Interview with Kate Candon: Leveraging express and implicit suggestions in human-robot interactions

On this interview sequence, we’re assembly a few of the AAAI/SIGAI Doctoral Consortium individuals to seek out out extra about their analysis. Kate Candon is a PhD scholar at Yale College fascinated about understanding how we will create interactive brokers which can be extra successfully in a position to assist individuals. We spoke to Kate to seek out out extra about how she is leveraging express and implicit suggestions in human-robot interactions.

Might you begin by giving us a fast introduction to the subject of your analysis?

I research human-robot interplay. Particularly I’m fascinated about how we will get robots to raised study from people in the way in which that they naturally train. Sometimes, loads of work in robotic studying is with a human trainer who is just tasked with giving express suggestions to the robotic, however they’re not essentially engaged within the process. So, for instance, you might need a button for “good job” and “unhealthy job”. However we all know that people give loads of different indicators, issues like facial expressions and reactions to what the robotic’s doing, perhaps gestures like scratching their head. It may even be one thing like shifting an object to the facet {that a} robotic palms them – that’s implicitly saying that that was the fallacious factor at hand them at the moment, as a result of they’re not utilizing it proper now. These implicit cues are trickier, they want interpretation. Nevertheless, they’re a method to get further info with out including any burden to the human consumer. Previously, I’ve checked out these two streams (implicit and express suggestions) individually, however my present and future analysis is about combining them collectively. Proper now, we’ve a framework, which we’re engaged on enhancing, the place we will mix the implicit and express suggestions.

When it comes to selecting up on the implicit suggestions, how are you doing that, what’s the mechanism? As a result of it sounds extremely troublesome.

It may be actually exhausting to interpret implicit cues. Folks will reply in another way, from individual to individual, tradition to tradition, and so on. And so it’s exhausting to know precisely which facial response means good versus which facial response means unhealthy.

So proper now, the primary model of our framework is simply utilizing human actions. Seeing what the human is doing within the process may give clues about what the robotic ought to do. They’ve completely different motion areas, however we will discover an abstraction in order that we will know that if a human does an motion, what the same actions can be that the robotic can do. That’s the implicit suggestions proper now. After which, this summer season, we wish to prolong that to utilizing visible cues and taking a look at facial reactions and gestures.

So what sort of situations have you ever been type of testing it on?

For our present venture, we use a pizza making setup. Personally I actually like cooking for example as a result of it’s a setting the place it’s simple to think about why these items would matter. I additionally like that cooking has this ingredient of recipes and there’s a components, however there’s additionally room for private preferences. For instance, someone likes to place their cheese on prime of the pizza, so it will get actually crispy, whereas different individuals prefer to put it below the meat and veggies, in order that perhaps it’s extra melty as a substitute of crispy. And even, some individuals clear up as they go versus others who wait till the top to take care of all of the dishes. One other factor that I’m actually enthusiastic about is that cooking will be social. Proper now, we’re simply working in dyadic human-robot interactions the place it’s one particular person and one robotic, however one other extension that we wish to work on within the coming yr is extending this to group interactions. So if we’ve a number of individuals, perhaps the robotic can study not solely from the particular person reacting to the robotic, but in addition study from an individual reacting to a different particular person and extrapolating what that may imply for them within the collaboration.

Might you say a bit about how the work that you simply did earlier in your PhD has led you thus far?

After I first began my PhD, I used to be actually fascinated about implicit suggestions. And I believed that I wished to give attention to studying solely from implicit suggestions. One in every of my present lab mates was centered on the EMPATHIC framework, and was trying into studying from implicit human suggestions, and I actually appreciated that work and thought it was the course that I wished to enter.

Nevertheless, that first summer season of my PhD it was throughout COVID and so we couldn’t actually have individuals come into the lab to work together with robots. And so as a substitute I did a web based research the place I had individuals play a recreation with a robotic. We recorded their face whereas they had been taking part in the sport, after which we tried to see if we may predict primarily based on simply facial reactions, gaze, and head orientation if we may predict what behaviors they most well-liked for the agent that they had been taking part in with within the recreation. We really discovered that we may decently nicely predict which of the behaviors they most well-liked.

The factor that was actually cool was we discovered how a lot context issues. And I believe that is one thing that’s actually vital for going from only a solely teacher-learner paradigm to a collaboration – context actually issues. What we discovered is that typically individuals would have actually massive reactions nevertheless it wasn’t essentially to what the agent was doing, it was to one thing that they’d performed within the recreation. For instance, there’s this clip that I all the time use in talks about this. This particular person’s taking part in and she or he has this actually noticeably confused, upset look. And so at first you may assume that’s destructive suggestions, regardless of the robotic did, the robotic shouldn’t have performed that. However if you happen to really take a look at the context, we see that it was the primary time that she misplaced a life on this recreation. For the sport we made a multiplayer model of House Invaders, and she or he acquired hit by one of many aliens and her spaceship disappeared. And so primarily based on the context, when a human seems at that, we really say she was simply confused about what occurred to her. We wish to filter that out and never really think about that when reasoning concerning the human’s conduct. I believe that was actually thrilling. After that, we realized that utilizing implicit suggestions solely was simply so exhausting. That’s why I’ve taken this pivot, and now I’m extra fascinated about combining the implicit and express suggestions collectively.

You talked about the specific ingredient can be extra binary, like good suggestions, unhealthy suggestions. Would the person-in-the-loop press a button or would the suggestions be given via speech?

Proper now we simply have a button for good job, unhealthy job. In an HRI paper we checked out express suggestions solely. We had the identical area invaders recreation, however we had individuals come into the lab and we had a bit Nao robotic, a bit humanoid robotic, sitting on the desk subsequent to them taking part in the sport. We made it in order that the particular person may give optimistic or destructive suggestions throughout the recreation to the robotic in order that it will hopefully study higher serving to conduct within the collaboration. However we discovered that folks wouldn’t really give that a lot suggestions as a result of they had been centered on simply making an attempt to play the sport.

And so on this work we checked out whether or not there are alternative ways we will remind the particular person to offer suggestions. You don’t wish to be doing it on a regular basis as a result of it’ll annoy the particular person and perhaps make them worse on the recreation if you happen to’re distracting them. And likewise you don’t essentially all the time need suggestions, you simply need it at helpful factors. The 2 situations we checked out had been: 1) ought to the robotic remind somebody to offer suggestions earlier than or after they fight a brand new conduct? 2) ought to they use an “I” versus “we” framing? For instance, “keep in mind to offer suggestions so I generally is a higher teammate” versus “keep in mind to offer suggestions so we generally is a higher group”, issues like that. And we discovered that the “we” framing didn’t really make individuals give extra suggestions, nevertheless it made them really feel higher concerning the suggestions they gave. They felt prefer it was extra useful, type of a camaraderie constructing. And that was solely express suggestions, however we wish to see now if we mix that with a response from somebody, perhaps that time can be an excellent time to ask for that express suggestions.

You’ve already touched on this however may you inform us concerning the future steps you might have deliberate for the venture?

The massive factor motivating loads of my work is that I wish to make it simpler for robots to adapt to people with these subjective preferences. I believe by way of goal issues, like with the ability to choose one thing up and transfer it from right here to right here, we’ll get to some extent the place robots are fairly good. Nevertheless it’s these subjective preferences which can be thrilling. For instance, I like to prepare dinner, and so I would like the robotic to not do an excessive amount of, simply to perhaps do my dishes while I’m cooking. However somebody who hates to prepare dinner may need the robotic to do the entire cooking. These are issues that, even in case you have the right robotic, it may’t essentially know these issues. And so it has to have the ability to adapt. And loads of the present choice studying work is so knowledge hungry that you must work together with it tons and tons of occasions for it to have the ability to study. And I simply don’t assume that that’s real looking for individuals to really have a robotic within the house. If after three days you’re nonetheless telling it “no, whenever you assist me clear up the lounge, the blankets go on the sofa not the chair” or one thing, you’re going to cease utilizing the robotic. I’m hoping that this mix of express and implicit suggestions will assist or not it’s extra naturalistic. You don’t must essentially know precisely the proper method to give express suggestions to get the robotic to do what you need it to do. Hopefully via all of those completely different indicators, the robotic will be capable to hone in a bit bit sooner.

I believe an enormous future step (that isn’t essentially within the close to future) is incorporating language. It’s very thrilling with how giant language fashions have gotten so significantly better, but in addition there’s loads of fascinating questions. Up till now, I haven’t actually included pure language. A part of it’s as a result of I’m not absolutely positive the place it matches within the implicit versus express delineation. On the one hand, you possibly can say “good job robotic”, however the way in which you say it may imply various things – the tone is essential. For instance, if you happen to say it with a sarcastic tone, it doesn’t essentially imply that the robotic really did an excellent job. So, language doesn’t match neatly into one of many buckets, and I’m fascinated about future work to assume extra about that. I believe it’s an excellent wealthy area, and it’s a method for people to be rather more granular and particular of their suggestions in a pure method.

What was it that impressed you to enter this space then?

Truthfully, it was a bit unintended. I studied math and pc science in undergrad. After that, I labored in consulting for a few years after which within the public healthcare sector, for the Massachusetts Medicaid workplace. I made a decision I wished to return to academia and to get into AI. On the time, I wished to mix AI with healthcare, so I used to be initially interested by medical machine studying. I’m at Yale, and there was just one particular person on the time doing that, so I used to be taking a look at the remainder of the division after which I discovered Scaz (Brian Scassellati) who does loads of work with robots for individuals with autism and is now shifting extra into robots for individuals with behavioral well being challenges, issues like dementia or nervousness. I believed his work was tremendous fascinating. I didn’t even notice that that type of work was an choice. He was working with Marynel Vázquez, a professor at Yale who was additionally doing human-robot interplay. She didn’t have any healthcare tasks, however I interviewed together with her and the questions that she was interested by had been precisely what I wished to work on. I additionally actually wished to work together with her. So, I by chance stumbled into it, however I really feel very grateful as a result of I believe it’s a method higher match for me than the medical machine studying would have essentially been. It combines loads of what I’m fascinated about, and I additionally really feel it permits me to flex forwards and backwards between the mathy, extra technical work, however then there’s additionally the human ingredient, which can be tremendous fascinating and thrilling to me.

Have you ever acquired any recommendation you’d give to somebody considering of doing a PhD within the subject? Your perspective shall be significantly fascinating since you’ve labored exterior of academia after which come again to start out your PhD.

One factor is that, I imply it’s type of cliche, nevertheless it’s not too late to start out. I used to be hesitant as a result of I’d been out of the sphere for some time, however I believe if yow will discover the proper mentor, it may be a very good expertise. I believe the largest factor is discovering an excellent advisor who you assume is engaged on fascinating questions, but in addition somebody that you simply wish to study from. I really feel very fortunate with Marynel, she’s been a superb advisor. I’ve labored fairly carefully with Scaz as nicely they usually each foster this pleasure concerning the work, but in addition care about me as an individual. I’m not only a cog within the analysis machine.

The opposite factor I’d say is to discover a lab the place you might have flexibility in case your pursuits change, as a result of it’s a very long time to be engaged on a set of tasks.

For our closing query, have you ever acquired an fascinating non-AI associated truth about you?

My predominant summertime interest is taking part in golf. My entire household is into it – for my grandma’s a centesimal birthday celebration we had a household golf outing the place we had about 40 of us {golfing}. And really, that summer season, when my grandma was 99, she had a par on one of many par threes – she’s my {golfing} function mannequin!

About Kate

Kate Candon is a PhD candidate at Yale College within the Laptop Science Division, suggested by Professor Marynel Vázquez. She research human-robot interplay, and is especially fascinated about enabling robots to raised study from pure human suggestions in order that they will change into higher collaborators. She was chosen for the AAMAS Doctoral Consortium in 2023 and HRI Pioneers in 2024. Earlier than beginning in human-robot interplay, she acquired her B.S. in Arithmetic with Laptop Science from MIT after which labored in consulting and in authorities healthcare.