.
Keywords—robotics, review, hardware, H-ROS, artificial intel-
ligence.
I. INTRODUCTION
The first use of the word ”Robot” dates back in 1921
and it was introduced by Karel ˇ
Capek in his play Rossum’s
Universal Robots. The play describes mechanical men that
are built to work on the factory assembly lines and that rebel
against their human masters [1]. The etymological origin of
the word Robot is from the Czech word robota, which means
servitude or forced labor.
The term ”Robotics” was first mentioned by the Russian-born
American science-fiction writer Isaac Asimov in 1942 in his
short story Runabout [1]. Asimov had a much brighter and
more optimistic opinion of the robot’s role in human society
compared to the view of Capek. In his short stories, he
characterized the robots as helpful servants of man. Asimov
defined robotics as the science that study robots. He created
the Three Laws of Robotics, that state the following:
•The First Law states that a robot should not harm a
person or let a person suffer damage because of their
inaction.
•Second Law states that a robot must comply with all
orders that a human dictates, with the proviso that
occurs if these orders were in contradiction with the
First Law.
•The Third Law states that a robot must take care of
its own integrity, except when this protection creates
a conflict with the First or Second Law.
Over the last decades, robotics evolved from fiction to reality
becoming the science and technique that is involved in the
design, manufacture and use of robots. Computer Science,
Electrical Engineering, Mechanical Engineering and Artificial
Intelligence (AI) are just some of the disciplines that are
combined in robotics. The main objective of robotics is the
construction of devices that perform user-defined tasks. The
rapid growth of the field in scientific terms had led the develop-
ment of different types of robots. Examples of different robotic
systems are: industrial robots, manipulators, terrestrial, aerial,
aquatic, research, didactic, entertainment robots or humanoids.
Section II covers the evolution of robotics over the last
decades including current trends. In Section III, we present the
future perspectives of robotics based on the historical overview
presented in II. In Section IV we conclude this work and
discuss our viewpoint for future development in robotics.
II. TH E EVO LU TI ON O F ROB OTICS
Figure 1illustrates a historical overview of the growth of
robotics, divided into four columns: the first column presents
the different robot generations, the second column (central)
shows some of the most relevant milestones and our vision
of the upcoming future of robotics, the third one the needs
and social impact of robotics, and the fourth summarizes the
different stages of development in robotics.
The progress of robotics is influenced by the technological
advances, for example, the creation of the transistor [3],
the digital computer [4], the numerical control system [5]
or the integrated circuits [6]. These technological advances
further enhanced the properties of the robots, and helped
them evolve from solely mechanical or hydraulic machines,
to programmable systems, which can even be aware of their
environment. Similar to other technological innovations,
robotics has advanced and changed taking into account the
needs of society.
Based on their characteristics and the properties of the robots,
we can classify the development of robotics into four genera-
tions:
A. Generation 0: Pre-Robots (up to 1950)
Characteristics:
•The first industrial robots were pneumatic or
hydraulic.
1
arXiv:1704.08617v1 [cs.RO] 27 Apr 2017
Figure 1. A historical overview of the most relevant milestones that occurred in robotics over the last decades. The timeline also provides an insight and the
vision of Erle Robotics for the future of robotics. c
Acutronic Robotics 2017. All Rights Reserved. A high resolution image is available at [2]
2
In 1495, the polymath Leonardo Da Vinci envisioned the
desing of the first humanoid [7]. In the following years, dif-
ferent machines were manufactured using mechanical elements
that helped the society and the industry. It was not until the
first industrial revolution that factories began to think about
automation as a way of improving manufacturing processes.
The automated industrial machines of this generation were
based on pneumatic or hydraulic mechanisms, lacking of any
computing capacity and were managed by the workers.
The first automation techniques were the punch cards [8], used
to enter information to different machinery (e.g. for controlling
textile looms). The first electronic computers, for example the
Colossus [9], also used punched cards for programming.
B. Generation 1: First Manipulators (1950-1967)
Characteristics:
•Lack of information regarding the environment.
•Simple control algorithms (point-to- point).
Due to the rapid technological development and the efforts
to improve industrial production, automated machines were
designed to increase the productivity. The machining-tool
manufacturers introduced the numerical controlled (NC)
machines which enabled other manufacturers to produce
better products [5]. The union between the NC capable
machining tools and the manipulators paved the way to the
first generation of robots.
Robotics originated as a solution to improve output and
satisfy the high quotas of the U.S. automotive industry. In
parallel the technological growth led to the construction of
the first digitally controlled mechanical arms which boosted
the performance of repeatable, ”simple” tasks such as pick
and place. The first acknowledged robot is UNIMATE
[10] (considered by many the first industrial robot), a
programmable machine created by George Devol and Joe
Engleberger that two years before funded the world’s first
robot company called Unimation (Universal Automation). In
1960, they secured a contract with General Motors to install
the robotic arm in their factory located in Trenton (New
Jersey). UNIMATE helped improve the production, which
further motivated many companies and research centers to
actively dedicate resources in robotics.
C. Generation 2: Sensorized robots (1968-1977)
Characteristics:
•More awareness of their surroundings.
•Advanced sensory systems: for example, force,
torque, vision.
•Learning by demonstration.
•These type of robots are used in the
automotive industry and have large footprint.
Starting from 1968, the integration of sensors marks the
second generation of robots. These robots were able to react
to the environment and offer responses that met different
challenges. Shakey [11], developed by Stanford Research
Institute, was the first sensorized mobile robot, containing a
diversity of sensors (for example tactile sensors) as well as a
vision camera.
During this period relevant investments were made in
robotics. In the industrial environment, we have to highlight
the PLC (Programmable Logic Controller) [12], an industrial
digital computer, which was designed and adapted for the
control of manufacturing processes, such as assembly lines,
robotic devices or any activity that requires high reliability.
PLCs were at the considered to be easy to program. Due to
these characteristics, PLCs became a commonly used device
in the automation industry.
In 1973, KUKA (one of the world’s leading manufacturers
of industrial robots) built the first industrial robot with 6
electromechanical-driven axes called Famulus [13]. One year
later, the T3 robot [14] was introduced in the market by
Cincinnati Milacron (acquired by ABB in 1990). The T3
robot was the first commercially available robot controlled by
a microcomputer.
D. Generation 3: Industrial robots (1978-1999)
Characteristics:
•Robots now have dedicated controllers (computers).
•New programming languages for robot control.
•Reprogrammable robots.
•Partial inclusion of artificial vision.
Many consider that the Era of Robots started in 1980 [15].
Billions of dollars were invested by companies all around
the world to automate basic tasks in their assembly lines.
The investments in automation solutions increased the sales
of industrial robots up to 80% compared to previous years.
Robots populated many industrial sectors to automate a wide
variety of activities such as painting, soldering, moving or
assembly.
Key technologies that still drive the development of
robots appeared during these years: general Internet access
was extended in 1980 [16], Ethernet became a standard in
1983 [17] (IEEE 802.3), the Linux kernel was announced in
1991 [18] and soon after, real-time patches started appearing
[19], [20] to increase the determinism of Linux-based systems.
The “robot programming languages” also became popular
during this time. For example, Unimation started using
VAL in 1979 [21] [22], FANUC designed Karel in 1988
[23] and in 1994 ABB created Rapid [24] making robots
re-programmable machines which also contained a dedicated
controller.
By the end of the 1990s, companies started thinking
about robots outside industrial environments. Among the
robots and kits created within this period, we highlight two
that became an inspiration for hundreds of roboticists:
•The first LEGO Mindstorms kit (1998) [25], a
3
set consisting of 717 pieces, including LEGO bricks,
motors, gears, different sensors, and a RCX Brick
with an embedded microprocessor to construct var-
ious robots using the same parts. The kit allowed
to teach the principles of robotics. Creative projects
have appeared over the years showing the potential of
interchangeable hardware in robotics.
•Sony’s AIBO (1999) [26], the world’s first enter-
tainment robot. Widely used for research and de-
velopment. Sony brought robotics to everyone with
a $1,500 robot that included a distributed hardware
and software architecture. The OPEN-R architecture
involved the use of modular hardware components
—e.g. appendages that can be easily removed and
replaced to change the shape and function of the
robots—, and modular software components that can
be interchanged to modify their behavior and move-
ment patterns. OPEN-R represented an inspiration
for future robotic frameworks and showed promise
to minimize the need for programming individual
movements or responses.
Sony’s AIBO and LEGO’s Mindstorms were built upon the
principle of modularity, both concepts were able to easily
exchange components and both of them presented common
infrastructures. Even though they came from the consumer
side of robotics, one could argue that their success was
strongly related to the fact that both products made use of
interchangeable hardware and software modules. The use of a
common infrastructure proved to be one of the key advantages
of these technologies.
E. Generation 4: Intelligent robots (2000-2017)
Characteristics:
•Inclusion of advanced computing capabilities.
•These computers not only work with data,
they can also carry out logical reasoning
and learn.
•Artificial Intelligence begins to be
included partially and experimentally.
•More sophisticated sensors that send informa-
tion to the controller and analyze it through
complex control strategies.
•The robot can base its actions on more solid
and reliable information.
•Collaborative robots are introduced.
The fourth generation of robots, dating from the 2000,
consisted of more intelligent robots that included advanced
computers to reason and learn. These robots also contained
more sophisticated sensors that helped them adapt more
effectively to different circumstances.
The robot Roomba [27] —the first vacuum cleaner domestic
robot— introduced the robots in many homes. YuMi [28],
the first collaborative robot included many advances in the
security systems beyond photoelectric barriers or interlocking
devices, ensuring the coexistence of worker and robot in the
same environment, improving the production process and
the ergonomics of the operator. These advances both on the
human-robot collaboration and improvements of the robot
security systems, have allowed the robots to work together
with humans in the same environment.
Among the technologies that appeared in this period we
highlight the Player Project [29] (2000, formerly the
Player/Stage Project), the Gazebo simulator [30] (2004) and
the Robot Operating System [31] (2007). Moreover, relevant
hardware platforms appeared during these years. Single Board
Computers (SBCs) like the Raspberry Pi [32] enabled millions
of users all around the world to easily create robots.
The following subsections will describe some relevant
observations our research obtained within this period:
1) Decline in Industrial robot innovation:Except for the
appearance of the collaborative robots in 2015, the progress
within the field of industrial robotics has significantly slowed
down compared to previous decades. While industrial robots
significantly improved their accuracy, speed or offer greater
load capacity, industrial robots regarding innovation up till
today are very stagnant.
2) The boost of bio-inspired Artificial Intelligence:Arti-
ficial Intelligence and, particularly, of neural networks became
relevant in this period as well. A lot of the important work
on neural networks occurred in the 1980’s and in the 1990’s,
however at that time computers did not have enough compu-
tational power. Data-sets were not big enough to be useful in
practical applications. As a result, neural networks practically
disappeared in the first decade of the 21st century. However,
starting from 2009, neural networks gained popularity and
started delivering good results in the fields of computer vision
(2012) [33] or machine translation (2014) [34]. During the last
years we have seen how these techniques have been translated
to robotics for tasks such as robotic grasping (2016) [35]. In
the coming years it is expected to see more innovations and
these AI techniques will have high impact in robotics.
3) Real-time communication solutions:According
to [36], since 2001 reputable industrial titans introduced
different Industrial real-time Ethernet standards (EtherCAT,
SERCOS, PROFINET, Ethernet/IP and Ethernet PowerLink)
represented in Figure 2. These solutions have been widely
used to criticize the deterministic and real-time capabilities of
traditional Ethernet. However they do not serve to standardize
the communications because the Industrial robots need
to adapt and speak the factory language that have been
chosen based on one of these technologies. This leads to
incompatibility between different robotic or automation
systems, therefore making integration task cumbersome.
4) A common infrastructure for robotics:An interesting
approach would be to have manufacturers agree on a common
infrastructure. Such an infrastructure could define a set of
electrical and logical interfaces (leaving the mechanical ones
aside due to the variability of robots) that would allow
industrial robot companies to produce robots and components
that could interoperate, be exchanged and eventually enter
into new markets. This would also lead to a competing
4
Figure 2. Comparison between different real-time, Ethernet-based fieldbuses.
As shown in this statistics EtherCAT is the most common automation
communication standard. Original source [36]
environment where manufacturers will need to demonstrate
features rather than the typical obscured environment where
only some are allowed to participate.
Integration effort was identified as one of the main issues
within robotics and particularly related to robots operating
in industry. A common infrastructure typically reduces the
integration effort by facilitating an environment where com-
ponents can simply be connected and interoperate. Each of
the infrastructure-supported components are optimized for
such integration at their conception and the infrastructure
handles the integration effort. At that point, components could
come from different manufacturers, yet when supported by a
common infrastructure, they will interoperate:
A hardware/software standardization is needed
”Currently, most of the time is spent dealing with the
hardware/software interfaces and much less is put into
behaviour development or real-world scenarios”
For robots to enter new and different fields, it seems reasonable
to accept that these robots will need to adapt to the environ-
ment itself. For industrial robotics, robots have to be fluent
with factory languages (EtherCAT, SERCOS, PROFINET,
Ethernet/IP and Ethernet PowerLink). One could argue that the
principle is valid for service robots (e.g. households robots that
will need to adapt to dish washers, washing machines, or media
servers), medical robots and many other areas of robotics.
Such reasoning led to the creation of the Hardware Robot
Operating System (H-ROS), a vendor-agnostic hardware and
software infrastructure for the creation of robot components
that interoperate and can be exchanged between robots.
Figure 3. Official logo of the Hardware Robot Operating System (H-ROS).
The image was inspired by the initial logo of the Robot Operating System
(ROS) with the consent of the ROS-community steered by the Open Source
Robotics Foundation (OSRF).
H-ROS is built on top of ROS, which is the de-facto standard
for robot software development [37]. In more detail, H-ROS
utilizes the functionality of ROS 2; a redesigned version of
the robot middleware that targets use cases not included in
the initial design of ROS.
The philosophy behind H-ROS is that creating robots should
be about placing together components that are compliant
with the standardized H-ROS interfaces, regardless of the
manufacturer. H-ROS aims to facilitate a fast way of building
robots choosing the best component for each use-case from
a common robot marketplace. It complies with different
environment requirements (industrial, professional, personal,
and others) where variables such as time constraints are
critical. Building or extending robots is simplified to the
point of placing H-ROS compliant components together. The
user simply needs to program the cognition part (in other
words, the brain) of the robot and develop their own use-
cases without facing the complexity of integrating different
technologies and hardware interfaces.
III. ENVISIONING THE FUTURE OF ROBOTICS
In order to predict the future of robotics we have analyzed
the historical growth of robotics, divided into the following
markets: industrial robots,professional robots and con-
sumer robots.
Figure 4. Summary and predictability of the distribution of robots in the
world, divided into three main markets: industrial robots, professional robots
and consumer or personal robots.
The presence of industrial robots led the growth of robotics
since its beginning, as shown in Figure 4, however, since
2000, the use and aim of many robot companies and initiatives
changed. A relevant amount of resources were invested into
getting robots outside of industrial environments. We can
distinguish two periods:
•1960-2000: boom of the automotive industry and
increased interest in industrial robots. Many started
including robots in their factories to increase produc-
tivity.
•Since 2000: robot development and innovations pivot
towards the consumer and professional markets which
opens the door for faster innovation cycles.
Figure 5illustrates the interest in robotics obtained from a joint
review of publications, conferences and events, solutions and
corporations:
5
Figure 5. The general interest in robotics since its inception obtained
from a joint review of publications, conferences and events, solutions and
corporations.
Generation 5: Collaborative and personal robots
Characteristics:
•Robots and humans share same environment and
collaborate.
•Reconfigurable robots.
•Robots help humans enhance every-day activities.
•Modular robots and components.
With latest developments in AI (e.g. AlphaGo beats the
world-class player in Go [38], an achievement that was not
expected for many years) being translated to robotics and the
recent investments in the field, there is a high expectation for
the future development of robotics. Our team believes that
the next generation robots will reflect all the technological
advances that developers and researchers have made in recent
years.
According to the characteristics of the 5th generation,
robots will be able to coexist with the humans, enhance
human capabilities, simplify and improve life. We foresee a
boom in collaborative and personal robots:
Figure 6. Envisioning the future robots.
The list presented in the Figure 6presents our perception
regarding the near future of robotics by taking into account
its technical feasibility.
IV. DISCUSSION AND CONCLUSIONS
Robotics did not grow as much as expected. Visionaries
predicted that by 2020 robots would be in our every day lives
helping with daily tasks. To the best of our knowledge, this
fact is highly unlikely, however the results obtained through
this research unveiled a promising future for the field. The
importance of robotics and its potential is being intensely
highlighted and a number of standardization bodies are taking
steps towards creating a common set of rules to govern the
interaction with these machines.
The following subsections reflect some of the most relevant
conclusions taken from our review:
A. Lack of compatible systems
•Hardware/software incompatibility: Building a new
robot is a bumpy road. The incompatibility between
components/elements/languages, take significant time
and effort leading to the fact that during development
of a new robotic solution most of the time is dedicated
in the integration and not to the behavior or developing
innovative solutions.
•Different programming languages and environ-
ments: In an attempt to dominate the market the
main industrial robots manufacturers had created their
own programming languages to keep their technol-
ogy as closed as possible. As consequence there are
many incompatible components/robots and integration
between components from different manufactures is
very cumbersome, time consuming process which
sometimes is not even feasible. In order to ”simplify”
integration effort many users decide to bound to
solutions provided from a single manufacturer which
increases the overall costs.
A common infrastructure for robot components is
needed, H-ROS to lead the change.
Making robotics hardware more affordable, versatile, and
“standardized” is hugely important for the field, as Aaron
Dollar, Francesco Mondada, Alberto Rodriguez, and Giorgio
Metta, who guest edited the special issue [39]:
”In the field of robotics, there has existed a relatively large
void in terms of the availability of adequate hardware,
particularly for research applications. The few systems that
have been appropriate for advanced applications have been
extremely costly and not very durable. For those and other
reasons, innovation in commercially available hardware is
extremely slow, with a historically small market and
expensive and slow development cycles. Effective open
source hardware that can be easily and inexpensively
fabricated would not only substantially lower costs and
increase accessibility to these systems, but would drastically
improve innovation and customization of available
hardware.”
•The Industrial robot industry —–will it remain
only a supplier industry?— For some, the indus-
6
trial robot industry is a supplier industry. It supplies
components and systems to larger industries, mainly,
the manufacturing industry. These groups argue that
the manufacturing industry is dominated by the PLC,
motion control and communication suppliers which
together with the big customers are setting the stan-
dards to capitalize on the cost savings from Ethernet
by extending their own standard to include Ethernet. In
doing so, their customers receive some of the benefits
from Ethernet but are still locked into the proprietary
networks for the long term. Frequently forgotten in
these discussions is the fact that it is not just technical
properties such as performance and transfer rates that
count, it is also the soft facts like ease of imple-
mentation, openness, vendor independence, risk avoid-
ance, conformity, interoperability, long-term availabil-
ity, and overall distribution that makes a standard
gain acceptance and even thrive. The Industrial robots
need to adapt and speak factory language (such as,
PROFINET, ETHERCAT, Modbus TCP, Ethernet/IP,
CANOPEN, DEVICENET) which for each factory,
might be different. As a result, most robotic peripheral
manufacturers suffer from supporting many different
protocols which requires a lot of development time
that does not add functionality to the product.
•Competing by obscuring is slowing industry
The close attitude of most industrial robot companies
is typically justified by the existing competition in
this environment. Such attitude leads to a lack of
understanding between different manufacturers and
solutions but in exchange, some believe that it secures
clients and favours competition. Our results indicate
that this behavior is slowing progress, innovation and
new solutions in the field of industrial robots.
B. The hype cycle of robotics
Robotics, like many other technologies, suffered from an
inflated set of expectations which resulted in a decrease of the
developments and results during the 1990s. Figure 5pictured
the evolution of the general interest in robotics. Such graph
displays a well known trajectory typically known as the hype
cycle [40]. Figure 7pictures the hype cycle as defined by
Linden and Fenn. The graph illustrates the five different states
that a technology goes through before entering mass-adoption:
a) technology trigger, b) peak of inflated expectations, c)
trough of disillusionment, d) slope of enlightenment and e)
plateau of productivity.
Comparing Figures 5and 7we conclude that the state
of robotics is past the ”second-generation products, some
services” and somewhere within the slope of enlightenment.
Industrial robots on the rise
Initiatives such as the U.S. Advanced Robotics for
Manufacturing (ARM) Institute are pushing the boundaries
of industrial robots once again [41]. Collaborative robots are
increasingly improving the performance of the manufacturing
processes while improving the interaction with humans.
Figure 7. Gartner’s Hype Cycles offer an overview of relative maturity
of technologies in a certain domain. They provide not only a scorecard to
separate hype from reality, but also models that help enterprises decide when
they should adopt a new technology. [40].
Robots everywhere
Robots and automation are actively being introduced in many
disciplines. With the growing popularity of such systems,
we observe a transition that goes from mass manufacturing
to a mass customization, particularly for industrial robots.
Increasingly, personal (e.g. cleaning robots) and professional
robots (e.g. service robots) are also demanding such
customizations. We foresee that an infrastructure such as
H-ROS will favor the creation of modular robots whose
components could be easily exchanged or replaced meeting
the growing needs for customization.
C. Artificial Intelligence (AI) taking over:
Current robot systems are designed by teams with multi-
disciplinary skills. The design of the control mechanisms is
one of the critical tasks. Typically, the traditional approach to
design such systems require going from observations to final
control commands through a) state estimation, b) modeling
and prediction, c) planning and d) low level control (for
example, inverse kinematics). This whole process requires
fine tuning every step of the funnel incurring into a relevant
complexity where optimization at every step have a direct
impact in the final result.
The work of Levine et al. [35] shows a promising path
towards simplifying the construction of robot behaviors
through the use of deep neural networks as a replacement
of the whole funnel described above1. Our team envisions
that the use of deep neural networks will become of great
relevance in the field of robotics in the coming years. These
abstractions will empower roboticists to train robot models in
specific applications (end-to-end) empowering engineers and
robots to tackle more complex problems.
1The use of neural networks could also replace individual tasks within the
funnel.
7
Robots are going to change the society, in the same way
computers changed our life. The introduction of robotics
in our society will be disruptive. Work, communication,
transportation and even social life will be affected by robotics.
This will lead to change from mass customization to mass
integration, so that robots and humans coexist helping each
other.
ACKNOWLEDGMENT
This review was funded and supported by Acutronic
Robotics2, a firm focused on the development of next-
generation robot solutions for a range of clients.
REFERENCES
[1] K. Low, Industrial Robotics: Programming, Simulation and
Applications, ser. ARS, Advanced robotic systems international.
Pro-Literatur-Verlag, 2007. [Online]. Available: https://books.google.
es/books?id=xj37AX VqHYC
[2] E. Robotics, “Envisioning robotics,” Official Webpage, April 2017.
[Online]. Available: http://erlerobotics.com/envisioning-robotics/
[3] P. K. Bondyopadhyay, “In the beginning [junction transistor],” Proceed-
ings of the IEEE, vol. 86, no. 1, pp. 63–77, Jan 1998.
[4] A. E. Bryson, “Optimal control-1950 to 1985,” IEEE Control Systems,
vol. 16, no. 3, pp. 26–33, Jun 1996.
[5] A. E. Middleditch, Survey of numerical controller technology. Pro-
duction Automation Project, University of Rochester, 1973.
[6] A. Saxena, Invention of Integrated Circuits: Untold Important Facts,
ser. International series on advances in solid state electronics
and technology. World Scientific, 2009. [Online]. Available: https:
//books.google.es/books?id=-3lpDQAAQBAJ
[7] B. Gates, “A robot in every home,” Scientific American, vol. 296, pp.
58–65, 2007.
[8] B. Trikha, “A journey from floppy disk to cloud storage,” International
Journal on Computer Science and Engineering, vol. 2, no. 4, pp. 1449–
1452, 2010.
[9] B. Copeland, “Colossus: its origins and originators,” IEEE Annals of
the History of Computing, vol. 26, no. 04, pp. 38–45, 2004.
[10] P. Mickle, “A peep into the automated future,” The Trentonian, 1961.
[Online]. Available: http://www.capitalcentury.com/1961.html
[11] M. V. Georges Giralt, Raja Chatila, “An integrated navigation and
motion control system for autonomous multisensory mobile robots,”
in Autonomous Robot Vehicles, vol. 7. Springer New York, 1990, pp.
420–443.
[12] L. Bryan and E. Bryan, “Programmable controllers,” 1988.
[13] S. Shepherd and A. Buchstab, “Kuka robots on-site,” in Robotic
Fabrication in Architecture, Art and Design 2014. Springer, 2014,
pp. 373–380.
[14] M. R. Cutkosky and P. K. Wright, “Position sensing wrists for industrial
manipulators.” DTIC Document, Tech. Rep., 1982.
[15] J. Maeda, “Current research and development and approach to future
automated construction in japan,” Construction Research Congress
2005: Broadening Perspectives, pp. 1–11, 2005.
[16] M. Castells, “Lessons from the history of the intenet,” in The Internet
galaxy: Reflections on the Internet, business, and society. Oxford
University Press, 2002, pp. 20–33.
[17] S. Yu, “Ieee 802.3TM ’standard for ethernet’ marks 30 years of innova-
tion and global market growth,” IEEE Standards Association, 2013.
[18] M. C. Daniel P. Bovet, “Understanding the linux kernel: from i/o ports
to process management,” vol. 3. O’Reilly Media, 2005.
[19] M. Barabanov, “A linux–based real–time operating system,” New Mex-
ico Institute of Mining and Technology, Tech. Rep., 1997.
2www.acutronicrobotics.com
[20] V. Yodaiken, “Cheap operating systems research and teaching with
linux,” Tech. Rep., 1996.
[21] K. Srihari and M. P. Deisenroth, Robot Programming Languages—
A State of the Art Survey. Berlin, Heidelberg: Springer Berlin
Heidelberg, 1988, pp. 625–635. [Online]. Available: http://dx.doi.org/
10.1007/978-3- 642-73890- 6 76
[22] W. A. Gruver, B. I. Soroka, J. J. Craig, and T. L. Turner, “Industrial
robot programming languages: A comparative evaluation,” IEEE Trans-
actions on Systems, Man, and Cybernetics, vol. SMC-14, no. 4, pp.
565–570, 1984.
[23] J. Lapham, “RobotscriptTM : the introduction of a universal robot
programming language,” Industrial Robot: An International Journal,
vol. 26, no. 1, pp. 17–25, 1999. [Online]. Available: http:
//dx.doi.org/10.1108/01439919910250188
[24] J. Hollingum, “Abb focus on “lean robotization”,” Industrial Robot:
An International Journal, vol. 21, no. 4, pp. 15–16, 1994. [Online].
Available: http://dx.doi.org/10.1108/01439919410068140
[25] D. C. Cliburn, “Experiences with the lego mindstorms throughout the
undergraduate computer science curriculum,” in Proceedings. Frontiers
in Education. 36th Annual Conference, Oct 2006, pp. 1–6.
[26] M. Fujita, “On activating human communications with pet-type robot
aibo,” Proceedings of the IEEE, vol. 92, no. 11, pp. 1804–1813, Nov
2004.
[27] J. Jones, N. Mack, D. Nugent, and P. Sandin, “Autonomous
floor-cleaning robot,” Apr. 26 2005, uS Patent 6,883,201. [Online].
Available: https://www.google.com/patents/US6883201
[28] A. group, “Abb introduces yumi R
, world’s first truly
collaborative dual-arm robot,” ABB Press release, 2015.
[Online]. Available: http://www04.abb.com/global/seitp/seitp202.
nsf/0/5869f389ad26c612c1257e26001c974c/$file/15 23+GPR+YuMi+
Hannover+pr.pdf
[29] A. H. Brian P. Gerkey, Richard T. Vaughan, “The player/stage
project: Tools for multi-robot and distributed sensor systems,”
11th International Conference on Advanced Robotics (ICAR 2003),
vol. 1, pp. 317–323, 2003. [Online]. Available: http://robotics.usc.edu/
∼gerkey/research/final papers/icar03-player.pdf
[30] N. Koenig and A. Howard, “Design and use paradigms for gazebo,
an open-source multi-robot simulator,” in 2004 IEEE/RSJ International
Conference on Intelligent Robots and Systems (IROS) (IEEE Cat.
No.04CH37566), vol. 3, 2004, pp. 2149–2154.
[31] W. Garage, “Robot operating system,” 2009. [Online]. Available:
Robotoperatingsystem
[32] M. Richardson and S. Wallace, Getting Started with Raspberry Pi,
ser. EBSCOhost ebooks online. O’Reilly Media, 2012. [Online].
Available: https://books.google.es/books?id=xYhMlilTwC4C
[33] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification
with deep convolutional neural networks,” in Advances in neural
information processing systems, 2012, pp. 1097–1105.
[34] I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning
with neural networks,” in Advances in neural information processing
systems, 2014, pp. 3104–3112.
[35] S. Levine, P. Pastor, A. Krizhevsky, and D. Quillen, “Learning hand-eye
coordination for robotic grasping with deep learning and large-scale
data collection,” CoRR, vol. abs/1603.02199, 2016. [Online]. Available:
http://arxiv.org/abs/1603.02199
[36] Kingstar, “White paper: 5 real-time, ethernet-based fieldbuses com-
pared,” Kingstar, Tech. Rep., January 2016.
[37] M. Quigley, K. Conley, B. Gerkey, J. Faust, T. Foote, J. Leibs,
R. Wheeler, and A. Y. Ng, “Ros: an open-source robot operating
system,” in ICRA workshop on open source software, vol. 3, no. 3.2.
Kobe, 2009, p. 5.
[38] C. S. Lee, M. H. Wang, S. J. Yen, T. H. Wei, I. C. Wu, P. C. Chou, C. H.
Chou, M. W. Wang, and T. H. Yan, “Human vs. computer go: Review
and prospect [discussion forum],” IEEE Computational Intelligence
Magazine, vol. 11, no. 3, pp. 67–72, Aug 2016.
[39] A. Dollar, F. Mondada, A. Rodriguez, and G. Metta, “Open-source and
widely disseminated robot hardware [from the guest editors],” IEEE
Robotics & Automation Magazine, vol. 24, no. 1, pp. 30–31, 2017.
[40] A. Linden and J. Fenn, “Understanding gartner’s hype cycles,” Strategic
Analysis Report NoR-20-1971. Gartner, Inc, 2003.
8