Figure 1 - uploaded by Daniela Conti
Content may be subject to copyright.
The Nao robot. The camera used for recording the child activity is the one on the top (circled in red).
Source publication
Recent studies suggest that some children with autism prefer robots as tutors for improving their social interaction and communication abilities which are impaired due to their disorder. Indeed, research has focused on developing a very promising form of intervention named Robot-Assisted Therapy. This area of intervention poses many challenges, inc...
Contexts in source publication
Context 1
... otherwise specified, this study used the default settings and the standard equipment of the Nao robot v4, which includes two 1.22 Mega pixels cameras that can be used to take pictures and record videos from the robot's perspective. Camera and other sensor positions are shown in Figure 1. According to the specifications, when image resolution is up to 1280 × 960 pixels and video recording is up to 30 fps, the actual resolution and frame-rate are usually restricted to 320 × 240 and 10 fps due the limited computing capacity of the main processor and memory resources. ...
Context 2
... the software features, Nao has the face detection and tracking functionality that was used in the clinical experiments to direct the robot toward the child during the interaction. Robotics 2018, 7, x FOR PEER REVIEW 6 of 20 Figure 1. The Nao robot. ...
Context 3
... each therapeutic session, the interaction was recorded using the robot's top camera (Figure 1). The video recording was restricted to 320 × 240 pixels per frame up to 10 fps. ...
Similar publications
The social interactions between caregivers and their children play a crucial role in childhood development; therefore, caregivers’ feelings for children are critical for the development of social minds. Mothers of children with autism spectrum disorder (ASD) are known to experience higher levels of stress. However, knowledge regarding mothers’ feel...
Approximately half of all autism spectrum disorder (ASD) individuals suffer from comorbid intellectual disabilities. Furthermore, the prevalence of epilepsy has been estimated to be 46% of patients with low intelligence quotient. It is important to investigate the therapeutic benefits and adverse effects of any recently developed drugs for this pro...
Background: Although clinical and demographic patterns in presentation of autism in the developed world have been extensively studied, comparable data from developing countries remain scarce. While a few attempts have been made previously to describe autistic children in some areas in Sri Lanka (SL), there are gaps in the understanding of autism in...
Autism is a group of complex neurodevelopmental disorders characterized by impaired social interaction and restricted/repetitive behavior. We performed a large-scale retrospective analysis of 1,996 clinical neurological structural magnetic resonance imaging (MRI) examinations of 781 autistic and 988 control subjects (aged 0–32 years), and extracted...
Citations
... Anamaria and their colleagues [38] emphasized the positive impact of the social robot Probo in enhancing children's abilities to identify emotions based on different situations. Furthermore, Di Nuovo and colleagues [39] studied new deep learning neural network architectures for automatically estimating whether a child focused his or her visual attention on the robot during a therapy session. Other research has focused on building verbal communication in children with autism. ...
Technology has always represented the key to human progress. It is believed that the use of supportive technological mediators can facilitate teaching/learning processes and enable everyone to learn how to critically manage technology without being its slave or passive user while contributing to the collective well-being. Educational robotics is a new frontier for learning that can offer numerous benefits to students. The use of robots can offer the possibility of creating inclusive educational settings in which all students, regardless of their abilities or disabilities, can participate meaningfully. The article proposes an analysis of the evidence obtained from a systematic literature review with reference to general educational robotics and social robotics for emotion recognition. Finally, as a practical implementation of an educational robotic intervention on emotion recognition, the "Emorobot Project" as part of the EU-funded "Ecosystem of Innovation-Technopole of Rome" Project in NextGenerationEU will be presented. The project's aim is to foster the development of social skills in children with autism spectrum disorders through the creation of an open-source social robot that can recognize emotions. The project is intended to provide teachers with a supportive tool that allows them to design individual activities and later extend the activity to classmates. An educational robot can be used as a social mediator, a playmate during the learning phase that can help students develop social skills, build peer connection, reduce social isolation-one of the main difficulties of this disorder-and foster motivation and the acquisition of interpersonal skills through interaction and imitation. This can help ensure that all students have access to quality education and that no one is left behind.
... The study aimed to measure participants' joint attention, eye contact, and adult seeking, achieving an agreement with the external judge of 67%, 76%, and 79%, respectively. Di Nuovo et al. (2018) studied the use of the robot to identify children's attention during therapy. They analysed recordings of a NAO robot embedded into the daily therapy of six children with ASD (Conti et al., 2021). ...
In the past decade, interdisciplinary research has revealed the potential benefits of using social robots in the care of individuals with autism. There is a growing interest in integrating social robots into clinical practice. However, while significant efforts have been made to develop and test the technical aspects, clinical validation and implementation lag behind. This article presents a systematic literature review from a clinical perspective, focusing on articles that demonstrate clinical relevance through experimental studies. These studies are analysed and critically discussed in terms of their integration into healthcare and care practices. The goal is to assist healthcare professionals in identifying opportunities and limitations in their practice and to promote further interdisciplinary cooperation.
... The most relevant information on the articles studied for this review can be found in Table 2, where the author, the type of article, the sample, the intervention, the type of scale used, and the results of each work are indicated. There are six study cases [10][11][12][13][14][15], two pilot studies [16,17], and one randomised controlled trial (RCT) [50]. In these papers, the number of subjects included was 186, of which 27 were known to be female. ...
Children with autism spectrum disorder (ASD) have deficits that affect their social relationships, communication, and flexibility in reasoning. There are different types of treatment (pharmacological, educational, psychological, and rehabilitative). Currently, one way to address this problem is by using robotic systems to address the abilities that are altered in these children. The aim of this review will be to analyse the effectiveness of the incorporation of the different robotic systems currently existing in the treatment of children up to 10 years of age diagnosed with autism. A systematic review has been carried out in the PubMed, Scopus, Web of Science, and Dialnet databases, with the following descriptors: child, autism, and robot. The search yielded 578 papers, and nine were selected after the application of the PRISMA guideline. The quality of the studies was analysed with the PEDRo scale, and only those with a score between four and six were selected. From this study, the conclusion is that the use of robots, in general, improves children’s behaviour in the short term, but longer-term experiences are necessary to achieve more conclusive results.
... To evaluate human facial expressions, Valles et al. [35] trained CNN models on photographs from Kaggle's (FER2013) 2013 dataset, which had been adjusted to include images of children with ASD taken in a variety of lighting conditions. Emotional assessments of children with ASD receiving robot-assisted treatment (RAT) were also the subject of several studies [36,37], which used deep learning and Raspberry Pi3 models. ...
Autism spectrum disorder (ASD) is a complex psychological syndrome characterized by persistent difficulties in social interaction, restricted behaviours, speech, and nonverbal communication. The impacts of this disorder and the severity of symptoms vary from person to person. In most cases, symptoms of ASD appear at the age of 2 to 5 and continue throughout adolescence and into adulthood. While this disorder cannot be cured completely, studies have shown that early detection of this syndrome can assist in maintaining the behavioural and psychological development of children. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre-trained convolu-tional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. Transfer learning was applied to every model included in the study to achieve higher results than the initial models. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models. The proposed method also outperformed the state-of-the-art models in terms of accuracy and computational cost.
... Finally, the question arises whether the child actually pays attention to the robot during therapy session. (Di Nuovo et al., 2018) addressed this issue by developing a deep neural network for engagement classi:ication. ...
The progress in Information and Communication Technologies (ICT) can make a real difference in the quality-of-life of persons with Autism Spectrum Disorder (ASD) by acting on several aspects, from customized software for the communication, to emotion recognition, to social behavior and also to provide systems for the observation of the wide spectrum of manifestations, to ease the diagnosis, to support the therapy, and to monitor the improvement and the growth of children with ASD. This has been achieved by the introduction of a large number of innovative technologies, spanning from Internet of Things, to robotics, virtual and augmented reality etc.
Differently from other surveys on the same research area, we focus this survey on innovative technologies used in this field, and we organize a classification of the works based on three different but strictly crossed axis, namely the triad of impairment (either communication, social interaction, or social behaviors), research purpose (either diagnosis or therapy) and system activity (either monitoring or intervention).
... The first robotic device designed for rehabilitation was created in 1992 and paved the way for robot-assisted therapy (RAT) [4]. Since then, RAT has been used to treat a wide range of skill deficits or functional impairments such as impaired social and intellectual skills, sensorimotor deficits, gait dysfunctions, decreased hand function, and decreased activity participation in clients with cerebral palsy, autism, spinal cord injury, ankle injuries, intellectual disabilities, and stroke [5][6][7][8][9][10][11][12][13][14]. RAT allows for repetitive practice in conjunction with conventional therapies. ...
Objective
To examine the effectiveness of robot-assisted therapy (RAT) combined with conventional therapy (CT) compared to CT alone in accelerating upper extremity (UE) recovery poststroke. Data Sources. We searched five databases: Ovid, MEDLINE, CINAHL, PubMed, and Scopus Study Selection. Studies were selected for this review using the following inclusion criteria: randomized controlled trials of adults, RAT combined with CT compared to CT, and Fugl-Meyer Assessment (FMA) as an outcome measure. Studies focused on children with neurological impairments, and studies that used RAT to facilitate lower extremity recovery and/or improve gait were excluded. Data Extraction. The initial search yielded 3,019 citations of articles published between January 2011 and May 2021. Fourteen articles met the inclusion criteria. Randomization, allocation sequence concealment, blinding, and other biases were assessed. Data Synthesis. Current evidence suggests that the use of RAT along with CT may accelerate upper extremity recovery, measured by FMA, in the beginning of rehabilitation. However, the progress fades over time. More empirical research is needed to validate this observation. Also, the findings related to cost-benefit analyses of RAT are inconclusive.
Conclusions
It is unclear whether RAT accelerates UE recovery poststroke when used in conjunction with conventional therapy. Given the capital and maintenance costs involved in developing and delivering RAT, more controlled studies examining the effectiveness and cost-benefit analysis of RAT are needed before it can be used widely. This trial is registered with CRD42021270824.
... Some studies do not report the duration and the number of sessions done. Several studies include less than five sessions, most only one session (Taheri et al., 2019;Askari et al., 2018;Moghadas and Moradi, 2018;Nakadoi, 2017;Suzuki and Lee, 2016;Wanglavan et al., 2019;Guedjou et al., 2017), as they are small pilot studies, aiming to evaluate the platform and protocol feasibility and the subjects' engagement in these novel robotic approaches (Fig. 9a) As for session duration, most studies have a short duration, less than 15 min, to avoid losing attention from ASD subjects (Fig. 9b) (Nuovo et al., 2018;Bharatharaj et al., 2017c;Golestan et al., 2017;Tariq et al., 2016;Boccanfuso et al., 2016;Attawibulkul et al., 2019;. Future studies should increase the session duration and the number of sessions in the study protocol to understand better the long-term impact of robot-mediated therapy on ASD subjects. ...
... Most of the contemporary studies still plan sessions once a week or once every 2 weeks (Fig. 9c) (Chung, 2019;Yun et al., 2017;Moorthy and Pugazhenthi, 2016;Beer et al., 2016;Zheng et al., 2020;Marino et al., 2020;Carlson et al., 2018;Wong et al., 2016;Hudson and Lewis, 2020). However, giving the evidence that a prolonged and repeated exposure to given stimuli provides higher chances of learning and a potentially larger number of learnt skills, experimenters have started to increase frequency to twice or more times per week (Nuovo et al., 2018;Clabaugh et al., 2019;Kumazaki et al., 2019a;So et al., 2019b;Saadatzi et al., 2018;Scassellati et al., 2018;Albo-Canals et al., 2018;Bharatharaj et al., 2017a, c;Boccanfuso et al., 2017;Choi et al., 2016;Srinivasan et al., 2016;Han et al., 2016;Yun et al., 2016;Marino et al., 2020;Fuglerud and Solheim, 2018;Schadenberg et al., 2020;Telisheva et al., 2019;Carlson et al., 2018;So et al., 2018a, b). Just 12% of the studies try to do follow-up acquisition of outcome measures, to test the generalisation and persistence of the skills acquired during the therapy/teaching robotic sessions on a longer time-scale or the robustness of a diagnosis (Chung, 2019;Han et al., 2016;Anzalone et al., 2019;Scassellati et al., 2018;Moorthy and Pugazhenthi, 2017). ...
... tic criteria from the Diagnostic and Statistical Manual of Mental Disorders-IV and V(So et al., 2019a;Giannopulu et al., 2018), and others based on Childhood Autism Rating Scale ScheduleGiannopulu et al., 2016;Schadenberg et al., 2020); some others chose diagnostic tools such as Autism Diagnostic Observation Schedule (ADOS)(Kumazaki et al., 2018b;van Straten et al., 2017;Askari et al., 2018) or Autism Diagnostic Interview-Revised(Zhang et al., 2019a;Aryania et al., 2020;Nuovo et al., 2018), and others collected anamnestic data and symptoms through parent questionnaires, as the Social Responsiveness Scale(Zhang et al., 2019b;Chung, 2019). ...
Robotic therapies are receiving growing interest in the autism field, especially for the improvement of social skills of children, enhancing traditional human interventions. In this work, we conduct a scoping review of the literature in robotics for autism, providing the largest review on this field from the last five years. Our work underlines the need to better characterize participants and to increase the sample size. It is also important to develop homogeneous training protocols to analyse and compare the results. Nevertheless, 7 out of the 10 Randomized control trials reported a significant impact of robotic therapy. Overall, robot autonomy, adaptability and personalization as well as more standardized outcome measures were pointed as the most critical issues to address in future research.
... These feedback types are decided by professionals in autism. In general, we plan to follow the recommendations given by the researchers in [29], who have previously worked with the Nao robot. As presented in Figure 3, the engagement detection system consists of three steps: ...
... In general, we plan to follow the recommendations given by the researchers in [29], who have previously worked with the Nao robot. As presented in Figure 3, the engagement detection system consists of three steps: ...
Children with autism face a range of challenges when it comes to verbal and nonverbal communication. It is essential that children participate in a variety of social, educational, and therapeutic activities to acquire knowledge that is essential for cognitive and social development. Recent studies have shown that children with autism may be interested in playing with an interactive robot. The robot can engage these children in ways that demonstrate and train essential aspects of human interaction, guiding them in therapeutic sessions to practice more complex forms of interaction found in social human-to-human interactions. This study sets out to investigate Robot-Assisted Autism Therapy (RAAT) and the use of artificial intelligence (AI) approaches for measuring the engagement of children during therapy sessions. The study population consisted of five native Arabic-speaking autistic children aged between 4 and 11 years old. The child–robot interaction was recorded by the robot camera and later used for analysis to detect engagement. The results show that the proposed system offers some accuracy in measuring the engagement of children with ASD. Our findings revealed that robot-assisted therapy is a promising field of application for intelligent social robots, especially to support autistic children in achieving their therapeutic and educational objectives.
... It is necessary to design a paradigm for autism that is based on robots in order to make it possible for this field to advance via the application of scientifically rigorous procedures. Time constraints, accuracy concerns, and reliability issues are some of the instances of the drawbacks that currently exist in techniques and algorithms [9,10,47,63,73,108]. Recent developments in technology have made it possible to create artificial robots that are both highly advanced and trustworthy as a treatment option for CwASD. ...
An array of developmental disorders known collectively as autism spectrum disorder (ASD) that can cause significant social interaction, communication, and behavioral challenges. To remedy this autistic impact at its very early stage, researchers are focusing their attention on robotics research with humanoid robots. It has been claimed that under certain circumstances, children with ASD (CwASD) interact more actively and spontaneously with robots than humans. Therefore, Human-Robot Interaction (HRI) has become a beneficial approach in training CwASD to abate their autism disabilities. This paper extensively reviews the prior findings on HRI for CwASD. With some critical analysis, a couple of findings have been highlighted to address the research gaps on the effectiveness of the intervention sessions administered by the robots. A total of nine traits of autism, intervention sessions administered by various tasks, different types of robots used, number of CwASD’s along with their age, diagnosis methods applied to quantify the autism levels, and, finally, the outcomes with identified research gaps have been analyzed. With some comparative depictions, the reader can visualize the broad scenario and overall research condition of robot-assisted training (RAT) for CwASD. This review recommends employing robots in supervised applications to enhance therapeutic effectiveness, broaden acquiescence, and inspire trust among practitioners, CwASD, and guardians. Overall, RAT is a promising use for intelligent social robots, especially for helping CwASD achieve therapeutic and educational goals. We expect interdisciplinary collaboration to address its difficulties quickly.
... One common use of robots to assist in therapeutic intervention is treating children with ASD [3,9,29]. Other cases used robotic therapy for paediatric rehabilitation in children with different special needs, such as intellectual disability [8,9,11], physical disability [15,21], and cancer rehabilitation [1]. These assistive robot coaches were generally used for monitoring rehabilitation performance and providing feedback during healthcare. ...
... Based on this TSES, we developed TSES-R in our study to measure the parents' expectations of robots for healthcare. In our adapted version (as seen in Table 1), we referred to the original first ten items from TSES and additionally developed items 11-20 (items in bolded texts) for measuring the parents' expectations for a robot designed to help their kids in a healthcare setting from the Social/emotional dimension (S/E; item [11][12][13][14], the Playful distraction dimension (PD; item [15][16][17], and the Assistive role dimension (AR; item [18][19][20]. The justifications for adding these three dimensions are driven by the related capabilities of current robotics technology reported in the literature (see above in sections 2.1-2.3 accordingly). ...
... which suggests very good internal consistency. Additionally, we found that the extended part (i.e., items [11][12][13][14][15][16][17][18][19][20] of TSES-R also had a satisfying internal consistency (α=0.877). To further understand how the S/E, PD, and AR are interrelated in this TSES-R, we performed a Principle Component Analysis (PCA). ...
