[00:00:00] Speaker A: The robot is about the size of a person. We made sure to think about form factor. We needed the robot to go onto the hospital unit floor so it couldn't be too big.
[00:00:15] Speaker B: Hello, everyone. Welcome to the Robot Industry Podcast. I'm looking forward to interviewing Vivian Chu. She is a roboticist with over a decade of experience in human robot interaction. She created Moxie and Polly and applied her HRI and machine learning expertise to platforms like PR2 Mecca and Canova Jaco2. She has worked at Google X Honda Research Institute and IBM Research. Vivian holds a PhD in robotics from Georgia Tech and an MSE from the University of Pennsylvania. She's been recognized by MIT Technology Review in the 35 Innovators under 35, Fortune 40 under 40. Named a Google Anita Borg Scholar and Stanford EECS Rising Star. She's been awarded Best Cognitive robotics paper at the ICRA and featured on RoboHub's 25 Women in Robotics list. Vivian, welcome to the podcast.
[00:01:10] Speaker A: Thank you. Thank you. I'm excited to be here. Sorry to be talking to you.
[00:01:14] Speaker B: Jim, it's great to have you here. And you're in Austin, Texas today. I imagine you travel a lot, so it's kind of nice to be home.
[00:01:20] Speaker A: Yes, yes. I was actually just earlier in the Seattle region, so it is nice to be home.
[00:01:25] Speaker B: Vivian, can you tell our audience a little bit about Diligent and kind of who you are? I did your intro, but who you are and what do you make at Diligent?
[00:01:32] Speaker A: Yeah, yeah. So I'm one of the co founders and the chief innovation officer here at Diligent Robotics. Diligent, we make robots that work side by side with people in human dynamic indoor environments. Our first product, our flagship product is Moxie the robot. So Moxie is a robot that goes around hospitals doing the tasks that people don't want to do. And the first task in particular is just walking things from place to place. So the robot will go and deliver labs, medication, lightweight equipment, just things that currently have people walking. That just doesn't make sense. By having the robot do that, then people can spend more time with their patients.
[00:02:12] Speaker B: Talk about a complicated place. We'll get in the hospitals, that is. We'll get into that in a minute. But I kind of was curious, how did you get interested in robotics and automation?
[00:02:23] Speaker A: Yeah, I probably have similar stories to other folks in robotics, but for me, it's technology has always been at the forefront. Even I was growing up, I would always like classic story, take things apart, try to put them back together, not always successfully. And so when I went to college, it was very much looking at engineering. I drove into electrical engineering and computer science, and it was interesting, but just there was something missing about things staying on the screen and not being able to see it work in the real world.
I mean, they work in the world, but to seeing it. And actually, for me, I took a Intro to Robotics class late in my college days, and that was transformative. We had the iRobot create where it is the Roomba without the vacuum. We had to program it to climb ramps using accelerometer and explored the room and environment. And for me, that was an aha moment where I got to connect my electrical background with programming and have things interact and change and move in the world. And so once I did that, I was like, wait, I'm at the end of college. I need to do more. So then I went on to graduate school, really thinking about how robots can make a difference and impact people. And that's where I discovered how, like, honestly, just how stupid robots are and how you have to spend a lot of time programming them and getting them to do things that were useful. And so I end up spending a lot of my graduate who are thinking about natural language and machine learning and how can robots quickly learn and adapt to the environment, use things like haptic and sensing and touch and all those things, Really, I fell in love at that point where you can spend days in the lab, not realizing they spent days in the lab. And so from there, we saw the technology improve so much and that it was potentially ready. And you would write in your research papers, robots are coming. Robots are here to help and make a difference.
And my co founder and I were like, let's actually go and make that difference.
And then. So that's how Diligent came to be. I know that wasn't your question, but that's how I got interested in robotics and decided that the technology was here and we should go and put it around people. And it just wasn't a thing that you could even find when we started the company in 2018.
[00:04:49] Speaker B: Well, you've had a hand in creating a lot of robots, but I'd really like to talk about Moxie. Can you tell everyone what does moxie look like? And how would they recognize moxie if it was if they were in a hospital setting?
[00:05:00] Speaker A: Yeah, yeah. So moxie is, we like to joke, the MVP humanoid robot. So moxie has a head, a face.
So that head has multiple degrees of freedom so it can look around.
The whole torso is on a mobile base, so it doesn't have legs, but it has wheels, so it roams around.
And then the main differentiator for us, aside from the head, is that we also have an arm, a full 7 degree of freedom arm on the robot.
The robot is about the size of a person. We made sure to think about form factor. We needed the robot to go onto the hospital unit floor, so it couldn't be too big.
It had to be compact, but also give enough workspace that our arm can actually interact with the world.
I like to think the robot's pretty cute. And when the. When the folks at the hospital see Moxie, or anyone really, they appreciate how. How we've managed to navigate the uncanny valley of robots quite well. And we've really designed Moxie to be a teammate where they think about how they can offload their work and their tasks to the robot. And so, yeah, so that's a little bit about the form factor and what Moxie looks like. And then we can go into a lot more details of why we decide on head and wheels and an arm. But those are crucial aspects in order for the robot to do its task, which is navigate the hospital fully autonomously in order to make deliveries and allow the staff to save time and spend it with their patients.
[00:06:29] Speaker B: So I have a question about how did you decide? Because you could have gone into so many different, easier environments, but why did you choose hospitals? I'm curious.
[00:06:37] Speaker A: So, yes, they're definitely like classic robotic environments, like warehouses, areas where people and robots don't interact.
We really were thinking about a few things when we selected the hospital market.
One, we wanted to pick a place where there was a need. Hospitals, nursing and staff members. They just. There aren't enough in the world, honestly. Right. There's a staffing shortage. They are often burned out because they're doing a lot of work they didn't sign up for when they. When they wanted to go and help people and be nurses. For example, a quarter of all new nurses end up burning out in the first year just because they're so busy. And so we wanted to pick a location where really there just wasn't enough people. The work should be focused on giving that time back to the people who are doing the work. And also hospitals. Yes, it's a really complex environment, but it's still simpler than, say, your home as a stepping stone because it's ADA compliant. You have pressure plate doors.
And so there's some aspects of it that actually do make it a little bit less challenging while still tackling the hardest part, which is people and dynamics. So we went with a little bit more semi structured environment.
But then we got to deal with directly the complexity of people who've never seen a robot before who don't know how to interact or walk around or even.
And that's been incredible journey that we are very excited to be a part of because it means that we have built robots and are building models now that can handle some of the most dynamic environments today.
[00:08:11] Speaker B: Well, and imagine that's a hospital, right, where stuff is left everywhere in the hallways and you're. Yet Moxie has to navigate all these things, all these constantly changing environments.
[00:08:21] Speaker A: Yes. So exactly. We definitely think about.
We definitely think about how you can't assume that that pallet is going to be there or not, or that bed or that wheelchair. Right. You have to very much think about what are your behavior systems look like. We have a whole set of behaviors in our system where it's like things are going to be blocked. You want to get to a place it's not going to be free. What do you do? And it's a surpr.
That's just one example, right. Of what happens when you hit a dynamic environment with people.
[00:08:51] Speaker B: Well, and even a person staying in front of a robot. I do that all the time. I'm like, I just want to see what the robot's going to do. And you're right that I think people are afraid of robots in general and that they've never. So that's one of the reasons you want the nurses like, oh my God, can we just get a robot to do this? And yes, the answer is yes, we can.
[00:09:07] Speaker A: Yeah, it definitely, when we first show up, we do a little bit. We have to do education and change management because otherwise. Yeah, there is uncertainty. What is, what are robots? What is it here to do? But once we explain what Moxie does, how it gives them time back, they start throwing out more, more things that the robot should do than even Moxie does. We're like, okay, okay, let's do this first and then we'll come back with our next product.
[00:09:32] Speaker B: So that's a good segue into my next question. What are some of the economic drivers and maybe who are the decision makers in hospital? Like, what's their pain points?
[00:09:41] Speaker A: Yeah, so there's multiple. So there's multiple decision makers throughout. So this is actually like if you think about it from like an enterprise sales. It's a standard enterprise sales model where we have our key stakeholders at the very top, Chief Nursing Executive, CFO, CEOs that are thinking about how do we continue to staff our hospitals? How do we continue to have good bed turnover and be able to have enough people that they can even have all their beds open? There are some hospitals we've talked to that they might have 500 beds, but they can only open 400 because they don't even have enough staff legally to service all 500 beds.
Those are all the aspects. Those are some of the decision makers at the top. All the way down to working with the direct nurses and technicians, like lab technicians and pharmacy technicians, who are the ones day to day trying to do their work and being interrupted and using the robot and giving us the direct feedback of what's working and what's not working.
So you need to make sure across the chain that you've really showed the roi, which is allowing the operational leaders to, to close job wrecks that they can't fill and have been open for a whole year.
And then on the actual frontline, give them time back so that those who are working in some double, triple shifts can then do less and actually do their work in a, in a less stressful environment and not burn out.
And so from like the economic driver, it's really around time returned to those staff members so retention their ability. Like we heard one hospital where Moxie does lab deliveries and before, because there just weren't enough people, the lab deliveries would just come in these batches, right? Like, okay, well we got enough now we'll send one person down and bring it all to the lab, right? And so that was the workflow before, but then now they have a fleet of robots, I think they have six robots actually. And though because they have this, because they have this fleet, they can just send the labs as they're getting collected. And so a, the labs are getting done faster, so the patients are getting the results faster, which is fantastic from a patient quality perspective and outcomes. And then the lab technicians were also more excited because instead of having a giant batch and they're like frantically processing every single one and then they sit there idle, they have a more predictable workflow where they can do their work and have a nice stream come in and they can make plans around that from their time perspective. So that's just like one example of how time returned reducing burnout. And then honestly, then not having to staff additional runners or not being able to even hire them are ways that the, like when you go all the way to the cfo, what they're thinking about and why they're excited about Moxie.
[00:12:37] Speaker B: I love the fact that you're Talking to nurses and you're getting feedback from staff.
But what are some of the surprises that you might have learned from hospitals about robotics that you didn't think about?
[00:12:47] Speaker A: Oh, there's so many probably go into this list. There were some that we were expecting would be a surprise, but then when we really went into it, so maybe specifically about nurses like you mentioned up until this point, robots next to people for long periods of time is just not anything anyone has done. So you'd have your research papers in HRI where you're like, okay, here's a long term longitudinal study where someone had a robot for a month maybe here's like a set of small set where they had a smaller tabletop robot and they had it for a whole like six months. Then you have maybe your toys like the Anki robots, right? And like those probably the gamut, but nothing where you have a robot working with you side by side in these environments. And our robots have now been out there for two and a half years just working with people.
And so novelty effect. We didn't know whether or not like would people just adapt? Would they be constantly, constantly feel like the robot is novel, like what's going to happen? And so we were surprised on how quickly people adapt to robots. They incorporate into their day to day. It becomes a little bit. And this is what we would love to hear. It comes a little bit like their appliance, right? Your dishwasher or something at home, right? You trust it, you rely on it, it's part of your workflow. But then the also surprising aspect was just people are still delighted by the robot even though they've been working with the robot for so long, right? You walk down the hallways, the nurses and staff, I can occasionally hear, it's like oh, moxie meeped at me, right? Like we have a mode where moxie will go around if it sees a person, it might make hard eyes or meep. And you still get those comments even though the robot has been there for a year. And I think that was surprising. I just assumed at some point people would just be like, eh, it's a robot, it's whatever, it's moxie.
But they truly still love interacting with the robot.
So that's more on the staff interaction, probably on more of like deploying robots into hospitals.
We're in the age of technology.
Connectivity is non trivially hard. Like just making sure your robot has connection to an Internet in an indoor environment was something that was incredibly surprising to me.
I think with a lot of other technologies like Self driving. You can be outside and you have an LTE connection and you like don't have, I mean you probably have a little bit of struggles when you're in like more urban and dense environments. But inside a hospital you have basements, you have different access points, there are dead zones, the dead spots. And so I assumed in a hospital environment where you have like MRI machines and all this equipment that connectivity would be more solved, but it is not. So that that was surprising.
And maybe the last one is just human creativity. We talk about how dynamic human environments is challenging.
Our robots open over 200,000 doors every month.
That's in order to do the tasks and deliveries. They do 30,000 deliveries a month and they have to open over 200,000 doors to do those deliveries.
We thought by hospital five or 10, we've seen all the ways people can mount a badge reader and mount a door pressure plate. We were wrong. We are now at Hospital like 25 and we're like, okay, I think we're getting there. But really human creativity, we have, we have examples where, which is like mind blowing and it's a hustle. It makes sense. Maybe like there's a pressure plate that was mounted right under a hand sanitizer. So you go in and like, I guess you like get some hand sanitizer, you push on the door and you clean your hands. So we had to be like, does the robot have to like if it triggers the hand sanitizer, like what do we do? Right, yes.
So it's. Yeah, yeah. That I knew that we were going to be dealing with variants, but it's just been fun seeing the creativity of how things come to be in these kind of environments.
[00:16:50] Speaker B: No, that's great. Thank you for that.
So my next question is a little bit on the AI side. So I was kind of interested to find out why Diligent chose to go AI hybrid versus all in on AI.
[00:17:03] Speaker A: Yeah, yeah. I think there's a lot of buzz these days about are you an AI native robot and you're just doing everything fully end. And for us we take a very pragmatic approach. There are some tasks that are much better with AI and there's some tasks that you have classical controls and they work well.
Also you need data to build your models. And so it's interesting, almost like a chicken and egg problem. Well, how do you build these amazing end to end models when you don't have the data, but then you can't deploy and get the data until you can actually work in the environment? So we've been taking this hybrid approach where we take some classical, more classical robotics, more classical ML approaches where we can then deploy the robot out into the world.
These methods are good, but they're a little bit more brittle. They don't scale as well. If we want to do this to a thousand robots, those approaches start to, you see the cracks and limits. But in the beginning, these approaches get us to where we need to be right in these environments, you need to be 99% right, 99.9 in terms of accuracy in order to deliver.
So it takes a little bit more effort in the beating for us to get there and get a hospital installed. And still it's fast. It's like within six to eight weeks we can get up and running.
But that creates this massive data fly that we've been using to collect more and more data so that we're now just replacing modules now going through and saying this whole section can be end to end.
Maybe this section doesn't make sense. And then because we've built this back end classical approach too, we always have a fallback right. Of something's going wrong. Let's fall back to our past solution. It might be a little bit more brittle and requires a little bit more remote support from our team, but it works. And so that's how we've been approaching this in a very pragmatic way.
But we do see the future is more AI, more models. But how do you build those? Well, you do it with this massive data set that we now have with our nearly 100 robots out there day in and day out, 200,000 doors every day, every month that we are using to collect this interaction and deploy.
[00:19:10] Speaker B: Thank you for that, Vivian, the importance of execution for you, like, you know, when you're doing demonstrations and then you go on to deployment. What taught Diligent different than the lab couldn't?
[00:19:20] Speaker A: Ah, that's a, that's a great question.
We very consciously in the beginning thought about, we wanted to be different from what we, we guessed other robotics companies do, which is stay in the lab, build something perfect for three years and then find customers and say, hey, we have this perfect thing. Now we very much are taking a human centered approach and continue to do so. Understand the problem, understand your customers. Like in the beginning of Diligent, we actually spent 150 hours just shadowing nurses and staff at the clipboard and stopwatch because we wanted to know we have a general purpose robot. What should that robot even do?
And so for us it was really important to see those problems natively and we even in the first two years of the company spent those two years fully in research mode where we drop our robot in and just try things that we thought could be useful.
Now people would say anything that we thought we could actually eventually do long term.
We got some crazy ideas. We're like, no, no, no, the robot's never going to be able to do that, so we're not going to do that for you.
But in doing so we learned a lot about not just about the technology, but change management, how people see technology and integration into their workflow.
What truly was giving them value versus not, which is early days we wanted to just straight go into more dexterous manipulation. And what we saw is the first step was let's do hospital wide navigation, solve that portion of it. And now what we're doing is going back and doing more of the dexterous manipulation in the beginning. But we wouldn't have made that understanding if we didn't go out into the world and see actually their number one problem and is the like 20,000 steps and like 20 minutes of walking every trip that we can give them back immediately. Because when you can't have a supply in your supply room, you have to go find it anyway. So if we first worked on the supply room, we would still have the problem of needing to navigate to the rest of the hospital to get that supply. And so those are things that we were able to get faster to product market fit. And then we're just solving problems now in the world that, that people don't even know that there are problems they're going to have to solve because they haven't put those robots out into the world. Things around locked obstacles, things around connectivity. And these are just like one of like hundreds of things that we're addressing now that if you were in the lab, it wouldn't even come up as a thing because you wouldn't have realized it's going to, it's going to come and be a challenge.
[00:21:54] Speaker B: And so you're.
Your strategy about designing robots to serve as co workers instead of like a human replacement has really worked very well for both nurses and for the company too, and the hospitals.
[00:22:06] Speaker A: Exactly, exactly.
It really highlights and makes everyone think about what is the lowest. Right. Dull, dirty, dangerous, right work that you don't want people to do. And how much of that are your currently highly paid, highly licensed staff doing? And so it ends up being a really, really interesting conversation for the hospital as because they have to think about, wait, how do I continue to level up my staff and it works out really well for the staff members. Right. Because they get to have these great discussions with their leadership on what do they enjoy doing, what do they want to do more, what do they not want to do?
[00:22:41] Speaker B: And Vivian, I imagine just like in some of the big warehouses that people are automating, that people want to work with Moxie, Right. If they know they're going into a zone where Moxie is doing all their walking, it's like, yeah, I'll work near Moxie for sure.
[00:22:54] Speaker A: Yes, yes. There's definitely some of our hospitals that are just like, like that, like to take their new nursing students through at Meet Moxie. They're like, when you finish nursing school, come back to us because we have robots. Right. And we will make your lives easier. Because it's an actual competitive thing where you go into a dense city and they have multiple hospitals. They can choose where they go. So if they know that there's a hospital that thinking about them and dedicated the, like, resources to making their lives better, then they might choose them more.
[00:23:25] Speaker B: So Moxie is a talent attraction device as well?
[00:23:28] Speaker A: Yes, yes. We've actually gone to a career fair, funny enough, where they're like, bring Moxie.
[00:23:32] Speaker B: We're like, okay, so what are the key design elements that you've built into Moxie, which makes Moxie, like, ultra adaptable, dexterous and safe?
[00:23:42] Speaker A: Yeah. So there are probably a couple of layers that we think about when we think about being adaptable and dexterous.
One, like, in general, one of the things that we decided early on, which was actually different, I like to joke that we were doing humanoids before humanoids were cool.
We put an arm on the robot. We got questions in the early days of like, why did you put an arm on your robot? If you imagine now there's like, why would you not put an arm on the robot? Right. Are the questions you're getting.
But for us, that was crucial. We had a full 7 degree of freedom arm on our robot because we knew the environment was going to be complex. We knew we were going to hit things that we cannot predict.
So we needed something that would give us that full range of motion. So already from the beginning, thinking about a platform that has the workspace to handle that diverse environment was already from the very beginning. And this is why we really focus on mobile manipulation and tackling mobile manipulation way before anyone thought it was necessary and has proven incredibly valuable now because we can deploy faster, we can handle more environments. We're building out the models now that people are having to start to build Out.
And so that's been sort of the key strategy around adaptability for us. And then as we collect more and more data, right, Our robots are doing some crazy dexterous manipulations and planning. We're continuing to build out more data so we can do even more.
So that's been our strategy there. And then from a safety perspective, we really think about safety from different layers. And given that we're in this crucial environment around people and hospitals, we very much think about low level from the hardware. The arm we selected was one intentionally because it was designed to go on wheelchairs originally. Every single joint has torque sensing, designed to have very few pinch points, designed to be around people. And so if it bumps you, like, if it bumps you, it's honestly, it's fine. Right? As opposed to you do not want a warehouse large kuka arm bumping you at any point in time. Not fine.
So then we go in and then you say we have like, well, safety layers around our sensors and safety layers around our behaviors, and then even safety layers around, like, we track very carefully how long each task takes. Right. Every single delivery has a patient behind it. It. So we're thinking about even to that highest level, how are we making sure that people and patients and their staff are getting what they need when they need it?
Because it impacts things. So that's. We think of it from all those. Like, in healthcare, they also. They call it the Swiss cheese model, right. And so we're thinking about it at all stages. So you can catch things because never every single layer is not going to be perfect.
[00:26:34] Speaker B: You know, you're talking a lot about data, and I imagine that the hospitals are kind of interested in this data too, right? Because it helps with their ROIs and helps with lots of other things.
[00:26:42] Speaker A: Things.
[00:26:42] Speaker B: How interested in. In data are the hospitals?
[00:26:46] Speaker A: Very, very much in data.
It was actually interesting. Talk about having a lot of customers. And like, we built out a customer success team and we're like, here's the initial graphs that you might care about. And then by the hospital, 10, we had like 20 extra graphs of what we were like, okay, we clearly underestimated what they want to know about the robots. So they are constantly wondering what takes their staff away, where the robots are going, where the most common deliveries are.
All of those portions come into play and they. And they want. And they don't have that when they have people walking the hospital. So it's really interesting. Now that they have a robot, we can actually be like, oh, sure, we'll just pull the most common locations the robot goes to. And you can see, you can see.
And so they can correlate to what is taking the staff away. Right. What are the items they can think about long term? Right. Is there route optimizations? Because this is a common place.
And then they're trying to connect this. The ultimate is not just thinking about the time and the locations and what's taking their staff, but they're also now trying to look at outcomes. Can we. One of our hospitals that had the robot for a long time, they're seeing a huge decrease in turnover. And it's like, well, can we correlate the number of steps to that?
Another hospital is looking at. Can we look at. At bed rotation, like, because we're doing discharge meds and are the meds coming sooner? So they are very much looking at all the data, using it to better optimize their operational efficiency, because they're constantly thinking about that. And so we're just excited to be part of that journey with them, to be able to transform the way that they can get data. Because now they have a robot because before you couldn't. And maybe that's even for pharmacy. It's a big one too. Where before.
We currently have badge access into our robots. So you now know at any point in time, like chain of custody of like, who has been interacting even with all the medication. And so these are things that just are things that didn't exist before that are. They're like gold. Right, essentially to the hospitals and helping them make improvements.
[00:28:53] Speaker B: Vivian, you just brought in some new executives to your team. Can you tell our audience a little bit about that and how. What kind of. Some of the expectations?
[00:29:01] Speaker A: Yeah, yeah, it's been very exciting for us.
We were looking at where we are as a company and thinking, well, what's next for us? We have our technology, we have our first, like, I would say almost like our first prototypes out in the world helping.
But our first hundred robots are not going to be the same way that we're going to scale to our next thousand. And we're really thinking about how do we get to that next level, how do we scale, how do we continue to use our data Flywheel to build those next generation of models that we are in the forefront of. And so as a result, we went out and decided to go find talent that could help us get there. And so, very excitingly, we actually brought on two executives, the COO and the COO at Cruise, and that was Todd and then Rashed was the VP over all of their AI and tech stack at cruise. And so bringing the two of them together is really going to help us scale and take us to the next level is think about how do we take these 100 robots and then take them to 1,000 robots? And we're excited because they see just so many parallels of what they had to tackle and solve. And they're seeing that here. And that's also why they're excited to join us. They're like, we know how to do this.
We see the potential here. We see that you've done something no one else has done, which is start to deploy.
So let's go and actually deploy this faster together. There.
[00:30:29] Speaker B: That's great. And what is next for Diligent? Now that you've proven yourselves in hospitals, do you have plans to expand into, say, offices and factories? And what makes your stack capable of doing it?
[00:30:41] Speaker A: Yeah, great question. The we always look at Moxie actually, as it's a robot that can handle complex indoors environments, period. We have there. There are more dynamics that we might be seeing in hospitals, like beds and wheelchairs that are a little bit specific. But otherw Moxie is a robot that can handle people and be around people. And so there are a lot of environments like offices, retail space that can and need robots in this kind of environment. So for us, what we've learned is we're continuing to build out the models, we're continuing to see that people are people, and we are very much seeing that these are transferable to other industries. So, yes, we're very much looking and thinking beyond hospitals and healthcare.
And really, by capitalizing on what we've built in this flywheel, we can continue to allow to continue to build out our systems to go to these next industries. So we're very excited. Which one is Next? We're not 100% sure to talk about yet, but we definitely have some really interesting ideas of where things are most transferable before. We also just say we're a robot that handles indoor environments. In any indoor environment, we're ready to go to.
[00:32:02] Speaker B: That's great. And so the future of robotics and working with people, you see a very bright future in front of you, I assume?
[00:32:09] Speaker A: I do. People always ask, well, okay, say fast forward.
What do you want the robots to be doing? Or how does that look? And so the future for me is really around seamless and collaborative robotics, where robots are your teammates.
Robots are handling all the repetitive tasks and going even further from where we are today. Robots are just here to make everything easier so you can actually reduce even cognitive load. For example, in hospitals, the future for me is you walk in or your staff member, and things are just where they need to be, just like period, full stop, right? You know, you need to get a blood sample from your patient, right? The order hits the medical record. Your supply for that patient to get that blood draw is now outside your patient room. You've taken that blood draw for them. Now, once that blood draw has been taken, it got scanned to the system. A robot comes and takes it away for you to the lab, right. If you're in your inventory supply room, you know that something's a little low. Robot comes and stocks it, right? Just so everything is where it needs to be so that you can focus on. On exactly what you care about, which is taking care of the patient or. Right. In other industries, thinking about the complex creative work that you are excited to do and just not thinking about the things that just don't matter and getting it done or just extra work or more like chores. Right.
[00:33:41] Speaker B: Vivian, this has been a great conversation. Did we forget to talk about anything today?
[00:33:45] Speaker A: I don't think so, actually. I was thinking. I was like, wow, we covered a wide swath of things.
So I'm just excited that we got to talk about moxie in the future and how we're making some of the biggest pushes and real deployed robots out in the world doing complex mobile manipulation.
And I think we covered that. So I'm very excited.
[00:34:09] Speaker B: You're a busy new mom, and when you're not automating, innovating, building robots and companies and AI, what do you like to do? Do you have any hobbies?
[00:34:18] Speaker A: Ah, hobbies.
Right now it feels like. What do you mean hobbies?
[00:34:24] Speaker B: You do two of them.
[00:34:25] Speaker A: Y two biggest hobbies are my kids.
So funny enough, let's see. I like to go outdoors. I like to eat.
So I combine the two with my other hobbies. With my kids, we go on a lot of walks. Austin has a lot of food trucks, and so we'll go on a walk and then stop by a food truck and I can eat some fun food or try something new. I'm waiting for them to get a little bit older because one of my longtime hobbies has been going to snowboarding.
It's a little hot, and there's not enough snow here in Texas, and they're a little small, so I'm just waiting, waiting for all those factors, and I can get back into. Get back into that.
[00:35:04] Speaker B: Well, you know, with kids, too, it's always good to get them to try new foods all the time. You got to try it once. That's been our rule in our house.
[00:35:12] Speaker A: Yes. Yes, exactly.
[00:35:16] Speaker B: So how can people get ahold of you and find out more about Diligent.
[00:35:20] Speaker A: Yes. So you can go to our website www.digentrobots.com or you can reach me at v2illigentrobots.com the confusing part is diligentrobots.com the company is Diligent Robotics, so just watch out for that.
[00:35:37] Speaker B: But yeah, awesome. Thank you so much for being a guest today on the podcast and we appreciate your time and look forward to meeting you in future sometime at a robot event of some sort.
[00:35:47] Speaker A: Yeah, yeah.
Thank you for having me on this, Jim. And it was a lot of talking through some of these, some of these questions.
[00:35:56] Speaker B: Thank you.
Our sponsor for this episode is Earhart Automation Systems. Earhart builds and commissions turnkey solutions for their worldwide clients. With over 80 years of precision manufacturing, they understand the complex world of robotics, automated manufacturing and project management, delivering world class custom automation on time and on budget. Contact one of their sales engineers to see what Earhart can can build for you and their info@airheart automation.com and Earhart's hard to spell. It's E, H R H A R D T. And thanks to our other sponsor, Meademic Industrial Robotics. Mecademic builds the world's most compact and precise robots in industries such as photonics, med devices, optics and electronics. Mecademic continues to set new standards in precision, footprint and flexibility accelerating small component automation for manufacturers, robot integrators and innovators alike. And you can find
[email protected] I'd like to acknowledge a three the association for Advancing Automation. They are the leading automation trade association for robotics, vision and imaging, motion control and motors and the industrial artificial intelligence technologies. You can Visit
[email protected] and if you'd like to get in touch with us at the Robot Industry podcast, you can find me, Jim Beretta on LinkedIn. Today's podcast was produced by Customer Attraction Industrial Marketing and I'd like to thank my team, Chris Gray for the music, Jeffrey Bremner for audio production, my business partner Janet and our sponsors, Earhart Automation and Mechademic Robotics.
