Hi, everyone. Thank you so much, Kelly, for the intro, and thank you everyone for attending today's panel. Hi. Today, my talk will be on brains and thoughts and making the two work together. So before I start, my good friend, L-E, here, would like to say a few words. 

[VIDEO PLAYBACK] 

[END VIDEO PLAYBACK] 

[LAUGHS] So some brief background. I entered Mount Holyoke College as a neuroscience and behavior major and later realized towards the end of my sophomore year that I also wanted to pursue a computer science major. So since I was a sophomore at that point, I really had to scramble to find an internship that could incorporate some knowledge from both fields. And more importantly, I really wanted to gain new experience in programming and possibly learn new languages to balance my skill sets. 

So I worked previous summers at the Yale Child Study Center, and while researching many of their labs, I happened to stumble upon the Technology and Innovation Lab. And something that's really common for STEM majors is that if you're not a client through a RISE program or an undergraduate summer program for research, most of the time, you were simply reaching out to a lab. Either a lab director, a post-doc, or a principal investigator. 

And usually you send an email, send a resume, a cover letter, and you link them to your LinkedIn account. And so before you start applying to labs, I think it's really important to know clearly what skill sets you wish to stretch before you apply to these labs, and you let them know what you're passionate about and what you're eager to learn. And I think that really makes up for any lack of experience in the field. 

I believe that while I did lack a lot of technical experience, my willingness to learn a lot of new languages and understand how to program really got labs to consider me. And I think, while it's certainly important to build upon already existing connections, it's always an option to consider. 

Yale Child Study Center was a really good entity with a strong community of researchers, and they are all more or less knew one another in the Center. So I was really able to build upon the various connections and managed to find Technology Innovation Lab through that. 

So overall, there's no official application or interview, except for maybe a formal psych interview sometimes. So it's important to maintain flexibility when you're applying to a research experience at a lab that isn't offered through a RISE program. And so it was also really hard to emphasize various aspects of your resume. 

So for example, while I didn't have a lot of experience in technology, I had a lot of experience working with children. I had a lot of tutoring experience, and I also had a lot of knowledge in scientific writing. And so it was all about making certain skill sets appeal to the particular lab's mission statement and their overall goals. So that was how I found my internship. 

My projects, well, L-E, what you saw, was my main project this summer. I also worked briefly with ongoing projects working with [? Keypon ?] and [? Sparrow. ?] I can talk to people about that later if they're interested. But L-E was my main project, and it was just getting started when I entered the lab, so it was really a great experience to see L-E change and evolve, working out the bugs, developing the protocol and the experimental design throughout the summer. 

So to go over, briefly, what I did, both of my coding was in Visual Studio, which I had no prior experience working in. And then it was also working with an Arduino board, which is a pretty standard microcontroller. We interfaced it with an Arduino servosensor here, and that was able to attach through multiple servomotors that would allow us to control the facial movements of the robot. 

So Visual Basic was mostly to call the servomotor functions and coordinate the movements of the robot's face and other behaviors. So this is what it overall looked like from the back after we put it together. And we also created a GUI from which we could tele-operate the robot or remotely control from an operating room. 

And so as you can see, there are faces, various actions and body positions, conversational basics, scripts, and so forth. We also wanted to personalize it as much as we could. So we would have a name box. We'd enter the child's name, so when the child came in, the robot would be like, hi, Jeffrey, and the child would be like, whoa, how do you know me? So that was really exciting to see the child react. 

So after implementing all these behaviors and gestures, giving it a voice, giving it a personality. Getting to work with it, we moved on to the more behavioral neuroscience aspect of the project, which was introducing them to ASD therapies. And the most prevalent therapy is pivotal response treatment, and it's considered an effective therapy that's more personalized for the child. 

It focuses on the child's interests and works with the child in a way that's much less stressful. A lot of ASD treatments, known behavioral therapies, are known to be stressful and not necessarily effective for children with ASD. And so we try to build upon pivotal response training. There's also a lot of ongoing research regarding the learning by teaching paradigm, which was established by a psychiatrist named William Glasser. And he established that 90% of what we retain the most is through what we teach. And so there's a learning period associated with that. 

There's also a lot of emerging research based on the benefits of socially-assistive robots used in ASD therapy. They're known to reduce stress and pressure often associated with interacting with people. So we believe that socially-assitive robots would be an effective way to help children with ASD feel more comfortable learning in academic settings, if they were to engage with a robot beforehand or to learn how to interact with them. 

So I'm just going to go over this really quickly because of lack of time. We recruited about six to 10 participants for our pilot study. They were children ranged from five to eight, all varying intensities on the autism spectrum disorder. And we allotted about a 20-minute session for the child to interact freely with the robot, to get a general idea of what the child was interested in. And from that, after that 20-minute session, we would develop a simple script in which the child could ask questions and encouraged the child to teach the robot a concept that they were passionate about. 

And we formulated the same script that we have with the robot with a human confederate, and after that, we compared and measured, through video coding, the following points. We looked at percentage and duration of responses from the child when the robot initiated a communication versus when the human confederate initiates communication and when the facilitator initiates communication. 

The lag time of the child's responses to the robot. The percentage and duration of child-initiated communication, number of conversational turns, and quality of conversation. And this was done through video coding. 

Unfortunately, video coding is a very long and tedious process, and I did not intern at the Technology Innovation Lab long enough to obtain statistical data. But we did receive-- well, L-E received a lot of love. There were a lot of parent comments. 

Parents who sat in the observation room said they were really excited. Their child had never been so engaged and passionate and have not been so talkative before. With L-E, a lot of children demanded revisits with L-E after meeting him and having the two sessions. So those were all good-- I think that's the best data of all, seeing people react well to L-E. 

And then for future directions, we plan on making L-E more autonomous. Before I left, I added a little bit of speech recognition, but it was very buggy. So getting rid of the bugs, adding a camera for face detection, et cetera. So moving from tele-operating to autonomy. And then we also want to introduce L-E to a lot of local schools. They planned on piloting them in in-school tutoring programs at local schools. 

OK. Before I end, I just wanted to show you that when we first started, L-E was not a very attractive robot. L-E was [INAUDIBLE]. And so there was a lot of growing and evolving. 

So while L-E grew, I also grew. I learned lot of things. I made a lot of mistakes. So if you don't get a mechanical engineering student to help you with the 3D printer, the robot's face will be orange. [LAUGHS] But we worked with it. The kids were fine. They liked orange. We just told them L-E was a little under the weather. 

So we worked with that. Other times, things just don't work out, and the robot looks creepy. Like uncanny valley, there are no eyebrows, it just looks really creepy. But ultimately, L-E ended up being quite a cute, adorable, and charming robot. 

The tie, the little bowtie, we also got a bunch of different kinds. We made a lot of little bowties. So L-E's got a lot of different personalities to understand what the child likes. For this project, I'd like to thank my mentor, the PI, and I met a lot of awesome and brilliant professors and researchers that I had the pleasure of working with this summer. So questions?