Introduction to Cloud Robotics

Abstract

Cloud Robotics was born from the merger of service robotics and cloud technologies. It allows robots to benefit from the powerful computational, storage, and communications resources of modern data centers. Cloud robotics allows robots to take advantage of the rapid increase in data transfer rates to offload tasks without hard real time requirements. Cloud Robotics has rapidly gained momentum with initiatives by companies such as Google, Willow Garage, and Gostai as well as more than a dozen active research projects around the world. The presentation summarizes the main idea, the definition, the cloud modell composed of essential characteristics, service models and deployment models, planning task execution and beyond. Finally some cloud robotics projects are discussed.

Full text

Introduction to Cloud Robotics
Gyula Mester
Óbuda University,
Bánki Donát Faculty of Mechanical and Safety Engineering, Doctoral School of Safety and Security Sciences
mester.gyula@bgk.uni-obuda.hu
Bécsi út 96/b, Budapest, Hungary
Abstract – Cloud Robotics was born from the merger of service robotics and cloud technologies. It allows robots to benefit from
the powerful computational, storage, and communications resources of modern data centers. Cloud robotics allows robots to take
advantage of the rapid increase in data transfer rates to offload tasks without hard real time requirements. Cloud Robotics has
rapidly gained momentum with initiatives by companies such as Google, Willow Garage, and Gostai as well as more than a dozen
active research projects around the world. The presentation summarizes the main idea, the definition, the cloud modell composed
of essential characteristics, service models and deployment models, planning task execution and beyond. Finally some cloud
robotics projects are discussed.
Keywords – service robotics, cloud technologies, robotics, cloud robotics, the definition, service models.
1. WHAT IS CLOUD ROBOTICS?
Cloud Robotics (CR) was born from the merger of
cloud technologies and service robotics, which was
preceded by a change in paradigm in both domains
[1]. It allows robots to benefit from the powerful
computational, storage, and communications
resources of modern data centers.
Cloud robotics allows robots to take advantage of the
rapid increase in data transfer rates to offload tasks
without hard real time requirements.
The term “cloud-enabled robotics” was presented by
James Kuffner for the first time at the IEEE RAS Int.
Conference on Humanoid Robotics in 2010. He was
first to point out the potential of distributed networks
combined with robotics, primarily to enhance the robot
[2].
Cloud Robotics has rapidly gained momentum with
initiatives by companies such as Google, Willow
Garage and Gostai as well as more than a dozen
active research projects around the world. The
increasing number of robots with up to date knowledge
will become a true helping hand for humans.
In 2011, at the Google I/O developer Conference,
Google and Willow Garage introduced their theory and
foreseen application of Cloud Robotics [3].
Cloud Robotics is currently driving interest in both
academia and industry, combines robot technology
with network and Cloud-computing infrastructure that
connects amount of robots, sensors, portable devices
and most important a data-center (Fig. 1).
Driven by advances in mobile communication
technologies, more and more robotics applications can
be executed in the cloud [4].
Fig. 1.
Cloud computing service models, the concept
of Robot as a Service and Cloud Robotics
2. ROBOTICS SCHOOL AND CLOUD ROBOTICS
The robotics school and cloud robotics complement
each other. The increasing number of robots with up to
date knowledge will become a true helping hand for
humans. Cloud robotics is the use of a cloud
computing to share resources and learning among
robots through the internet [5]. The robotics cloud
needs the robotics school to provide a standard coding
system, knowledge structures and resources, and a
method by which robots can be certified to serve in
various fields [6-7]. A robotics school is a collection of
data pools, resources pools and service clusters for
robots with advanced intelligence, it also has a

knowledge coding standard together with an
authentication standard for robots. A robotics school is
based on the concept of the robotics cloud; it is also
the key element for building the robotics cloud. The
concept of a robotics school mainly includes three
aspects:
admittance,
teaching, learning,
testing and graduating.
Hardware functionality must meet the hardware
requirements for specific activity areas without too
much encoding in software. A model of a robotics
school is shown in Fig. 2.
Fig. 2. A model of a robotics school
3. ROBOT WEB TOOLS
Robot Web Tools is designed to enable Web
developers, roboticists, and even students to start
building a robot Web application quickly [8-10]. A
variety of routes are available for architecting a robot
web application. A common route is building web
technologies on an existing robot framework. The
Robot Operating System (ROS) is one of the more
popular robot middle wares to build upon. Currently
available tutorials include interfaces for navigation a
quadrotor (Fig. 3.).
Fig. 3. Tutorial interface for quad-rotor navigation
ROS (Robot Operating System) provides libraries and
tools to help software developers create robot
applications. It provides hardware abstraction, device
drivers, libraries, visualizers, message-passing, packa-
ge management, and more. ROS is licensed under an
open source, BSD license [8-9].
4. CLOUD ROBOTICS PROJECTS
Finally some Cloud Robotics projects are
discussed.
With the RoboEarth Databases and its Cloud
Engine, RoboEarth provides an open-source Cloud
Robotics framework that allows robots to share
knowledge via a www-style database and access
powerful robotic cloud services [4]. Source code and
documentation are available via RoboEarth’s Software
Components page.
Rosbridge focuses on bridging communication
between a robot and single ROS environment in the
cloud. Available open-source via [11].
The RosJava library allows to run ROS on Android
phones. While not strictly a cloud robotics project, it
allows ROS developers to use Android devices to
connect to (human) cloud services such as Google
Goggles. Available open-source via [12].
The DAvinCi Project showed the advantages of
cloud computing by parallelizing a SLAM algorithm
using a Hadoop cluster [13].
The Cloud-Based Robot Grasping project uses
Google’s Object Recognition Engine to recognize and
grasp common household objects.
GostaiNet offers to execute robot behaviors such
as vision and speech algorithms on compatible robots
in the cloud. GostaiNet provides seamless control of
any robot, using a web browser from anywhere in the
world. Gostai can host the services on the GostaiNet
robotics cloud [14].
5. GPS NAVIGATION OF QUAD-ROTOR
The four rotor flying robot - a quad-rotor is a four
rotor helicopter. A quad-rotor helicopter is controlled by
varying the rotors speed, thereby changing the lift
forces. It is an under-actuated dynamic vehicle with
four input forces and
six outputs coordinates.
One of the advantages of using a multi-rotor
helicopter is the increased payload capacity.
The quad-rotors are highly maneuverable, which
enables vertical take-off/landing, as well as flying into
hard to reach areas [15-19].The quad - rotor is
installed:
- a GPS sensor is used to detect the present
position.
Quad-rotor is requested to track the imposed
trajectory between the particular points (j=1,…,n) with
satisfactory precision keeping the desired attitude and
height of flight.
Quad-rotor checks for the current position (X and Y)
by use of a GPS sensor and/or electronic compass.

Trajectory of quad-rotor can be introduced by GPS
coordinates, e. g.
)( jPGPS
as shown in Fig. 4.
Fig. 4. Quad-rotor localization and navigation with
respect to the imposed GPS coordinates
Quad-rotor checks for the current position (X and Y)
by use of a GPS sensor and/or electronic compass.
Also, the altitude is measured by a barometric sensor.
On-board microcontroller calculates the actual
position deviation from the imposed trajectory given by
successive GPS positions
)( jPGPS
.
It localizes itself with respect to the nearest trajectory
segment (by calculation of the distances δ1or δ2).
Using the gyroscope, quad-rotor determines desired
azimuth of flight α (Fig. 4) and keeps the desired
direction of flight.
Height of flight is also controlled to enable
performance of the imposed mission (task).
The corresponding Google Earth map is utilized to
provide corresponding GPS coordinates of the quad-
rotor trajectory as presented in Fig. 5.
Fig. 5. Google-Earth map of the lake used to define
desired GPS trajectory of the quad-rotor flying robot
GPS coordinates:
longitude, latitude and altitude,
defined in the map and given in the Fig. 6, are used
to calculate quad-rotor trajectory in the earth frame.
Fig. 6. GPS coordinates acquired from the Google
Earth map and used for determination of the desired
quad-rotor trajectory
Corresponding model of the trajectory given in earth
frame is presented in Fig. 7.
Fig. 7. Multi-segment trajectory model of the quad-
rotor determined in the earth inertial frame
6. CLONCUSIONS
Cloud robotics allows robots to take advantage of
the rapid increase in data transfer rates to offload
tasks without hard real time requirements.
Cloud Robotics has rapidly gained momentum with
initiatives by companies such as Google, Willow
Garage, and Gostai as well as more than a dozen
active research projects around the world.
It allows robots to benefit from the powerful
computational, storage, and communications
resources of modern data centers.
The presentation summarizes the main idea, the
definition, the cloud model composed of essential
characteristics, service models and deployment
models, planning task execution and beyond.
Cloud computing can enable cheaper, lighter,
smarter robots.

The infrastructure exists and is rapidly evolving in
terms of performance and accessibility. Finally some
cloud robotics projects are discussed.
7. REFERENCES:
[1] S. Jordán, T. Haidegger, L. Kovács, I. Felde and I.
Rudas, "The Rising Prospects of Cloud Robotic
Applications", Proceedings of the ICCC 2013,
IEEE 9th International Conference on Computati-
onal Cybernetics, July 8-10, 2013, Tihany, Hunga-
ry, pp. 327-332.
[2] J. Kuffner, "Cloud-Enabled Robots". In proc. of
the IEEE Intl. Conf. on Humanoid Robots,
Nashville, 2010.
[3] D. Kohler, R. Hickman, K. Conley and B. Gerkey,
"Cloud Robotics". Google I/O 2011 Developer
Conference, 2011.
[4] http://roboearth.org/cloud_robotics (October 17,
2014)
[5] http://tech-salad.com/cloud-robotics (October 17,
2014)
[6] Fuji Ren, "Robotics Cloud and Robotics Schoo"l,
Proceedings of the 7th IEEE International Confe-
rence Natural Language Processing and Know-
ledge Engineering (NLP-KE), ISBN: 978-1-61284-
729-0, DOI: 10.1109/NLPKE.2011.6137767, To-
kushima, 27-29 Nov. 2011. pp. 1-8.
[7] Gyula Mester, "Distance Learning in Robotics",
Proceedings of the Third International Conferen-
ce on Informatics, Educational Technology and
New Media in Education, ISBN 86-83097-51-X,
Sombor, Serbia 2006, pp. 239-245.
[8] Brandon Alexander, Kaijen Hsiao, Chad Jenkins,
Bener Suay, and Russell Toris, "Robot Web
Tools", IEEE Robotics & Automation Magazine,
DOI: 10.1109/MRA. 2012.2221235, December
2012, pp. 20-23.
[9] http://robotwebtools.org (October 17, 2014)
[10] Zlatko Covic, "Development and Implementation of
Location Based Native Mobile Applications",
Proceedings of the 32nd International Conference
Science in Practice, Osijek, Croatia, October 15-
17, 2014, pp. 1-4.
[11] http://wiki.ros.org/rosbridge_suite (October 17,
2014)
[12] http://ros.org (October 17, 2014)
[13] Arumugam R., Enti V.R., Liu Bingbing, Wu Xiaojun,
Baskaran K., Foong Foo Kong, Kumar, A.S., Kang
Dee Meng, Goh Wai Kit, "DAvinCi: A cloud
computing framework for service robots",
Proceedings of the IEEE International Conference
on Robotics and Automation (ICRA), Anchorage,
AK, ISSN: 1050-4729, ISBN: 978-1-4244-5038-1,
DOI: 10.1109/ROBOT.2010. 5509469, 3-7 May,
2010, pp.3084 – 3089.
[14]http://www.gostai.com/activities/consumer/index.htm
l#gostainet (October 17, 2014)
[15] A Rodić, K Addi, " Mathematical Modeling of
Human Affective Behavior Aimed to Design Robot
EI-Controller", Book: New Trends in Medical and
Service Robots, Springer International Publishing
2014:(1, 1), pp. 141-162.
[16] Dr Rajnai Zoltán, " Új kommunikációs technológiák
a védelmi szektorban: New Communication
Technologies in the Defense Sector", Bánki
Közlemények 2013:(1) pp. 1-11.
[17] Aleksandar Rodic, Gyula Mester, " Modeling and
Simulation of Quad-Rotor Dynamics and Spatial
Navigation", Proceedings of the SISY 2011, 9th
IEEE International Symposium on Intelligent
Systems and Informatics, ISBN: 978-1-4577-1973-
8, DOI: 10.1109/SISY.2011.6034325, Subotica,
[18] Orosz Tamás, Vajda István, " Power Transformer
Design Optimization with Geometric Program-
ming.", In: Dr Janis Zakis (Edit.) Topical Problems
in the Field of Electrical and Power Engineering:
Doctoral School of Energy and Geotechnology II.,
Tallinn, Elektrijam, ISBN: 978-9985-69-055-0,
Parnu, Estonia, 2014.01.13-18, pp. 199-205.
[19] Gyula Mester, Aleksandar Rodic, " Simulation of
Quad-rotor Flight Dynamics for the Analysis of
Control, Spatial Navigation and Obstacle Avoidan-
ce ", Proceedings of the 3rd International Workshop
on Advanced Computational Intelligence and Intel-
ligent Informatics, IWACIII 2013, ISSN2185-758X,
Shanghai, China, October 18-21, 2013, pp. 1-4.