Content uploaded by N. M. Fonseca Ferreira
Author content
All content in this area was uploaded by N. M. Fonseca Ferreira on Sep 11, 2018
Content may be subject to copyright.
1
NAO ROBOT AS A DOMESTIC ROBOT
JESSICA P. M. VITAL
INESC TEC-INESC Technology and Science and
University of Tras-os-Montes and Alto Douro, Vila Real, Portugal
Email:Jessicavital_hotmail.com
ORCID: 0000-0002-1660-7718
N. M. FONSECA FERREIRA
INESC TEC - INESC Technology and Science and
Institute of Engineering Of Coimbra, Polytechnic Institute of Coimbra, and
Knowledge Research Group on Intelligent Engineering and Computing for Advanced
Innovation and Development (GECAD) of the ISEP/IPP, Portugal.
Email: nunomig@isec.pt
ORCID: 0000-0002-2204-6339
ANTONIO VALENTE
INESC TEC-INESC Technology and Science and
University of Tras-os-Montes and Alto Douro, Vila Real, Portugal
Email: avalente@utad.pt
ORCID: 0000-0002-5798-1298
Over the years robotics has made great progress. Nowadays, robots begin to be part of the
life of any person, designated social robotic. Humanoid robots are fascinating and have
several advantages, such as they can work in places where there is a risk of contamination,
risk of health, danger of life, places that are difficult to access. They also are able to access
different types of terrain and to climb stairs. NAO robot is currently the humanoid platform
with high sensory capacity that it has lower costs in the market. This robot is similar to
human in order to have a more real and natural with society. Using the capabilities of the
robot and adding other sensors, we can have a more powerful machine in our society. NAO
robot is presented in this paper as a domestic robot.
Keywords: NAO robot, wireless sensors, Humanoid robots, Domestic robots, object
recognition
1. Introduction
Over the years robotics has made great progress, nowadays robots begin to be part
of the life of any person, designated social robotics [1].
Humanoid robots are fascinating and have several advantages, such as they
can work in places where there is a risk of contamination, risk of health, danger
CLAWAR 2018: 21st International Conference on Climbing and
Walking Robots and the Support Technologies for Mobile Machines,
Panama City, Panama, 10-12 September 2018
2
of life, places that are difficult to access [2]. They also are able to access different
types of terrain and to climb stairs [3]. The behavior of humanoid robots produces
feelings that facilitate the communication between machine and man.
There are many cases where you need a machine similar to the man to be able
to replace it in your work environment [4].
In recent years, social robotic has seen the emergence of sophisticated
humanoid robots, as Honda Asimo and NAO [5].
We chose the platform NAO that is currently the humanoid platform with high
sensory capacity that it has lower costs in the market. This robot is similar to the
human in order to have a more real and natural interaction with society. NAO is
a good platform for software development because it is easy to learn how to
program and it has a high sensory ability.
This paper is divided into four sections. The first section gives a brief
introduction of different domestic robots. The second section presents NAO robot.
An extension of platform NAO using sensors and an architecture of recognize
objects using NAO robot is described in third section. Our conclusions are drawn
in the final section.
2. Domestic Robots
Domestic Robots can help you carry out all kinds of tasks at home, such as
cooking, cleaning, company, babysitting or answering questions. Science fiction
has come to fruition, and they are available to make people's lives easier by
dismissing people from household chores and giving them the opportunity to do
other leisurely things [6].
Nowadays all people use domestic robots in their homes, such as:
Roomba Vacuum: can vacuum the floor of the house alone [7];
Bimby: can cook alone meals, sweets or whatever the person wants;
Winbot: robot that clean the glass;
Husqvarna automower: robot that mows the lawn very efficiently.
The area of robots has been an area of great evolution appearing also robots
as: Zenbo, Kuri. The use of humanoid robots as domestic robots were appeared,
as, Pepper [8], Honda Asimo and NAO robot [5]. These robots are more
developed able to do different household tasks, thus becoming much more
expensive when compared with the simpler robots and that only perform one task.
To combat this situation we present the NAO robot, as a domestic robot.
3
3. NAO robot
NAO robot (figure 1) is humanoid robot developed by Aldebaran Robotics,
a French company. It has 58 cm in height and it weighs 5.4 kg which make it easy
to transport [9]. With twenty five degrees-of- freedom (DOF) and more than 50
sensors, NAO is a robust robot to develop a wide range of applications.
Figure 1- NAO robot
NAO is specially used as a social robot. NAO robot has a similar appearance
when compared with a human. NAO allows to perform several basic actions, such
as sitting, walking, picking up objects with your hands, among others.
NAO robot has a disadvantage, its autonomy. In normal use NAO just has 90
minutes of autonomy which makes this robot only used as proof of concept and
not as a daily instinctive use robot. On the other hand we can conclude that the
robot has several advantages, as it is easy to carry, because it is small and it is
light. It has equipped with two cameras, like human eyes and can speak and can
recognize the most popular languages in world [10]. Are so many applications
that NAO robot has been used, such as: sports and interaction with humans.
A. Rehabilitation
By cameras robot can see the movement of patients and avoid them if the
movement are correct or no [11]. NAO is able to replicate the movement of
humans, so it can explain to patient how to the correct movement [12, 13].
B. Autism Children
NAO robot has been used to help autistic children in improving their behavior
[15, 16]. The studied cases show that children suppress the autistic behavior
during human-robot interaction and they can maintain visual contact with NAO
[17].
4
C. Traditional Robotic Soccer
NAO robot participate in RoboCup (the World Championship of Robotics)
as a soccer playing NAO robot has been the star of the Standard Platform
League where robots are expected to operate fully autonomously [17, 18].
4. Nao robot as a domestic robot
In this section we present different architectures that can reach NAO robot as
a domestic robot. Firstly is presented an extension of NAO robot using sensors
and after is presented an architecture to recognize objects.
4.1. Platform using sensors
This architecture present the integration of three sensors to NAO robot (figure
2). To integrate the sensory network were chosen the following sensors:
Temperature sensor: LM35 sensor 545753 YWrobot.
Photoresistor Light sensor: 531289 ywrobot;
Gas sensor: MQ Series Gas Sensor Module L1te v1.0 sandbox
electronics
Figure 2- Architecture integrating three sensors to NAO robot
When integrating three sensors in Arduino, a set of collections is provided in
order to validate their operation against the accuracy and precision.
The Arduino is equipped with the Wireless Proto Shield by using SPI
Communication. This allows pairing both NAO and sensorial array using WIFI
802.11 [19]. Using Choreographe, the tool used to program the NAO, it is possible
to elaborate a set of tasks for the interaction with the general public.
5
An Arduino library called CoGasSensorShield was used. This library
allowed to receive a value (e.g., gas sensor) via Wifi from an Arduino board and
thus issue an alert when desired. Given the limitations of the library, it was
extended in order to access the three sensors previously chosen, and with the
respective intervals that had previously been analyzed. After this work of
adaptation, a project was developed in Choregraphe that allowed to execute a set
of movements and dialogues associated to the output of the program in Arduino
in order to promote the human-machine interaction.
Intervals of values for the presence of gas, high temperature and luminosity
were analyzed and elaborated. In the Arduino, an alert was sent via Wifi when
values outside these ranges were registered. It reads and analyzes the values that
the sensors transmit and throws an alert, if it justifies, and if it has in the presence
of a dangerous situation. So that the alert is given correctly, different parameters
have been stipulated. The Arduino continuously reads all sensor values and
processes this information and whenever there is a state change it alerts the robot.
NAO robot will transmit alerts in different situations that was predefined, in
situations of danger to people, taking into account the ambient temperature, gas
levels and brightness. If the sensors detect that ambient has a high level of
temperature and the light is less, the robot will transmit a fire alert. In case of an
alert, NAO tells people to evacuate and explains to them what is happening. The
alert is also given by sending a message directly to the responsible. In case of fire
the message will be sent directly to the firemen, with the address, in order to solve
the problem effectively and quickly.
4.2. Recognition Objects
Choreographe Software is the tool used to program the NAO, it is possible to
elaborate a set of tasks for interaction with the general public. Through this
program that we used to program NAO robot can learn the different objects so
that later it can identify them. As proof of concept we used five types of object to
recognize, such as, a banana, a bottle of water, a mobile phone and a medicine.
Objects of different areas that are essential in ambient assisting living.
First we used robot to capture different images with different objects. We
selected different objects in different positions and at different distances, in order
to create a dataset, so that the robot could distinguish the different objects. Then
the images were segmented. The contour of the object was made so that the robot
could distinguish it when the object is surrounded by other objects. After the
outline of each object, we indicate the name of the object and the position in which
it is.
6
All the information is sent to the robot so that it can memorize the different
images, the name of the different objects and their position so that the robot can
later distinguish the different objects in different circumstances.
Finally, the vision recognition module belonging to the Choreographe
program was used. We was used this module robot acquire an image in real time
and analyze, if him recognize they tell what it is.
One of the limitations of NAO robot is the memory, so as future work will be
created a cloud computing service. It is through the cloud computing service that
the robot can recognize objects more quickly and accurately. Cloud will have a
wide set of images of many objects in different positions so that the robot can
recognize all the existing objects in a more viable and faster way of processing.
Despite being connected to the cloud will always have the ability to recognize a
set of predefined objects, essences of that environment so that in case there is
some failure of connection to the cloud the robot with him in the same way do
their activities. In a house we may have one robot but we can have more than one.
Figure 3- Cloud Operating Diagram
In figure 3 we can observe a cloud operating diagram. There we see robots in
different places of the house communicating each other and communication with
the server. The server communicating with the cloud to obtain the information
and give it back to the robot.
5. Conclusion
NAO robot can perform different domestic tasks. NAO robot can walk, talk,
see and grab objects. Despite its basic functions, through cameras the robot can
recognize objects and people. Adding sensors to the robot, it is able to send
7
environmental alerts in dangerous situations. We can conclude that the robot is a
domestic robot capable of doing not only domestic tasks, but also doing company
or having a dialogue. Having a humanoid aspect and an affordable cost is a key
point in the acceptance of the robot by our society.
Acknowledgments
This work is financed by the ERDF - European Regional Development Fund
through the Operational Programme for Competitiveness and Internationalization
- COMPETE 2020 Program within project POCI-01-0145-FEDER-006961,and
by National Funds through the FCT - Fundação para a Ciência e a Tecnologia
(Portuguese Foundation for Science and Technology) as part of project
UID/EEA/50014/2013.
References
1.
T. Fong, I. Nourbakhsh and K. Dautenhahn, "A survey of socially
interactive robots," Robotics and Autonomous Systems, pp. 143-166, 2003.
2.
R. Calo, "Robots and privacy," 2010.
3.
A. Hornung, K. M. Wurm and M. Bennewitz, "Humanoid Robot
Localization in Complex Indoor Environments," in Intelligent Robots and
Systems (IROS), 2010.
4.
L. Takayama, W. Ju and C. Nass, "Beyond Dirty, Dangerous and Dull:
What Everyday People Think Robots Should Do," in Proceedings of the
3rd ACM/IEEE international conference on Human robot interaction ,
2008.
5.
I. Rodriguez, A. Astigarraga, E. Jauregi, T. Ruiz and E. Lazkano,
"Humanizing NAO robot teleoperation using ROS," in 14th IEEE-RAS
International Conference on Humanoid Robots (Humanoids), 2014.
6.
J. Carpenter, J. M. Davis, N. Erwin-Stewart, T. R. Lee, J. D. Bransford and
N. Vye, "Gender Representation and Humanoid Robots Designed,"
International Journal of Social Robotics, vol. 1, pp. 261-265, 2009.
7.
J. Forlizzi and C. DiSalvo, "Service robots in the domestic environment: a
study of the roomba vacuum in the home," in Proceedings of the 1st ACM
SIGCHI/SIGART conference on Human-robot interaction, 2006.
8.
J. Lafaye, D. Gouaillier and P.-. B. Wieber, "Linear Model Predictive
Control of the locomotion of Pepper,a humanoid robot with omnideirection
wheels," in Humanoid Robots (Humanoids), 2014 14th IEEE-RAS
International Conference on, 2014.
8
9.
D. Gouaillier, V. Hugel and P. Blazevic, "Mechatronic design of NAO
humanoid," in Robotics and Automation, 2009.
10.
S. Fojtu, M. Bresler and D. Prusa, "Nao Robot Navigation Based on a
Single VGA Camera," in 17th Computer Vision Winter Workshop, 2012.
11.
D. L. Recio, E. M. Segura, L. M. Segura and A. Waern, "The NAO models
for the elderly," in Proceedings of the 8th ACM/IEEE international
conference on Human-robot interaction, 2013.
12.
C. Stanton, A. Bogdanovych and E. Ratanasena, "Teleoperation of a
humanoid robot using full-body motion capture, example movements, and
machine learning," in Proceedings of Australasian Conference on Robotics
and Automation, 2012.
13.
J. Lei, M. Song, Z.-N. Li and C. Chen, "Whole-body humanoid robot
imitation with pose similarity evalution," Signal Processing, vol. 108, pp.
136-146, 2015.
14.
S. Shamsuddin, H. Yussof, L. I. Ismail, S. Mohamed, F. A. Hanapiah and
N. I. Zahari, "Initial Response in HRI- a Case Study on Evaluation of Child
with Autism Spectrum Disorders Interacting with a Humanoid Robot
NAO," International Symposium on Robotics and Intelligent Sensors , pp.
1448-1455, 2012.
15.
S. Shamsuddin, H. Yussof, L. I. Ismail, S. Mohamed, F. A. Hanapiah and
N. I. Zahari, "Humanoid Robot NAO Interacting with Autistic Children of
Moderately Impaired Intelligence to Augment Communication Skills,"
International Symposium on Robotics and Intelligent Sensors, pp. 1533-
1538, 2012.
16.
A. Tapus, A. Peca, A. Aly, C. Pop, L. Jisa, S. Pintea, A. Rusu and D.
David, "Children with autism social engagement in interaction with Nao, an
imitative robot : A series of single case experiments.," Interaction studies,
pp. 315-347, 2012.
17.
T. Niemuller, A. Ferrein , G. Eckel, D. Pirro, P. Podbregar, T. Kellner, C.
Rath and G. Steinbauer, "Providing Ground-truth Data for the NAO Robot
Paltform," RoboCup, pp. 133-144, 2010.
18.
L. M. Cruz, Humanoid Robot NAO: Developing Behaviors for Soccer
Humanoid Robots, LAP Lambert Academic Publishing, 2013.
19.
J. P. M. Vital, N. M. M. Rodrigues, M. S. Couceiro, C. M. Figueiredo and
N. M. F. Ferreira, "Fostering the NAO platform as an elderly care robot," in
Serious Games and Applications for Health (SeGAH), 2013.