Conference PaperPDF Available

Humanoid Robots for children with Autism: Experiences with Robosapien and NAO


Abstract and Figures

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.
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
Uvais Qidwai
Department of Computer Science and Engineering
KINDI Research Center, Qatar University
Doha, Qatar
AbstractAutism 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.
KeywordsAutism Spectrum Disorder (ASD); Human Robot
Interface (HRI); NAO; Robosapiens; Humonoid robots.
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.
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.
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
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
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
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
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 youproject 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.
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
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.
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.
A. robotics, “NAO H25 datasheet.”
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. 37463755, 2015.
D. Hutchison and J. C. Mitchell, “A Survey on Storytelling with
Robots,” in 6th International Conference on E-learning and Games,
2011, pp. 450456.
D. P. Miller, I. R. Nourbakhsh, and R. Siegwart, “Robots for
Education,” in Springer handbook of Robotics, 2008, pp. 1283–
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.
704713, 2013.
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.
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. 218228.
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.
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. 5974, 2014.
M. A. Goodrich and A. C. Schultz, “Human Robot Interaction: A
Survey,” Found. Trends Human–Computer Interact., vol. 1, no. 3,
pp. 203275, 2007.
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. 119, 2015.
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. 77677802, 2014.
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.
R. Meresca and L. de Magistris, “Autism: What Is It?,” in
Translational Approaches to Autism Spectrum Disorder, 2015, pp.
1 10.
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.
U. Qidwai and M. Shakir, “Electromyography Controlled Robotic
Toys for Autistic Children,” Int. J. Biotechnol. Bioeng., vol. 2, no.
1, 2015.
U. Qidwai, “Using Course Projects to Tackle Social Problems : Use
of Robots for children with ASD,” in International forum on
Engineering Education, 2015, pp. 111.
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
U. Qidwai, M. Shakir, W. Hakouz, and N. Musa, “Wirelessly
Controlled Mimicing Humanoid Robot,” in Computer Systems and
Applications (AICCSA), 2014, pp. 156 160.
V. M. Durand, “Behavioral Therapies,” in The Molecular Basis of
Autism, 2015, pp. 195 212.
Wowee, “Robosapien X datasheet.”
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.,
Full-text available
The purpose of this chapter is to provide readers with a literature review of the latest research with regard to augmented reality (AR) and virtual reality (VR) technologies, as well as assistive and humanoid robots, for especially differently abled students, who have been diagnosed with autism spectrum disorders (ASDs). While introducing and describing the general perspective of the chapter as specifically focusing on objectives in terms of students with ASDs, background that summarizes the content of this chapter as also consisting of significant results from certain earlier work and/or with regard to young children, adolescents, adults, and/or older people, as well as references in terms of research related to other connected conditions, will also be offered where applicable. Problems and challenges in this regard are presented, together with possible solutions and recommendations, future research directions, and concluding remarks.
Full-text available
The use of robots in therapy for children with autism spectrum disorder (ASD) raises issues concerning the ethical and social acceptability of this technology and, more generally, about human-robot interaction. However, usually philosophical papers on the ethics of human-robot-interaction do not take into account stakeholders' views; yet it is important to involve stakeholders in order to render the research responsive to concerns within the autism and autism therapy community. To support responsible research and innovation in this field, this paper identifies a range of ethical, social and therapeutic concerns, and presents and discusses the results of an exploratory survey that investigated these issues and explored stakeholders' expectations about this kind of therapy. We conclude that although in general stakeholders approve of using robots in therapy for children with ASD, it is wise to avoid replacing therapists by robots and to develop and use robots that have what we call supervised autonomy. This is likely to create more trust among stakeholders and improve the quality of the therapy. Moreover, our research suggests that issues concerning the appearance of the robot need to be adequately dealt with by the researchers and therapists. For instance, our survey suggests that zoomorphic robots may be less problematic than robots that look too much like humans.
Full-text available
To utilise the knowledge gained from highly specialised domains as autism therapy to robot-based interactive training platforms, an innovative design approach is needed. We present the process of content creation and co-design of LEGO therapy for children with autism spectrum disorders performed by a humanoid robot. The co-creation takes place across the disciplines of autism therapy, and behavioural robotics, and applies methods from design and human–robot interaction, in order to connect state-of-the-art developments in these disciplines. We designed, carried out and analyzed a pilot and final experiment, in which a robot mediated LEGO therapy between pairs of children was mediated by a robot over the course of 10 to 12 sessions. The impact of the training on the children was then analysed from a clinical and human–robot interaction perspective. Our major findings are as follows: first, game-based robot scenarios in which the game continues over the sessions opened possibilities for long-term interventions using robots and led to a significant increase in social initiations during the intervention in natural settings; and second, including dyadic interactions between robot and child within triadic games with robots has positive effects on the children's engagement and on creating learning moments that comply with the chosen therapy framework.
Full-text available
This study analyzes the technologies most widely used to work on areas affected by the Autistic Spectrum Disorder (ASD). Technologies can focus on the strengths and weaknesses of this disorder as they make it possible to create controlled environments, reducing the anxiety produced by real social situations. Extensive research has proven the efficiency of technologies as support tools for therapy and their acceptation by ASD sufferers and the people who are with them on a daily basis. This article is organized by the types of systems developed: virtual reality applications, telehealth systems, social robots and dedicated applications, all of which are classified by the areas they center on: communication, social learning and imitation skills and other ASD-associated conditions. 40.5% of the research conducted is found to be focused on communication as opposed to 37.8% focused on learning and social imitation skills and 21.6% which underlines problems associated with this disorder. Although most of the studies reveal how useful these tools are in therapy, they are generic tools for ASD sufferers in general, which means there is a lack of personalised tools to meet each person's needs.
Conference Paper
In this paper we combine robot control and data analysis techniques into a system aimed at early detection and treatment of autism. A humanoid robot - Zeno is used to perform interactive upper body gestures which the human subject can imitate or initiate. The result of interaction is recorded using a motion capture system, and the similarity of gestures performed by human and robot is measured using the Dynamic Time Warping algorithm. This measurement is proposed as a quantitative similarity measure to objectively analyze the quality of the imitation interaction between the human and the robot. In turn, the clinical hypothesis is that this will serve as a consistent quantitative measurement, and can be used to obtain information about the condition and possible improvement of children with autism spectrum disorders. Experimental results with a small set of child subjects are presented to illustrate our approach.
This study proposes an innovative device specifically designed for investigating the ability of children with autism spectrum disorder (ASD) to test the intention of a partner in a dyadic interactive game. Twenty one children with ASD were exposed to both a contingent and a noncontingent interaction condition with either a human agent or the Robonova robot as partners. The statistical analysis indicates a strong tendency toward a significant higher frequency of testing behaviors in the robot noncontingent condition and no difference between the two groups (robot/human) for the contingent condition. Children with ASD showed significantly more eye gaze to the robot compared to the human agent in both contingent and noncontingent conditions, but no difference in affect was found. The high level of initiations recorded in all conditions suggests that the game has a high motivational value for ASD children. Further longitudinal studies should investigate if such synchronous interaction games lead to improved shared intentionality in children with ASD.
Intervention for the core symptoms and comorbid conditions associated with autism spectrum disorder (ASD) primarily involves behavioral and/or cognitive behavioral therapy. This chapter reviews the relevant research for the effectiveness of these approaches across several areas. It begins with a review of the rapidly growing research focused on early intervention for young children with ASD. Next, interventions for persons on the severe end of the autism spectrum are discussed. Specifically, studies focus either on symptomatic treatment (e.g., increasing social skills) or on packages of treatments that are designed to address the range of difficulties persons with ASD display. The chapter then describes the nascent research on persons on the milder end of the spectrum-especially work on social skills training. Finally, a growing research base on treating comorbid conditions (e.g., anxiety, sleep problems) is also briefly reviewed. A theme throughout the chapter is the need to individualize treatment and the special needs of the range of persons with ASD.
Educational humanoid robots have started to find there place in institutions for children with special needs and Autism Spectrum Disorder (ASD) children therapy centers. Most of the humanoid robots are expensive, or come with specific software or method for controlling the robot. This gives limits to what can be done with the robot and the software or method used may not allow expansion of the robot functionalities or possible applications. This paper presents an of system integration example with custom-built graphical toolkit used in controlling a simple toy like robot, the robot (RoboSapien), for a variety of customizable functions and applications. The main focus is on the activities and games that can be used with this platform in order to customize enhance the functionalities of the robot to suit the therapy process for the child under consideration. The mimicking mode of the robot, where the robot mimics the behavior of the user, has been found to be very promising for catching attention, making children involve in an activity, and retain their interest for longer period of time. Several activities have been developed and tested with children having ASD and have shown remarkable improvement in concentration spans, focus, and willingness to follow instructions.
Autism spectrum disorder (ASD) impacts 1 in 68 children in the U.S., with tremendous individual and societal costs. Technology-Aided intervention, more specifically robotic intervention, has gained momentum in recent years due to the inherent affinity of many children with ASD towards technology. In this paper we present a novel robot-mediated intervention system for imitation skill learning, which is considered a core deficit area for children with ASD. The Robot-mediated Imitation Skill Training Architecture (RISTA) is designed in such a manner that it can operate either completely autonomously or in coordination with a human therapist depending on the intervention need. Experimental results are presented from small user studies validating system functionality, assessing user tolerance, and documenting subject performance. Preliminary results show that this novel robotic system draws more attention from the children with ASD and teaches gestures more effectively as compared to a human therapist. While no broad generalized conclusions can be made about the effectiveness of RISTA based on our small user studies, initial results are encouraging and justify further exploration in the future.
The purpose of this research is to design develop an early model for the use of early treatment that will improve the social interactions of children with ASD. Researchers from the department of social welfare, electrical engineering, industrial design, and fashion design carried out a fusion research for this purpose. The department of social welfare conducted a survey with professional therapists in order to first find out the necessary treatment components of the cat robot. The department of electrical engineering gave technical suggestions on the practical functions of the robot such as movements and emotional exchanges with humans. In addition, the department of industrial design proposed the robot's exterior, movement, and character designs. Considering that the robot will be used as a therapeutic medium for children, they also developed an eco-friendly material in order to prevent infection and other hygienic problems and also improve the therapeutic effects of the robot. According to the result of FGI's analysis, elements of function and motion have to be prepared for a cat robot was grasped. In consideration of these elements, guidelines to the construction of shape and motions for the design of the cat robot were established. By applying these guidelines, the design of outer shape of the cat robot was developed. And a cat robot's structures, electrical circuits, and driving program for the treatment of children with ASD were suggested. Design of the cat robot's Outer shape has to be developed to match inside structure of the cat robot, and the early model of the cat robot has to be completed to match these criteria.
Conference Paper
This paper presents an initial study related to the use of robotic toys as teaching and therapeutic aid tools for teachers and care-givers as well as parents of children with various levels of autism spectrum disorder (ASD). Some of the most common features related to the behavior of a child with ASD are his/her social isolation, living in their own world, not being physically active, and not willing to learn new things. While the teachers, parents, and all other related care-givers do their best to improve the condition of these kids, it is usually quite an uphill task. However, one remarkable observation that has been reported by several teachers dealing with ASD children is the fact that the same children do get attracted to toys with lights and sounds. Hence, this project targets the development/modifications of such existing toys into appropriate behavior training tools which the care-givers can use as they would desire. Initially, the remote control is in hand of the trainer, but after some time, the child is entrusted with the control of the robotic toy to test for the level of interest. It has been found during the course of this study that children with quite low learning activity got extremely interested in the robot and even advanced to controlling the robot with the PS2 type joystick. It has been observed that the children did show some hesitation in the beginning 5 minutes of the very first sessions of such interaction but were very comfortable afterwards which has been considered as a very strong indicator of the potential of this technique in teaching and rehabilitation of children with ASD or similar brain disorders.