Observations on Robot-mediated Behavior Intervention (RMBI) for autism

I need to share at the outset that I am not a medical expert or an expert in autism diagnosis or treatment. I am however an experienced technology executive with over 45 years of real-world experience on focusing emerging and new technologies to address and solve real world problems and challenges. When I entered the robotics field it was not long before I experienced firsthand the engaging and positive impact that robotic technology had upon children with autism.

The history of the utilization of robots as a pathway vehicle to effective autism therapy has been attested to by many leading researchers. Bottom line is that numerous university-based research studies attest to the positive impact robots can have on autistic behavior intervention. The reasons for the positive findings while varied, group around the following observations. Children trust robots. Most children are captivated by robot interactions. Robots do not tire in their interactions. Robots do not inadvertently convey upsetting facial expressions or use nuanced voice inflections that children find distracting or even upsetting. Robots do not get emotionally swayed off the path.

This article is founded upon my observations while working to increase the attention and focus of clinicians, researchers and educators on the as of yet unrealized future positive possibilities and benefits of robot assisted behavior interventions for autism or what I refer to as robot-mediated behavior intervention or RMBI.

The numbers of children being diagnosed with autism continue to increase at an alarming rate. The CDC now has posted that number at 1 in 59 children. This is a staggering number. The impact on individual lives is also staggering. The average cost for a family to care for an autistic child is approximately $60K/year. Autism is a lifelong challenge and it is not just an early childhood issue. Being able to “skill develop” and prepare younger children for their learning and teenage years and then on to self-sufficient adult living can take years of behavior intervention and skills development. The burden on families emotionally and financially can be crushing. Most therapists would agree that 40 hours of therapeutic and skills development interactions and behavior interventions per week is what is needed. Imagine dedicating 40 hours per week to the treatment of a single child? That is a full-time job for anyone.

At the foundation of robot-mediated behavior intervention lies ‘behaviorist’ psychological principles, that behaviors are the result of ‘stimulus-response’ interactions and that resulting behaviors can be observed by the therapist and learned by the child through the repetitive utilization of such interactions. In the case of autism, we are striving to encourage the recognition and learning of acceptable social interactions and create confidence in their adoption and use by the child with autism.

While many states in the U.S. recognize the need especially for early childhood intervention and many now even provide some financial subsidy or medical reimbursement for such therapy, the available resources outstrip the demand. Most of the burden falls upon special education teachers in public or special needs schools and increasingly on the families of children with autism themselves.

Great progress is being made to culturally embrace children and adults with autism. Autism is now more frequently seen less as a disease or a handicap and more as a condition that bespeaks the uniqueness of a person. “Each child is unique” is the mantra of those impacted or those working with those impacted. While I respect these sentiments, it tends to belie the work that needs to be done to treat such a devastating condition. None the less we must always keep in mind that every therapeutic approach must embrace the uniqueness of the child being cared for.

More than a decade of research has established the fact that human-robot interaction possesses a huge potential as an intervention tool for many children with autism. The world-wide prevalence of autism has triggered the need for training professionals and developing new technologies to efficiently deliver autism intervention to a wave of demand that if it has not already, will soon overwhelm providers.  Technology-aided interventions should be seen as emerging tools for autism intervention and robot-mediated behavior intervention (RMBI). More importantly as robot technology advances and costs lower the possibility of having a robot mediated intervention platform that can be used in a “at home” setting is the real target. Leading researchers have documented that 30 days of 30 minute in home use can have very positive results.

Another noted university researcher has recently stated however, that “Despite impressive new developments in robot-mediated behavior intervention (RMBI), there is a huge gap in understanding among robotics researchers, robotics industries and stakeholders (autistic children, parents/caregiver, and clinicians) on the clinical utility of robots in autism intervention, best practice in RMBI, and the robotics technology (hardware and software) required to establish RMBI as an effective evidence-based practice (EBP) in autism”.

We are entering a new era of robotics and for social robots in particular. Advances in artificial intelligence and machine learning when combined with the hardware elements and technologies that comprise today’s robots clearly point to a future where much of the behavior intervention work can be assisted by or transferred to a social interactive style robot. Every day we learn more about robots that can sense emotions and derive diagnostic, personality-based information by ‘reading’ facial expressions. Unfortunately, the momentum in robot-based autism behavior interventions once driven by university-based research programs has lessened as seemingly, in their minds the case for the use of robots has been made. While this is true, we now need to advance, in a unified manner, the software, robotic platform design and the Applied Behavior Analysis (ABA) curricula needed to establish the expanded viability of robot mediated behavior interventions. This needs to be done so that more individuals, family members in particular, and not just professional therapists can with the assistance of a social robot, engage in credible behavior intervention and skills development therapies. Families need access to comprehensive social robot-based platforms that can increase the amount of productive skills development time they can provide to a child’s development.  This is especially powerful as therapy in a home-based environment is a more natural and less threatening environment than a school room or a therapist’s office location. This approach would open the pathway to an increased utilization of robots in autism behavior interventions which in turn expands the number of hours that can be applied to therapies and skills development.

Much is being said and written about the impacts, advantages and threats that the advent of the age of robots has and will have on our society and culture. And, those discussions and debates are important and vital to our perceptions and our thinking. However, I believe that the use of robots in therapeutic sessions for autism and many other conditions will only continue to develop and expand. The major objections to the advancement of robots in the medical arena I encounter are (1) robots remove the human touch (2) robots are to expensive and (3) robots will take my job away. To which I observe that we adopt the use of X-ray machines and MRI machines which improve on our human constraints, and that costs will overtime, be reduced as adoption grows and the need for workers in robot related fields will expand, creating jobs. 

What I rarely hear is that robot mediated behavior does not work. Experience the child with autism in front of a robot and you will see the real joy of engagement. It is that experience that makes for the passion to continuously work to advance robot-mediated behavior intervention.

*Michael D. Radice is Chairman, Technology Advisory Board of ChartaCloud Technologies / Robotteca

.

Robots Can Inspire.

Having been in technologies for far too many years to mention, I have always been amazed at the discovery of the unexpected paths when new technologies are introduced. Two recent studies have proven once again, that introducing a new technology, in this case, a robot, into a sector can generate new and innovative approaches to doing things.

 

In the first instance, using robots to teach children seems like the right idea and the right approach. Using robots to teach children expands available instructional resources and robots have the patience to repeat and re-iterate until the correct answer to a question is provided by a student. These are just a few of the attributes of ‘teaching’ robots. There are many more of course. But researchers are discovering that turning the tables can make for a great learning experience. Have the children teach the robot! This approach is the result of an expanding field of robotics studies and a class of robots called “Care Receiving Robots” (CCR). Children take on the task of helping the robot learn to do something and by doing so learn the subject themselves. Suddenly, the number of potential ideas for such an approach is seemingly endless.

In a similarly structured project that I am involved with, students are challenged with a planetary exploration where the robots are on a remote planet, but the students need to solve problems or overcome challenges managed from their Earth-bound operations Center. They need to teach the robots to explore the planet and prepare the new planet’s base of operations in anticipation of humans arriving on the planet.

In another sector, autism, it is deemed beneficial to utilize robots in the delivery of robot-mediated behavior intervention in autism. The approach has been to provide the robots as an augmented resource to/with a professional therapist to deliver the intervention session. Here again, researchers have determined that it is possible and beneficial for family members themselves to use the robot in their homes and thereby expand the amount of therapeutic time that can be given to a child with autism. This is especially powerful as therapy in a home-based environment is a more natural and less threatening environment than a school room or a therapist’s office location. This approach now opens the pathway to an increased utilization of robots in autism behavior interventions which in turn expands the number of hours that can be applied to therapies and skills development.

So, there we have it, inspirations. Children teaching robots and robots in the home doing therapies. These are just two examples of what I have seen time and time again or as the old showman’s saying goes, when it comes to robots: “You ain’t seen nothing yet!”

Mike is Chairman of the Technology Advisory for ChartaCloud ROBOTTECA

Top 5 Advances Needed in Robot-mediated Behavior Intervention Technology in autism and Why We Need Them

The number of children diagnosed and thus impacted by autism continues to rise, and staggeringly so. Recall, that in 1985 children with autism was estimated to be 1 in 2500. Ten years later in 1995, it was 1 in 500. The CDC now estimates (2018) 1 in 59. Associated lifetime costs have risen past $3 million dollars. Medicaid costs for children with autism is reported to be 6 times the normal at over $10,000.00 per year. ABA therapy at $120.00 per hour for 10 hours of therapy per week, puts therapy cost at an annual rate of over $50,000. per year. 80% of children with autism are in divorced families. The human costs over a life time? Special living requirements? Employment potential? Lost productivity? Social lifestyle impacts? How can these be quantified?

To even have a chance at mitigating these impacts early intervention is critical. The efficacy of early interventions are, therefore, even more critical.

The utilization of social robots in autism behavior especially in early intervention is an emerging and powerful force. The past initial phases of academic research clearly demonstrated that ‘robots’ can be an effective resource used in behavior intervention therapies. We now face the challenge of further developing hardware, software and curriculum that improves upon and enables the transfer of robot-mediated behavior intervention technologies to be more broadly used and more cost-effectively deployed to therapists, special education professionals, school teachers and, yes, even to parents, guardians and family caregivers.

Bottom line is that current intervention methods and resources are not sufficient to address the growing need. As technologists working with autism experts we can and must do more with robots.

What is needed?

I helped organize and conduct a just completed workshop held under the auspices of Carnegie Mellon University’s 2018 Robotic Sciences and Systems Conference in June 2018. The workshop was designed to specifically address this very subject. Participants from academia, education and the robotics industry joined-in to contribute their thoughts about the current state and the future design requirements needed to support the advancement of robot-mediated behavior intervention.

Robot-mediated behavior intervention needs to advance to the next level with:

1    1.     More software behavior ‘APPS’ for use with the robots – especially for early age (3-6) use
2.       APPS that are highly customizable to the ‘speed, sound and voice interaction’ needs and capacities of individual children
3.       Robotic platforms that are less disrupted by the environmental conditions of ‘light and noise’
4.       Advanced technological response interfaces for ‘non-verbal’ children
5.       More accurate and more comprehensive data collection progress and performance data capture facility built into the ‘APPS’

The full list is longer but the above five will help significantly move ‘progress and adoption’ measures. The next major technological phase will be machine-based learning algorithms that designs in real time, custom therapy interventions. I will soon address that subject in a future blog.

Michael Radice is Chairman of the Technology Advisory of ChartaCloud | ROBOTTECA and can be reached at mike@chartacloud.com

How One Robot Can Transform A Library and Its Community

While there is a lot of justifiable discussion about the pros and cons of a future world cohabited with robots, one thing is clear – positive outcomes are being achieved. It seems every day we see a new leap forward in robot construct, artificial intelligence, machine learning object manipulation and facial and emotional visual recognition being exhibited by robots. As someone who is immersed in the world of social robots and robot process automation the pace of innovation I see is staggering.

Equally wondrous in the world of social robots is the creative manners they are being put to use. That too takes imagination. The proliferation of use cases is now significantly expanding beyond proto-typical research. True uses are now being substantiated and legitimized. When one first encounters a social robot the most prevalent question is what can it do? Many times, the environment is a clue to that answer and sets expectations. Encounter a robot behind the concierge desk in a hotel and you expect it can make dinner reservations, get you tickets to a play or make a golf tee time. This is happening. Encounter a robot in a retail cosmetics store and you would expect cosmetic advice based on its perception of your style and ‘facial’ attribute composition. Happening.  Encounter a robot in an art gallery and you would expect expert advice and counsel on the art pieces being displayed. This is happening.

Imagination gets even better. I have experienced seeing a NAO⁽¹⁾ social humanoid robot in a community library and all-of-a-sudden they had an exciting and engaging community digital literacy program. Library traffic and value perception of the library went way up. (Think fundraising.) One robot can serve multiple audiences. In another library, it also became a resource for the local school such that students can do STEM robotics programming assignments at home or in school and then come to the library to test them out on the robot. Parents that have children with autism go to the library to use the robot to do their own ABA/pivotal response training and social skills development exercises and interventions. Art groups are planning to conduct robot performances. The robot becomes a knowledgeable spokesperson, information resource, and presenter for special community educational events. So, this too is happening, and it is engaging and transformative.

Local businesses, community fellowship groups, church groups and individual donors now have a unique opportunity to positively impact their communities with – one robot. One robot causing good things to happen.

Mike Radice is Chairman of the Technology Advisory Board for ChartaCloud | ROBOTTECA www.robotteca.com. (1) NAO is a product of Softbank Robotics.

Observations on the New Era of Retail Brand Management and Humanoid Robots

 Driven by the introduction of humanoid style social robots we are rapidly entering a new era of consumer engagement and with it a new opportunity for marketers and retailers to secure competitive advantage. The initial introductory phases of robots in consumer engagement models have been mostly about fast food restaurants where they work as receptionists/order takers, in consumer banking as product concierge spokespersons, and in airports as information guides. While that will continue, more businesses engaged in a wider variety of consumer ‘retailing’ are finding the use of robots simply too compelling to ignore.

The driving factor is not that robots are less expensive than humans or are being used to replace workers. The real driving factors are that businesses can learn from the robot’s interactions with consumers at a speed and at a depth not possible via human staff and that consumers can benefit from the knowledge conveyed by the robot. Paper-based consumer survey information or store based data collection/extraction exercises can take months to filter and categorize. Today’s technologies enable that time to be reduced to minutes. A properly designed robot used in a consumer retail ‘brand management’ engagement model will add significant value to the consumer relationship and a competitive advantage to the business.

The lure of humanoid robots in a retail settings rests on the robot’s attraction and engagement power. Consumers are drawn to the aura of an interaction with a humanoid robot and the robot’s mobility to ‘meet and greet’ and even lead them on the route through the store to the product of their choice. More deeply is the anthropomorphic effect whereby people trust robots in many instances more than humans.

The digital toolset of consumer engagement platforms that already includes smartphones, chatbots, computer tablets, laptops, interactive digital kiosks has now expanded to add humanoid retail / concierge robots.

A few examples set the stage.

A robot ‘sommelier’ in a wine store that can recommend a wine respective of your taste and price range having recognized you as a returning previous purchaser and knowing your prior experiences would certainly enhance the loyalty and satisfaction of the customer.

A robot in a cosmetics or clothing store that can communicate the ‘hottest’ colors based on the current preferences of ‘celebrities’ or even identify the specific fashion being worn by a celebrity and motivate a purchase suggestion in that store would certainly add to the desirability of shopping there.

With a robot interaction, however, we can now instantly discover quantitative and qualitative data that can guide and refine our consumer engagement strategy.  Properly designed the qualitative element of a robot-based engagement model would enable us to learn/assess/ estimate: age; gender and language for example. Quantitatively, we could learn ‘hot topic’/ issue preferences or the appearance of new or increased demand for certain items or styles etc. and even the emotional posture of the consumer. Decisions about inventory and sales promotions become ever more knowledge-based and data-driven.

What this means is that the engineering of successful future robot-based consumer engagement application design will need to embrace new concepts for consumer engagement, an extensive embrace of gamification strategies, access to third-party information resources, real-time data logging, artificial intelligence and machine learning capabilities.

Furthermore, for larger retailers the need to manage a ‘fleet’ of deployed robots from a central location becomes critical. The essential rules for all adopters of robots in retail will be to be sure to frequently and constantly refresh the robot’s general interaction script with new versions, items and news as no one will be stimulated to revisit a boring repetitive robot; and ever strive to raise the level of personal engagement and gamification. The more custom the engagement interaction to the individual consumer the more powerful the model e.g. show your loyalty card to the robot to prompt it to recall the specific ink cartridge that you need for that printer.

Michael Radice is Chairman of the Technology Advisory Board for ChartaCloud and Robotteca.com and a provider of the leading software for Pepper.

How Four Companies from Four Countries Forged The Powerful Robot-mediated Behavior Intervention Solution Platform for autism.

This week was a landscape changing moment for the advancement of Robot-mediated Behavior Intervention for autism. Three years ago, I discovered that as nation we faced an epidemic in the growth of the number of children impacted with autism. Like many others I thought of autism as only a childhood disease. As I learned more, I came to understand the impact that autism has on the entire lives of children and their families.  And, that these ‘children’ must face the challenge of learning the skills needed to become a self-sufficient, independent adult.  I came to understand that autism is not a disease and that it is a human condition. I have been continually motivated by the dedication of the many therapists, school teachers and parents that I have met along the way.  I decided to see if and what role technology might play in helping meet the challenges.

In my opinion there exists an abundance of researchers and clinicians that contribute mightily to the ‘science’ of diagnosis and care strategies. What I felt was missing was a strategy for those delivering the care. What was currently being done was not sufficiently scalable to meet the rapidly escalating need. The growing volume of the requirements for care are over-whelming the existing care giving resource model. This is true on multiple fronts. Trained care givers are growing in short supply in proportion to the need. Institutions are unable to subsidize the increasing costs of professional care delivery. The medical re-imbursement and insurance systems are playing catch-up while families struggle to afford early diagnosis and arrange early care. Early care being one of the best mediations.

Even on the corporate front the recognition that a new model is needed is growing. 

Corporate programs are starting to emerge. If employing individuals on the autism spectrum is becoming a need and a value- based element of corporate and community responsibility, then special educational and training programs are needed to guide managers and create successful management policies that positively embrace employees with autism in their employee base.

So, the framework of a structural response by and with technology started to reveal itself. I called it the 1-2-3 model and I searched the world to build it.

One. From Japan, I landed upon the use of the NAO social robot from SoftBank Robotics to deliver robot-based mediated behavior interventions. The NAO robot was engaging to many children with autism. The robots were in many circumstances, calming. They were non-threatening. They didn’t tire. They didn’t grow or convey frustration. They could be made to deliver sessions customized to the needs and conditions of an individual child. And, they worked!

Two. The next step was to find a robot-based system that could be operated by non-technical personnel in a common school classroom. That has now been accomplished with askNAO a computer tablet-based system from ERM Robotique in France that easily and quickly connects to the robot and with ‘one touch icons’ be made to deliver an intervention session.

Three. A comprehensive autism therapy practice management system was needed to improve the efficiency, effectiveness and lower the cost of therapy practice operations and care delivery. Integration with the robot and the behaviors was needed. That is now available with TN ActiveCare from Canadian Company TN NORTH.

So here we are ChartaCloud ROBOTTECA in the U.S. now deploying, installing and training end users on a platform that can deliver results in autism therapies, expand delivery resource capacity and lower delivery costs.

I call what has happened - landscape changing. If you would like to learn more about the detailed elements of this platform please message me at mike@chartacloud.com I’d be happy to send you a detailed solution brief.

Mike Radice is Chairman of the Technology Advisory Board of ChartaCloud | ROBOTTECA www.robotteca.com

My Five Most Amazing Moments with A Robot

As I continue to engage in the ‘real world’ of robot use cases…oh? what do I mean ‘real world’? – I mean the actual things that are truly being done, really happening…not theory, not speculations…real stuff, happening every day. The robot I spend most of my time with is the NAO robot from Softbank Robotics.

Amazing Moment #1: A Child in a hospital pediatric ward struggling with muscular dystrophy. This child refused to leave his wheel chair for weeks. But once having interacted with NAO and having been invited by NAO to get out of his wheel chair to sit with NAO on the floor and have his picture taken with NAO – he did just that! A stunningly powerful moment.

Amazing Moment #2: A child with autism, unfocused and erratic was introduced and engaged with NAO. Calm, focus, joy and delight resulted. Because NAO is available in his public library he now visits once week and is studiously progressing in learning about how to program NAO and will soon test his work out at the library. Transformative.

Amazing Moment #3: An eight-year-old, via his parents, contacted me and wanted to share the teaching applications he had developed for his school. It was some of the best quality work I had seen. Amazing yes, at eight years old!

Amazing Moment #4: I was with NAO when he walked out on a stage in front of 7,000 people. Yes, seven-thousand and delivered a show stopping performance. I was very jealous not because NAO was the star but because there was no nervousness, no hesitation, no stage fright on NAO’s part. I seem to recall that he looked at me and conveyed…” Come on we can do this!” Amazing!

Amazing Moment #5: While visiting a Skilled Nursing Facility for the elderly. NAO was used to play a few games and lead a group exercise session. The rejuvenated animation of the elders was overly evident. The proof was that when the session was over, they clamored to want to know when NAO was returning, and could they sit and engage with him (I say him… but who knows…) for a while longer! Hold his hand and take a walk with him. Exciting moments in an otherwise drearily routine day.

The point is, putting aside all the talk and the arguments about robots and what our robot future will be like, we can lose sight that when you are in the real world amazingly wonderful things are happening.

There is a reason that NAO remains the most popular humanoid robot. Above are just a few examples of why.

Mike Radice is Chairman of the Technology Advisory for ChartaCloud |ROBOTTECA See: www.robotteca.com and https://robotteca.blogspot.com/ for more information and articles.