Content uploaded by Anas Tahir
Author content
All content in this area was uploaded by Anas Tahir on Feb 23, 2016
Content may be subject to copyright.
Humanoid Robots for children with Autism:
Experiences with Robosapien and NAO
Anas Tahir
Department of Electrical Engineering
KINDI Research Center, Qatar University
Doha, Qatar
at1003225@qu.edu.qa
Uvais Qidwai
Department of Computer Science and Engineering
KINDI Research Center, Qatar University
Doha, Qatar
uqidwai@qu.edu.qa
Abstract—Autism Spectrum Disorder (ASD) impacts many
families in the gulf region, especially in Qatar (prevalence rate is not
officially specified yet). This paper presents a brief review of different
existing robotic or computer based solutions for therapy of Autistic
children and focuses on the use of NAO and Robosapien robots in
this context in Qatar. Many solutions are present in the market but
most renowned and popular solutions are summarized in this paper
in order to have insight of the work done for the therapy of Autistic
patients. The main objective of this review paper is to give a quick
and brief overview of existing technologies with emphasis on NAO
and Robosapien robots in order for new researchers to break new
grounds in to the field of Autistic therapy using robotic solutions.
There are various solutions present in the market which can be
interfaced or programmed in order to interact with the Autistic
children by dexterous movement, speech and mobility functions.
These assist in enhancing learning for such children, enabling them
to adjust in the society around them, have more focus and increase
attention span etc.
Keywords—Autism Spectrum Disorder (ASD); Human Robot
Interface (HRI); NAO; Robosapiens; Humonoid robots.
I. INTRODUCTION
Autism Spectrum Disorders (ASD) are neurodevelopmental
disorders in which a person have abnormal social interaction,
impaired communication and language abilities and imitational
behavior [15]. Children who suffer from ASD prefer to have
same unchangeable routine on daily basis, as change annoys
them. They can learn through imitation and joint attention
methodologies as well as similar tools to help them overcome
the barriers created between them and the society around them.
Prevalence rate of ASD in US is 1 out of every 88 newborn
being diagnosed as ASD affected [15]. This prevalence rate is
really high in gulf region, and continuously increasing,
therefore it is one of the problem Qatar is investing in. The
study of exact prevalence rate is undergoing, but still there no
exact figure to define it. There are many different schools being
established in Qatar to help children with ASD. Following is an
account of various therapeutic methods used in these schools
for children with ASD.
A. Diagnosis and Therapies
There is no specific cause of ASD, it can be said that ASD
is caused due to genetic or environmental factors. There are
many different set number of diagnosis methods, such as neuro
imaging and behavior analysis can be used to indicate that a
child is suffering from ASD. Therapies, on the other hand, are
tailored to child’s need, as ASD is not same from one child to
the other. Behavioral therapies have been set following
standards, but they are mostly effective at younger age [21].
There is a therapy for Early and Intensive Behavioral
Intervention (EIBI) in which for two years 40 hours per week
of educational therapy is focused upon. Most of the behavioral
therapies have fixed durations, some have to be implemented
by the family members of the autistic child. There are many
different therapies presented in the book [21], from which it is
clear that these therapies are affective at young age therefore
the focus group in this paper is children of the ages between 5
and 11 years.
B. Different technologies used for Autism Therapy
There are many different technologies being used to help
autistic children to become independent in the future or in the
long run in their lives. Most of the technologies in use for
aiding the autistic children fall into one of the following
technological groups [16]:
1) Virtual Reality applications or environment
It includes technologies that depict the environment, as 3D
room etc.
2) Dedicated applications or Interactive environment
Includes tablets, computers and mobile phones, dedicated
technologies to autistic child
3) Telehealth systems or telerehablitation systems
Includes devices through which the health condition of the
autistic child can be monitored
4) Robots or avatars
Devices through which different behavioral therapies or
diagnosis techniques be implemented
It has been seen that the use of robots with autistic children
has shown great improvements in their behavioral and learning
related therapies.
C. Role of Robots
Robots used for autistic children have been shown to have
made tremendous amount of difference in 4 different areas of
therapy. Specifically, social learning, imitation skills,
communication and interaction with society. Robots for autism
have been focus of study since late 20th century but recently it
made a boom due to technological advancement [13]. In paper
[13] in (table 4), it shows different therapies are being devised
using robots in different countries and what are results of them.
It is clearly seen that robots have made lives of autistic children
easier, and helped them tremendously.
It is necessary to see the ethical issues related to the robots,
paper [12] shows that robots are ethically accepted specially
robots which are implemented with supervision. It can also be
seen that the robots which are being developed for autistic
children are safe by following some specific standards, and a
child is more comfortable in interaction with a robots as it is
similar to a human but at the same time it is also a toy for them.
II. BACKGROUND
Robots have been developed and created for really long
since the first machine came out in early 20th century. Human
robot interface (HRI) have been one of the topics being studied
and made it possible nowadays, as the survey on HRI clearly
points out in the paper, how HRI have changed lives and
flourished with time [11]. To help and contribute to the society
and technological advancement, machines are widely used, and
robots have played a really important role to aid.
Paper [9] presented many different robots that are being
used to help autistic children. It is a brief survey on robots’
roles and their benefits. Robots paper [9] presented are Bobus,
CHARLIE, CPAC, Diskcat, FACE, HOAP-2, Infanoid,
IROMEC, Jumbo, KASPER, Keepon, Kismet, Labo-I, Lego
Mindstorm NTX, Maestro, NAO, Paro, Pekee, Roball, Robota,
Tito, TREVOR, Troy. There are many new robots that
emerged, as paper was written in 2013, like Popchilla, Zeno,
Lucy [14], Rubi, Romibo and Robosapiens. These robots are
mostly designed as Humanoids or animal shaped robots, as
both of them have different effects on the autistic child. It can
be clearly seen from the paper [10] in which a cat robot was
used and on contrary in paper [8] Zeno a humanoid robot being
used, showed different results and improvements. The focus of
the paper is on the robots that are Humanoid which is
explained in next section.
III. WHY HUMANOID
Robots which are used to aid autistic children, they are
being studied and have been a main focus nowadays especially,
as not every robot showed same improvement as other. Each
robot used to help autistic children differed from groups of
children itself so it cannot be generalized or interpreted as
being the best solution in terms of improvements in autistic
children. The shape, size and aesthetics of the robot made a lot
of difference. The humanoid robots, being similar to a human,
showed better results than other robots [4]. Autistic children
appeared more comfortable in interacting with a robot than
human, as in paper [1], it can be clearly seen from the
experiment that eye gaze, testing behaviors and tests per
initiation showed higher results than in case of human
interaction with autistic children. The two humanoid robots
that we have worked on; NAO and Robosapiens, are briefly
explained.
Figure 1: NAO robot
Figure 2: Robosapien
Figure 3: Child with ASD interacting with Robosapien
Figure 4: Match the patch game
Figure 5: Get me out game
Figure 6: Where is my color? game
A. NAO
NAO is a humanoid, a robot with 58cm height and weighs
4.3 kg, looks like a little human (Figure 1). It is fully
programmable, open, autonomous, and has features to adapt
many different needed behaviors for autistic children [2].
Therefore, it is widely used nowadays to develop courses or
therapies for autistic children. Perhaps the only shortcoming in
NAO robot is the cost since it is really expensive compared to
other types of robots. In [3, 6, 7] it is shown how NAO robot is
being used in order to develop a Lego therapy session for
autistic children and their families. Using NAO in Lego
therapy showed that long term trainings do not exhaust the
autistic children and they can easily follow as well as improve
with time. Specifically in [3], it is clearly shown that using
NAO in Lego therapy which is implementation of single
behavior, have shown better interaction results of the autistic
child with his or her family and they have positive response to
surroundings.
NAO robot is being used in a number of applications all
around the world including interactive activities with children,
especially children with special needs like the children with
autism. In this context we have started using NAO robot with
children suffering from autism or having some aspects of
autism spectrum disorder (ASD) with respect to certain
functional activities. One group of children are being focused
on with speech related interactive and social skill development
activities while other group is more into dexterous and mobility
aspect of activities. In both cases the same robot is controlled
with a remote command station which is essentially a laptop or
a tablet PC with various behaviors in accordance with the
requirements of the therapy are pre-programmed into a
remotely operated program. As such NAO robot is in contact
with the children along with their teachers for the activities
requiring certain behavioral display by the robot. For instance,
in one of the activities the robot acts as teacher’s assistant. In
this activity the teacher is trying to bring the students to do an
activity such as putting a basket on one side of the room. In this
activity, there are several baskets in the middle of the room and
they are asked to put them in order on one side of the room.
Obviously these are low functioning children who are not
conversing very well with the teacher in this activity. Once, the
teacher has tried two three times with the student and a good
response is not received, the NAO robot is given the same
instruction and the behavior is controlled remotely as a result
the robot starts to work and start walking in the middle of the
room, picks up the small basket and then walks to the other
side of the room to place it where it is needed. As a result of
this activity the students got interested in the activity or
behavior and the next time when the teacher ask them, better
response was received and they also tried to do the same thing
what the robot did.
In a different experiment, the robot is made a part of the
activity along with the students. Hence, the robot is not just a
facilitator in this case but also an active member of this activity
which involves certain exercise-like routines. The teacher is
asking the student to do these routines but only some of them
follow the teacher in the beginning while others are not. At the
same time, the teacher asked the robot to start doing the same
thing and surprisingly it has been observed that the students
who were not interested in the activity after seeing the robot
doing the same functions began taking interest and started
doing mimicry of the action the robot is doing. Although the
teacher is doing the same thing, but it was observed that the
children were more attracted to the activity of the robot!
In terms of speech related activities, NAO robot at the
moment has been programmed in few languages of the world
but more predominantly it is still in English language. In our
initial experiments, these were not useful with the children who
were Arabic speaking. An alternate approach was used initially
and pre-recoded waveforms of specific conversational phrases
were played remotely, so the child would perceive that they
were coming from the robot. This included certain questions
and answers, and several reinforcement phrases. For instance,
the robot would show a card with a picture on it asking the
students ‘what is it?’, so that the actual linguistic file of ‘what
is it?’ is stored previously as a wave file and then played
through the program. Then when the child sees this from the
robot it tries to give an answer. If the answer is wrong the robot
will be directed to play another file which says to ‘try again’, or
‘please try again’ or ‘you are close’, etc. Sentences like these
were programmed and one by one they were played if the
answer was wrong. However, if the answer was correct the
positive reinforcement was done by the robot by showing the
gestures of ‘high-five’ or happiness or excitement with audio
file saying ‘very good’, ‘excellent’, ‘keep it up’, ‘that was
great’, etc. Sentences like these can encourage the child to
continue the activity and, of course, very positive results were
observed in terms of increased attention span and prolonged
learning phase.
The third activity with NAO robot is related to a personal
contact or interaction with the child. This usually involves
medium to high functioning children who have social
interaction problems especially eye contact, following
instructions and fear of being close to someone. For this
scenario, the robot is programmed to ask the child to hold its
hand. As the child holds the hand, the robot provides the
positive reinforcement in terms of verbal encouragement as
well as gestures of moving up and down as the gesture of
happiness (‘Hooray’) or something similar to that. Then the
robot would ask the child if he or she could take it to a
predefined destination inside the classroom. The robot waits
for the child to try to give a little bit of push to its hand and
senses it by the touch sensors located in the upper side of the
palm and near the wrist of the robot. Once it senses the
pressure from the child in a specific net direction, the robot
starts moving in that direction until it reaches the location or
the child starts to give a different type of push to the hand. By
understanding the direction of the pressure from the child’s
hand, the robot would follow the child in the direction the child
wants to take it. This activity has not been tested with the low
functioning children because of the delicate nature of the robot
and it has been observed that children would like to hold the
hand with the fingers only because of the fear of the social
contact. As such, sometimes they like to pull the fingers
strongly and the fingers can detach from the socket of the
robotic arm. Hence, to be careful with this scenario it has been
tested with only high and medium functioning children. Of
course the results have been surprisingly very positive and the
child who is usually not very familiar with holding a finger of
someone and walking with that person, was able to do it quite
independently and quite freely with NAO robot.
B. Robosapien
Robosapiens are also humanoid robots (Figure 2). They are
similar to NAO but smaller in size and lighter [22]. They are
not easily programmable as in case of NAO, but at least 50
times cheaper. Therefore, Robosapien has been used in many
of the projects being conducted at Qatar University, especially
in KINDI research lab. There are four publications [17 - 20]
which talks about the project done with Robosapien to help
autistic children. First, Robosapien was used to do a specific
behavior action which an autistic child can adapt to using a
remote control. Then later it was developed in to Microsoft
Kinect based system through which it can mimic the movement
of the autistic children helping them to improve interactions
[23]. Figure 3 shows an autistic child, who is suffering from
severe challenges of behavior control, interacting with the
Robosapien. The activity helped him to learn control over
himself and to develop some level of focus and involvement in
the activity. In publication [17], the Robosapien was developed
to do behaviors using electromyogram (EMG), by movement
of limbs. In publication [18, 20], different games were devised
in order to improve the IQ and understanding of surroundings
of the autistic children. These games are Match the patch game
(Figure 4), Get me out (Figure 5) and where is my color?
(Figure 6). These are further explained later in the section.
Robosapien robot is a very low cost toy available
commercially. Primarily, it is an infrared based remotely
controlled robot which has a very complicated 30 plus keys
keyboard which has lot of functionality in it and lots of
dexterous as well as audio performances are available. Also,
mobility in a variety of different patterns, such as walking or
dancing etc., are also provided. However, the remote control is
quite difficult object for children with autism to handle. They
are more comfortable with joysticks that are more commonly
used in games, e.g. PS joystick. As part of our ongoing
research, first thing we did was to remove the dependencies on
the remote control by changing it or converting the control to a
friendlier input device. To do this first we had to map all the IR
commands from the remote into a file and then any type of
input device can be used to select one of these commands and
then the output is given to the robot by using an IR transmitter.
It is a USB IR Transmit and Receive device (USB IRT) that is
quite successful in sending these big blocks of IR commands in
in near real time mode. Initially, this joystick was given to
medium to high functioning children and the activity that was
placed in front of them was that they were asked first of all to
select a color from a circle of color that has different colors in
it. Usually, this is not a very simple activity for them due to
lack of focusing capabilities. But when the teacher showed
them how the robot will react to it, then suddenly their interest
developed and they became very cooperative in selecting a
color. Then, there were different color patterns (stickers) on the
ground in the shape of maple leaves. The color the child chose
is the color they want the robot to go to, e.g. if the child has
selected the red color, the child is told to direct the robot using
the joystick to the first red leaf and from there to second red
leaf and then to third. Interestingly the child did not understand
it initially but when he started moving the robot the first time
he liked it so much that for some minutes he did not pay any
attention to the instructions being given by the teacher. Instead,
he was very busy playing by trying many different experiments
with the robot; experimenting with different types of moves
forward, backwards, right, left, making it move, swing it from
right and left, etc. All of these were very easy for the child
because of the user friendly joystick that he was using and the
activity became a lot more fun for the child. Then instructions
were repeated and the child came back to the activity and he
found that the control he has it is easy for him to move the
robot from one color to second and third color, the
reinforcement that was given to him is basically by all of his
classmates who were jumping and encouraging him for the
way he did it. Then it was repeated with different children with
different level of functionality and a very positive response
from all of them was observed. They really liked playing with
it and we were able to achieve some level of enhancement in
the objectives of pattern recognition, eye and hand coordination
that usually takes weeks by the teachers to help the students
learn. The Robosapien activity made it happen in few hours.
Second activity with Robosapien was planned with very
low functioning child who was basically not able to distinguish
between stationary and non-stationary move, so a simple iPad
program was built for the child, again, using the same platform
of IR commands. The iPad provided the child with a screen
having a floor mat design on it with four colors to choose from.
This was the replica of a small arena built on the ground with
the Robosapien standing in the middle on a circle with four
colored rectangles on the corners of this area with different
colors. The child is asked to pick one color and the robot will
move automatically to that color. The activity involvement of
the child was very little and most of the command and control
was done by the software on the robot. However, initially the
child was not cooperative as for him it was not interesting, until
the robot was turned ON, the minute it was turned ON, the
attention span increased and the focus was completely directed
towards the robot. When the teacher asked the child to select
the color he cooperated and selected the color. When he saw
the robot moving to specific rectangle that he selected made
him more interested, and the next color he selected without
even being instructed and basically the robot started to follow
him.
Third activity was done with an addition of an IO device,
which was a Kinect camera. This was a project called as ‘I
Copy You’ designed in such a way that Robosapien was
copying the movements of anyone, who are moving hands or
walking, in front of a Kinect camera connected to the same
laptop. As such this activity was performed only with very high
functioning children because for low functioning children it
was difficult to hold them steady in one place in front of the
camera. ‘I Copy you’ project was designed to take the skeletal
vectors from Kinect camera, and copying these vector
movements to various motors and various limbs of the robots
accordingly. Hence, a mimicry action can be produced by the
robot for anyone who is acting in front of the camera. Different
activities were designed with this interface. The most
interesting was an activity called ‘Get me out’. In this activity a
small maze was built on the floor and a child was standing in
front of the camera and the robot is at the starting point of the
maze and child was taught three different hand movements.
The child was directed to use them in order to control the
movement of the robot, basically forward, right and left, so that
child knows how to steer the robot in the maze and ultimately
take it out from the maze. It turned out to be really exciting
activity although little bit difficult, as it not that easy to act and
get an immediate response, there is some latency involved in it
due to programming overheads. However, the child it was
tested with found it to be very interesting and participated in
activity with full heart and the performance was found to be
positive and encouraging.
IV. DICUSSION AND CONCLUSION
In light of the above experiences, it can be seen that in
general, children with autism suffer with the social isolation
issues that implants in them short comings like not being able
to have eye contact or converse properly, to be able to
concentrate for long period of time with different types of
activities, etc. Specifically, for the parents who are not aware of
the issue for their children at very early age, they tend to isolate
them more rather than exposing them to people as part of their
own psychological barriers. As a result, autistic children
become more and more isolated and hermitized. On the other
hand, when they are doing this isolation and putting self-
restrain on themselves, weather voluntarily or in-voluntarily,
they tend to soothe their playing instincts with toys. It turns out
that the toys which mimic humans in shape, can make different
types of noises, sounds and can also make lot of flashing lights
etc., are really the kind of gadgets they are happy with and they
would like to play with them a lot. Combining these ideas
objectively with the shortcomings of such children, in order to
enhance their missing skills by using what they really like, the
toys in the form of a robot, really compliments the idea of what
should be taught and how should it be taught to these children.
We have seen from various interactions with these children that
the robotic solutions are very strong, very assertive and the
children would not understand that they are being taught as
being part of their therapy rather they would be playing with
them and subconsciously learning things that they are missing
due to their disorder. Based on our experiences, it is really
recommended that robots used should be robust in their activity
as the child’s reaction could be damaging to the body of the
robot as well. The robots should not have a lot of delays while
performing actions because this is a very critical aspect that
unnecessary delays in the performance of the action would
make these children to lose interest, and when they lose interest
it is very difficult to bring them back to the same therapy. On
the same note however, robot should also be made as attractive
as possible because they like to play with such toys more than
the dull shaped robotic
So which robot to choose and for what activity, this has to
be a careful selection based on the guidance of the care giver of
the children, the teachers or the nurses or the parents.
Sometimes these children can recommend things as well. For
instance, in Robosapien study, we have seen that one of the
child (seven years old girl) really liked the robot but said ‘it
looks so strange’ and asked us if ‘the robot can wear a pink
color frock’? We did that and she got more attached to the
robot then before. Hence, such recommendations would help
making the robot more ergonomic and friendly with the child
so the barrier of fear and strangeness is gone and as a result the
child would interact better with the robot. In terms of activities
it is very subjective because it depends on the nature of the
deficiency in the child. However, from the above mentioned
experiences, it has been seen that activities related to
mimicking, conversations and dexterous action, putting things
from one point to other point or handing things work really
well with robots as main or facilitating players. Probably a
fourth category where combination of all of this exists, is
where facial recognition can be introduced so it usually occurs
in more complex and probably in more expensive robots where
face recognition can be done. The robot can understand where
the child is and how he or she is moving. Accordingly, the
robot changes the behavior which really helps in developing
the interaction or the understanding of interactive behavior of
the child and how it is developing it further. However having
said this, it should be understood as well that this is not the
single solution for all kinds of scenarios. One robot might suite
well with one child and may not suite well with the other. So in
our opinion the decision of which one to use or how to use
should lay with the caregiver, the teacher or the parents,
especially in an institution it should be done at the collective
level. These children initially, when they are low functioning,
they are not that responsive to most of the therapies so at that
level an individual robot might help them a lot. However, when
they start socializing with it, perhaps it would be best to come
up with the activity at group level rather than individual level,
such as mimicking exercises or combine group activities in
which we share responsibilities and do things collectively one
at a time. Hence, the decision of how to use it is still very
subjective but it has very good positive potential to work and it
was expected that this would be next line of technological tool
needed in the therapy with the children with autism
ACKNOWLEDGMENT
We would like to thank KINDI research center to give us
the platform to gain practical experience and to develop
innovative solutions to help the future of our country. We
would also like to acknowledge the support of Step by Step
School Qatar, Shafallah Institute Qatar, and Al-awsaj academy
Qatar for their collaborations.
REFERENCES
[1]
A. Peca, R. Simut, S. Pintea, and B. Vanderborght, “Are Children
with ASD more Prone to Test the Intentions of the Robonova Robot
Compared to a Human?,” Int. J. Soc. Robot., vol. 7, no. 5, pp. 629–
639, 2015.
[2]
A. robotics, “NAO H25 datasheet.”
[3]
B. Huskens, A. Palmen, and M. Van Der Werff, “Improving
Collaborative Play Between Children with Autism Spectrum
Disorders and Their Siblings : The Effectiveness of a Robot-
Mediated Intervention Based on Lego Ò Therapy,” J. Autism Dev.
Disord., vol. 45, no. 11, pp. 3746–3755, 2015.
[4]
D. Hutchison and J. C. Mitchell, “A Survey on Storytelling with
Robots,” in 6th International Conference on E-learning and Games,
2011, pp. 450–456.
[5]
D. P. Miller, I. R. Nourbakhsh, and R. Siegwart, “Robots for
Education,” in Springer handbook of Robotics, 2008, pp. 1283–
1301.
[6]
E. I. Barakova, J. C. C. Gillesen, B. E. B. M. Huskens, and T.
Lourens, “End-user programming architecture facilitates the uptake
of robots in social therapies,” Rob. Auton. Syst., vol. 61, no. 7, pp.
704–713, 2013.
[7]
E. I. Barakova, P. Bajracharya, M. Willemsen, T. Lourens, and B.
Huskens, “Long-term LEGO therapy with humanoid robot for
children,” Expert Syst., vol. 00, no. 00, 2014.
[8]
I. Ranatunga, M. Beltran, N. A. Torres, N. Bugnariu, R. M.
Patterson, C. Garver, and D. O. Popa, “Human-Robot Upper Body
Gesture Imitation Analysis for Autism Spectrum Disorders,” in 5th
International Conference, ICSR, 2013, pp. 218–228.
[9]
J. J. Cabibihan, H. Javed, and M. Ang Jr., “Why Robots? A Survey
on the Roles and Benefits of Social Robots in the Therapy of
Children with Autism,” Int. J. Soc. Robot., vol. 5, no. 4, pp. 593–
618, 2013.
[10]
K. H. Mun, J. Y. Kwon, B. H. Lee, and J. S. Jung, “Design
Developing an Early Model of Cat Robot for the Use of Early
Treatment of Children with Autism Spectrum Disorder ( ASD ),”
Int. J. Control Autom., vol. 7, no. 11, pp. 59–74, 2014.
[11]
M. A. Goodrich and A. C. Schultz, “Human – Robot Interaction: A
Survey,” Found. Trends Human–Computer Interact., vol. 1, no. 3,
pp. 203–275, 2007.
[12]
M. Coeckelbergh, C. Pop, R. Simut, A. Peca, S. Pintea, and D.
David, “A Survey of Expectations About the Role of Robots in
Robot-Assisted Therapy for Children with ASD: Ethical
Acceptability, Trust, Sociability, Appearance, and Attachment,”
Sci. Eng. Ethics, vol. 21, no. 6, pp. 1–19, 2015.
[13]
N. Aresti-bartolome and B. Garcia-zapirain, “Technologies as
Support Tools for Persons with Autistic Spectrum Disorder: A
Systematic Review,” Int. J. Environ. Res. Public Health, vol. 11,
no. 8, pp. 7767–7802, 2014.
[14]
R. Khosla, K. Nguyen, and M.-T. Chu, “Socially Assistive Robot
Enabled Home-Based Care for Supporting People with Autism,” in
Pacific Asia Confrence on Information Systems, 2015, p. Paper 12.
[15]
R. Meresca and L. de Magistris, “Autism: What Is It?,” in
Translational Approaches to Autism Spectrum Disorder, 2015, pp.
1 – 10.
[16]
S. Boucenna, A. Narzisi, E. Tilmont, F. Muratori, G. Pioggia, and
D. Cohen, “Interactive technologies for autistic children: A
review,” Cognit. Comput., vol. 6, no. 4, pp. 722–740, 2014.
[17]
U. Qidwai and M. Shakir, “Electromyography Controlled Robotic
Toys for Autistic Children,” Int. J. Biotechnol. Bioeng., vol. 2, no.
1, 2015.
[18]
U. Qidwai, “Using Course Projects to Tackle Social Problems : Use
of Robots for children with ASD,” in International forum on
Engineering Education, 2015, pp. 1–11.
[19]
U. Qidwai, M. Shakir, and O. B. Connor, “Robotic toys for autistic
children: Innovative tools for teaching and treatment,” in 2013 7th
IEEE GCC Conference and Exhibition, GCC 2013, 2013, pp. 188–
192.
[20]
U. Qidwai, M. Shakir, W. Hakouz, and N. Musa, “Wirelessly
Controlled Mimicing Humanoid Robot,” in Computer Systems and
Applications (AICCSA), 2014, pp. 156 – 160.
[21]
V. M. Durand, “Behavioral Therapies,” in The Molecular Basis of
Autism, 2015, pp. 195 – 212.
[22]
Wowee, “Robosapien X datasheet.”
[23]
Z. Zheng, E. M. Young, A. R. Swanson, A. S. Weitlauf, E.
Zachary, and N. Sarkar, “Robot - mediated Imitation Skill Training
for Children with Autism,” IEEE Trans. Neural Syst. Rehabil. Eng.,
2015.
