#59 - When a Humanoid Robot Removes A Gallbladder

WEBVTT
00:00:00.000 --> 00:00:03.279
What if the next surgeon you meet isn't human?
00:00:03.600 --> 00:00:09.519
Researchers just had humanoid robots perform gallbladder surgery on a pig.
00:00:18.559 --> 00:00:23.519
Hello and welcome back to Coding Cure, where we discuss decoding health in the age of AI.
00:00:23.679 --> 00:00:25.679
And my name is Vasant Sarathi.
00:00:25.839 --> 00:00:30.559
I'm an AI researcher and cognitive scientist, and I'm here as always with Laura Hagopian.
00:00:30.719 --> 00:00:32.320
I'm an emergency medicine physician.
00:00:32.560 --> 00:00:37.840
And today we're talking about humanoid, humanoid robots doing surgery.
00:00:38.079 --> 00:00:42.960
But that like brings me to my first question because it's not just like any robot, it's a humanoid.
00:00:43.200 --> 00:00:44.960
So like what is what is that?
00:00:45.280 --> 00:00:56.719
Well, first of all, uh to me, I think this whole business of robots doing surgery is really cool because you know you see these science fiction movies and someone's on a bed and you have all of these arms coming down and they're all doing different things simultaneously.
00:00:56.799 --> 00:01:06.000
They're like all perfectly precise, and you know, they help, you know, and if the human is behaving or misbehaving, they're able to like control the human back down and fix the human or whatever.
00:01:06.159 --> 00:01:10.959
And I'm always amazed at at that because it's like, whoa, that's that's the future, right?
00:01:11.120 --> 00:01:12.000
Um is it?
00:01:12.079 --> 00:01:13.920
That's the question of today, I suppose.
00:01:14.159 --> 00:01:14.560
Yeah, yeah.
00:01:14.640 --> 00:01:23.280
But you see that this is like one stream that you see in every science fiction movie, is that you have machines that are basically performing full-on surgeries, right?
00:01:23.519 --> 00:01:29.280
Yeah, and not it's not like to that extent in reality, right?
00:01:29.519 --> 00:01:33.840
But um, there are robotic systems that are being used by surgeons right now.
00:01:34.079 --> 00:01:38.000
Like there's the thing called the Da Vinci system, which is probably the most well-known one.
00:01:38.159 --> 00:01:45.840
Yes, which is not humanoid, it's like robotic arms that perform the surgery with like a human operator kind of videoing in behind it.
00:01:46.079 --> 00:01:46.239
Yeah.
00:01:46.319 --> 00:01:48.480
And so that brings us to what a humanoid is, right?
00:01:48.560 --> 00:01:52.959
Yeah, that imagine the vision of a robot that has 12 arms coming in.
00:01:53.040 --> 00:01:54.159
That's not a humanoid.
00:01:54.319 --> 00:02:04.719
A humanoid is a robot that looks like a human that walks around, has has a couple of arms, has two legs, uh has hands, has hands, often has a head and a face of some sort.
00:02:04.879 --> 00:02:11.120
Uh, maybe not perfectly um, you know, designed to look exactly like a human, like no skin and stuff.
00:02:11.360 --> 00:02:18.400
But it you can imagine when we think of a an a robot, a robot, modern-day robot, like in the movie iRobot or whatever, right?
00:02:18.479 --> 00:02:19.840
Those are those are humanoids.
00:02:19.919 --> 00:02:21.120
They're walking around.
00:02:21.280 --> 00:02:25.199
Um, and it gets a little bit, it's not like a fixed definition by any means.
00:02:25.280 --> 00:02:26.479
There's obviously variance to this.
00:02:26.560 --> 00:02:30.159
There'd be robots that have le don't have legs, but have wheels instead, right?
00:02:30.319 --> 00:02:37.199
But still have arms and and still have, and they might have, you know, three fingers instead of five, depending on what tasks they perform.
00:02:37.599 --> 00:02:38.560
But they're human-like.
00:02:38.800 --> 00:02:39.759
That's the whole idea.
00:02:40.000 --> 00:02:43.840
It's not just like robotic arms that are isolated on their own.
00:02:44.000 --> 00:02:45.759
It's like a human-like entity.
00:02:45.919 --> 00:02:46.319
Yes.
00:02:46.560 --> 00:02:50.000
That is then going into the operating room, walking around and doing stuff.
00:02:50.240 --> 00:02:50.400
Yes.
00:02:50.479 --> 00:02:54.639
And so I think the way to think about this also is what it affords us, right?
00:02:54.800 --> 00:02:55.599
Why do they even care?
00:02:55.680 --> 00:02:57.919
Why does it have to be human looking at all?
00:02:58.000 --> 00:02:59.759
Like what is that and why is that an important thing?
00:02:59.919 --> 00:03:06.000
And and I and I think it's important to realize that we're not saying it needs to look like a human, like in its face or whatever, right?
00:03:06.159 --> 00:03:10.159
Uh, we're saying it's like able to act, like have the dexterity of a human or whatever.
00:03:10.479 --> 00:03:13.360
Have the dexterity of a human, but you know, have mobility, right?
00:03:13.439 --> 00:03:18.159
Being able to move around like a human does in an in a in a in a in an operating room is important.
00:03:18.319 --> 00:03:24.560
And I think that's kind of the basis for this whole paper was that look, we have these surgical instruments out there, like the Da Vinci system.
00:03:24.719 --> 00:03:34.639
These are excellent, they do things really well, a limited number of things, um, albeit, but they do them really well, but they require a lot of infrastructure and a lot of setting up to do.
00:03:34.800 --> 00:03:37.520
And we'll talk about specifically in this paper what that means.
00:03:37.680 --> 00:03:40.080
But more generally, they just need to have a setup.
00:03:40.479 --> 00:03:42.960
The OR already needs to be set up for them, right?
00:03:43.120 --> 00:03:47.120
And so that costs a lot of money and that can be very expensive, and they're very purpose-built.
00:03:47.199 --> 00:03:52.960
They're often um, they uh they're they require some kind of docking, they require, like I said, space.
00:03:53.120 --> 00:03:57.439
They might have um, and and the other thing is they might only be doing one specific thing, right?
00:03:57.759 --> 00:04:00.560
Right, or they might have specialized instruments for certain things.
00:04:00.960 --> 00:04:07.759
For its own, right, for their own uh the idea of the humanoid is to say, look, we need more people doing these surgeries.
00:04:07.840 --> 00:04:09.280
We don't have as many humans doing this.
00:04:09.439 --> 00:04:18.959
Why don't we have instead of having a robot that requires this like bespoke setup, why not just have um a humanoid robot in an existing surgical OR using human tools?
00:04:19.279 --> 00:04:19.680
Yeah, exactly.
00:04:19.759 --> 00:04:23.199
The same tools that a human would like manually be using.
00:04:23.439 --> 00:04:25.199
Yes, that that type of medical equipment.
00:04:25.519 --> 00:04:25.759
Exactly.
00:04:26.000 --> 00:04:28.959
This doesn't like you you don't have no humans involved, by the way.
00:04:29.120 --> 00:04:34.000
Like you have the humanoid robot, but they have a human assistant that's present in the operating room.
00:04:34.240 --> 00:04:35.040
Oh, it's more than that.
00:04:35.519 --> 00:04:42.160
And they have someone, yeah, you know, like a physician who's actually doing the surgery maybe remotely, like with the video screen.
00:04:42.319 --> 00:04:43.759
No, no, it's not maybe that's that's it.
00:04:44.079 --> 00:04:44.800
Maybe yeah, yeah.
00:04:45.040 --> 00:04:47.920
They are not not maybe doing surgery, but maybe they're remote.
00:04:48.000 --> 00:04:49.600
Like they don't have to be physically present.
00:04:49.759 --> 00:04:50.160
Exactly.
00:04:50.399 --> 00:04:54.879
But in all of these systems, it's not like the humanoid robot's just like doing it on its own.
00:04:55.199 --> 00:04:55.600
No, no.
00:04:55.680 --> 00:04:58.720
And in fact, that's it's not a it's not a it's not an AI system.
00:04:58.800 --> 00:05:02.240
It's a humanoid robot, it's a machine that somebody's teleoperating.
00:05:02.319 --> 00:05:05.920
They literally have a joystick, something more than a joystick, but something more advanced.
00:05:06.319 --> 00:05:06.959
It's like a video game.
00:05:07.120 --> 00:05:08.079
It's like a just like a video game.
00:05:08.319 --> 00:05:10.000
Just just removing gobletters.
00:05:10.240 --> 00:05:14.480
Then do you get like 10,000 points at the end when you've successfully removed it?
00:05:14.800 --> 00:05:15.120
Yeah.
00:05:15.360 --> 00:05:16.560
Well, that's it.
00:05:16.639 --> 00:05:18.560
So they have uh it's all teleoperated.
00:05:18.720 --> 00:05:22.000
So let me just take a step back for a second because that is important to note.
00:05:22.319 --> 00:05:35.199
The as much as we've seen a lot of AI development over the last you know a few years and really cool stuff that AI can do, there are some very basic um robotic things that AI can't do even today.
00:05:35.360 --> 00:05:40.240
Like the AI automated robots, it's even simple problems are really, really hard.
00:05:40.560 --> 00:05:44.160
And just think about the simple example of grabbing a tool, right?
00:05:44.240 --> 00:05:49.759
Like a surgical tool or and really anything, there are so many different ways of grabbing it and grasping it.
00:05:49.920 --> 00:05:57.360
And uh the different ways might have different meanings, it depending on if the tool is dirty or clean or if you're passing it to someone versus whether you're using it.
00:05:57.600 --> 00:06:00.959
You can imagine holding it in different places, holding it at different angles.
00:06:01.199 --> 00:06:09.920
Um, and also you want to make sure that in addition to holding it so that it uh can serve its purpose, that you're grasping it so it doesn't fall out.
00:06:10.079 --> 00:06:14.480
Um, you know, and when you hand it over to somebody or they pass it to you, you grab it in the right way.
00:06:14.720 --> 00:06:21.600
There's like a whole bunch of different challenges just in the physics and the mechanism of just grabbing a thing, right?
00:06:21.759 --> 00:06:23.680
That's but beyond that, there's even more.
00:06:23.839 --> 00:06:27.680
There's like navigation, like moving around the surgical room by itself.
00:06:27.759 --> 00:06:31.920
Like if it were completely autonomous, it would need to know where it can go and can't go.
00:06:32.079 --> 00:06:36.560
It would need to be able to move around a surgeon and not bump them, right, while they're busy working.
00:06:36.800 --> 00:06:38.000
Yeah, what happens if it falls over?
00:06:38.399 --> 00:06:38.560
Right.
00:06:38.639 --> 00:06:42.000
Well, it can't it can't trip on something and fall over, which can happen, right?
00:06:42.079 --> 00:06:43.839
These robots are not like perfectly designed.
00:06:43.920 --> 00:06:58.399
I mean, I know we've seen a lot of really cool videos, like Boston Dynamic, for example, puts out these really cool um humanoid robot demo videos in which they like push down the robot and it like gets up and stands up, or it's able to like you know, do like parkour, right?
00:06:58.480 --> 00:07:00.800
Jump through things and do flips and things like that.
00:07:00.959 --> 00:07:01.839
All of that is great.
00:07:02.000 --> 00:07:09.600
But in a surgical setting and in many of these settings, it's way more precision and you know, like careful management of space and and movement.
00:07:09.839 --> 00:07:13.439
The dexterity is like very important for very important, yeah.
00:07:13.680 --> 00:07:18.399
So, like, so having so let's just the whole issue of autonomy is out the table here.
00:07:18.480 --> 00:07:20.639
There's no way this is not doing it on its own.
00:07:20.879 --> 00:07:26.879
Like we're literally just talking about a remote-controlled robot remote-controlled robot that a human is on the other end of that their tele operates.
00:07:27.279 --> 00:07:27.839
Yeah, yes.
00:07:28.079 --> 00:07:29.839
And even that is challenging.
00:07:30.000 --> 00:07:40.399
And so the I think the really cool part of the study was that, hey, it's a good idea maybe to put a humanoid there because they can move around and up and not not require all of this specialized um setup.
00:07:40.800 --> 00:07:45.360
Uh, but then the next question is how do we use it for performing surgery?
00:07:45.439 --> 00:07:46.480
And what are the challenges there?
00:07:46.560 --> 00:07:48.480
And they focused on laparoscopic surgery.
00:07:48.720 --> 00:07:49.519
Yeah, they did.
00:07:49.680 --> 00:07:57.279
And um, laparoscopic surgery is basically the surgery where you get like little tiny holes put in you, right?
00:07:57.360 --> 00:08:00.160
It's not like a big open surgery.
00:08:00.319 --> 00:08:12.959
Um, it is much tinier incisions where they put these little trochars through, they introduce these small instruments and they kind of inflate you with air and they do the surgery and then they close you up and you just have these like a couple of tiny little holes.
00:08:13.199 --> 00:08:17.519
Um, and so that is a very common form of surgery done today.
00:08:17.600 --> 00:08:20.800
Like if you get your appendix out, most people have it done laparoscopically.
00:08:20.879 --> 00:08:23.920
If you get your gallbladder out, most people have it done laparoscopically.
00:08:24.160 --> 00:08:27.199
So it's a great um, it's great because it's very common.
00:08:27.279 --> 00:08:28.160
It's very commonly used.
00:08:28.480 --> 00:08:29.519
Right, right, right.
00:08:29.759 --> 00:08:37.039
And so then the question was like, hey, when we're using a humanoid in this situation, what is it good at?
00:08:37.200 --> 00:08:39.200
Like it needs to have good dexterity, right?
00:08:39.279 --> 00:08:41.039
And good range of motion, whatever it is.
00:08:41.200 --> 00:08:44.159
And like, where, where might there be drawbacks?
00:08:44.320 --> 00:08:45.519
What might it not be good at?
00:08:45.840 --> 00:08:47.679
Yeah, and this is where I think it's very interesting.
00:08:47.759 --> 00:08:52.960
I know we're gonna get a little technical here, but this is where it gets very interesting because of the nature of the problems.
00:08:53.120 --> 00:09:03.759
And I think it's a nice opportunity to talk about, you know, we've talked in abstract about how um uh the old surgical systems take up space and and the modern human eye robots can move around.
00:09:03.840 --> 00:09:05.440
But the issues are even more specific than that.
00:09:05.600 --> 00:09:12.799
So with laparoscopic surgery in particular, one of the challenges is because you're inserting it through such a small point, very small cuts, right?
00:09:12.879 --> 00:09:19.360
It's not a large opening, and you use these very long, thin instruments and cameras through those openings.
00:09:19.679 --> 00:09:19.919
Exactly.
00:09:20.559 --> 00:09:21.440
Yeah, no, exactly.
00:09:21.519 --> 00:09:25.039
And so, because of that, and because once it's inside, you need to be able to move around.
00:09:25.120 --> 00:09:34.799
Like there are things you're doing inside within uh within the confines of that small hole, which means um then there's this point called the remote center of oper uh motion or the RCM.
00:09:34.879 --> 00:09:38.399
Um, that's almost like a point that is the entry point into the skin.
00:09:38.799 --> 00:09:39.600
That is, yeah, exactly.
00:09:39.759 --> 00:09:45.200
And and that point, you you want to be able to kind of pivot and move around it without uh moving across it.
00:09:45.360 --> 00:09:48.240
Because the moment you start moving across it, you're tearing the skin more.
00:09:48.320 --> 00:09:53.279
So you want to keep that hole and keep that skin, but be able to move the tool kind of um kind of around it.
00:09:53.360 --> 00:10:08.799
And and I think we talked about this before, and you gave me a great analogy of of the ore in the in the in a in a in a canoe where you know uh or or a boat where the ore is attached to the side of the boat, and you can kind of like move the oar, but there's a fixed pivot point about which it it cannot move.
00:10:09.120 --> 00:10:09.519
Exactly.
00:10:09.679 --> 00:10:18.000
And so the robotic instrument can like angle and rotate inside the body, but the point at the skin is going to stay the same.
00:10:18.159 --> 00:10:18.399
Yes.
00:10:18.720 --> 00:10:21.039
You can't change that and you don't want to rip that.
00:10:21.360 --> 00:10:21.759
Exactly.
00:10:21.919 --> 00:10:34.799
And and in the old Da Vinci systems, the non-humanoid robotic systems, those things were actual metal things, bars and like a parallelogram or trapezium-shaped thing that held that fixed point in place.
00:10:34.879 --> 00:10:38.159
So the robot machine couldn't accidentally tear your skin.
00:10:38.320 --> 00:10:40.000
So it would be able to operate within that space.
00:10:40.080 --> 00:10:43.120
So that was like a constraint that was enforced physically before.
00:10:43.200 --> 00:10:48.559
But again, that requires a lot of setup and requires the OR to be equipped with something like that.
00:10:48.720 --> 00:10:53.360
But if you don't have that, now you have a machine, a humanoid robot that's walking around with a tool.
00:10:53.600 --> 00:11:00.720
How do you enforce that it doesn't move around along that pivot point, that it stays at that pivot point?
00:11:00.879 --> 00:11:03.200
And that it can still reach everything it needs to on the inside.
00:11:03.519 --> 00:11:06.399
Like a human, for example, might be like, Oh, I can't reach that.
00:11:06.480 --> 00:11:13.679
Let me change my own angle, let me move to the other side of the patient, or let me move closer to the head, or whatever it is to get the angle that they want.
00:11:13.840 --> 00:11:27.840
And so this is one of the interesting things I think they found with the humanoid, which was like, hey, it was able to reach some stuff in the regions that we wanted it to, but then it in other in other areas it wasn't able to.
00:11:28.159 --> 00:11:33.360
So it couldn't reach everything that they that they wanted it to reach or essentially.
00:11:34.080 --> 00:11:35.200
Yes, yes, exactly.
00:11:35.440 --> 00:11:44.960
And you know, uh they had to also constrain the the pivot point that you know, because they in the in the old Da Vinci systems, they had like a physical pivot attachment.
00:11:45.200 --> 00:11:46.320
For these systems, they don't.
00:11:46.399 --> 00:11:47.759
So they had to do that in software.
00:11:47.840 --> 00:11:55.840
So they had to figure out how to make it so that the robot was able to manipulate and move the tool without uh ever changing that fixed point in space.
00:11:56.159 --> 00:11:59.679
Um and there's a lot of geometry stuff that comes into play there, and it's really cool.
00:11:59.840 --> 00:12:01.759
And they were able to figure that out first.
00:12:01.919 --> 00:12:06.159
And then once they were able to figure that out, the next thing was to evaluate the quality of how the system performed.
00:12:06.320 --> 00:12:09.440
And they had and the way they evaluated is to see can it draw straight lines inside, right?
00:12:09.519 --> 00:12:12.240
Can it make straight lines uh while sticking to the pivot?
00:12:12.320 --> 00:12:13.519
Can it make circles inside?
00:12:13.600 --> 00:12:17.679
Because these are the types of motions that are needed inside to be able to manipulate.
00:12:17.840 --> 00:12:21.840
And it was able to do straight lines like pretty well pretty well, yeah, yeah.
00:12:22.159 --> 00:12:22.720
Really well.
00:12:22.879 --> 00:12:29.120
Uh, but circles it had more trouble with, and it was a little bit uh, you know, kind of had a few errors in it, and it wasn't it wasn't great.
00:12:29.360 --> 00:12:32.720
And that just like is sort of setting up for the next stage of research, I'm guessing.
00:12:32.879 --> 00:12:39.120
And they also measured um not just the accuracy, but the latency that is the uh that the time it would take to do these things.
00:12:39.200 --> 00:12:40.799
And humanoids tend to be a little slow.
00:12:40.960 --> 00:12:41.919
That that's just the case.
00:12:42.080 --> 00:12:44.240
They are they are a little bit on the slower side, right?
00:12:44.320 --> 00:12:59.120
But if you are, if I am, for example, I don't I don't do this kind of surgery, but if I am like, you know, the one on the other end of this, kind of directing the robot what to do, and there's I think they measured 150 sec 156 second millisecond latency.
00:12:59.200 --> 00:12:59.440
Sorry.
00:12:59.679 --> 00:13:00.000
That's right.
00:13:00.159 --> 00:13:09.600
Yeah, that means that the time that it takes from for me to the robot or the robot to me, that like that's there's a lag there.
00:13:10.080 --> 00:13:18.159
I I think I would get I think I would get really annoyed by that lag because it's not it's not real time.
00:13:18.320 --> 00:13:22.799
You're not getting real-time feedback, you're not seeing what the robot is doing in real time.
00:13:23.039 --> 00:13:30.080
And so I think that latency is something that would definitely need to be solved for from a user standpoint.
00:13:30.399 --> 00:13:31.360
Yes, exactly.
00:13:31.519 --> 00:13:32.159
Exactly.
00:13:32.320 --> 00:13:48.559
So I think if you were to do what they said was like with manual laparoscopic laparoscopic surgery, uh humans were generally the worst in terms of accuracy, and the Da Vinci robots were the best, these are the non-humanoids with the best in accuracy, and the and and our humanoid robot was kind of in between, right?
00:13:48.720 --> 00:13:51.840
Uh it had some errors with the circle drawing piece of it, at least.
00:13:52.000 --> 00:14:02.799
Um, and then we also had speed, and and again, the humans, sorry, sorry, the Da Vinci robots were the fastest, uh, and the humans were kind of in the middle, and this one was the humanoids were a little bit on the slower side.
00:14:02.960 --> 00:14:08.159
Um, and again, the point is if it was only about accuracy, then the Da Vinci robot wins.
00:14:08.240 --> 00:14:10.559
If it was only about speed, the Da Vinci robot wins.
00:14:10.720 --> 00:14:15.279
But it's about the fact that practic practically speaking, it's really hard to get this everywhere.
00:14:15.600 --> 00:14:18.879
Well, and I would say like the Da Vinci has been around for a while.
00:14:19.120 --> 00:14:19.759
Yeah, it's true.
00:14:20.000 --> 00:14:24.159
And they've probably made a bunch of different iterations on it.
00:14:24.240 --> 00:14:33.519
And so no wonder that it's that's not I'm not surprised that it does better at some of these things because they've probably been working on this for, I don't know, almost yeah, 25, 30 years.
00:14:33.840 --> 00:14:34.559
Yeah, yeah, yeah.
00:14:34.639 --> 00:14:35.120
That's a good point.
00:14:35.200 --> 00:14:36.480
I mean, that's still certainly a good point.
00:14:36.559 --> 00:14:40.480
And humanoids has been in and out, it's been really challenging to work on humanoid robots.
00:14:40.559 --> 00:14:41.919
I've myself worked on them.
00:14:42.080 --> 00:14:49.759
Um, there's a lot of challenging aspects of just like movement and motion and things like that, in addition to the teleoperation and the dexterity and all of that.
00:14:49.919 --> 00:14:55.440
Um, and you know, hopefully doesn't trip on things, you know, like there's all kinds of other things that have to be have to come into play.
00:14:55.600 --> 00:15:03.279
Um, but if they can, if they're getting so close on its performance, um, we're already, you know, a long, you know, we're already a big step there.
00:15:03.360 --> 00:15:06.000
And these robots, uh humanoid robots are getting cheaper.
00:15:06.159 --> 00:15:21.919
I mean, some of these robots they're using is in the range of$15,000 to$16,000, which is which seems like a large number, but when you compare it to like, you know, the Da Vinci system, which is multi-million dollars, it it it becomes a lot more affordable to have um in your system, in your uh in your in your OR.
00:15:22.320 --> 00:15:29.600
Um, so I I think there's there this is just kind of setting up setting us setting us up for some very interesting future work, I'm sure.
00:15:29.840 --> 00:15:32.159
And um, and there are some challenges, right?
00:15:32.320 --> 00:15:33.039
With these robots.
00:15:33.279 --> 00:15:33.360
Yeah.
00:15:33.440 --> 00:15:35.200
And so they took it to the next level, right?
00:15:35.279 --> 00:15:38.879
In this article, they said, okay, we're not just doing like bench top research.
00:15:39.039 --> 00:15:43.919
We're gonna try this in a dry lab and then we're gonna try this in pigs and see what happens.
00:15:44.000 --> 00:15:55.039
And so the dry lab was like kind of normal surgical stuff that you that you might have um people do just as like practice, where you say, Okay, like there's uh these O-rings on a peg.
00:15:55.120 --> 00:15:58.159
I want you to grasp the O-ring and like transfer it to the other peg.
00:15:58.320 --> 00:15:58.639
Got it.
00:15:58.720 --> 00:16:02.639
Um, or I want you to grasp one peg and transfer it to the other side of this board.
00:16:02.720 --> 00:16:11.200
And so it was like regular transfer tasks where you'd have to like, you know, have the dexterity to grab it, pick it up, move it over, and get it on the next location.
00:16:11.360 --> 00:16:11.840
Yeah.
00:16:12.080 --> 00:16:16.879
Um, and and so they compared, like, hey, how is the human doing?
00:16:17.039 --> 00:16:18.320
How is the humanoid doing?
00:16:18.399 --> 00:16:21.519
And again, how is this, you know, DaVinci system doing?
00:16:21.759 --> 00:16:33.279
And not surprisingly, they found the results that we would expect based on what we've just been talking about, where, you know, it was slower for sure.
00:16:33.519 --> 00:16:45.200
Um, people said, hey, it has a less intuitive kind of control interface, and there was also some motion error in it, especially, you know, around this circular type of motion if it was needing to do it.
00:16:45.600 --> 00:16:50.879
And the less intuitive interface is is also another another product of Da Vinci being around for a while.
00:16:51.039 --> 00:16:51.120
Yeah.
00:16:51.519 --> 00:16:54.399
Because they try to set it up with the Da Vinci setup, but it's obviously a little different.
00:16:54.559 --> 00:17:00.080
And so people are going to experience that kind of user interface and user experience type problems, right?
00:17:00.320 --> 00:17:01.039
Totally.
00:17:01.279 --> 00:17:05.839
And so then the next step was like, hey, could we actually do surgery with this thing?
00:17:06.000 --> 00:17:06.400
Yeah.
00:17:06.640 --> 00:17:09.920
Um, and they did two gallbladder surgeries on pigs.
00:17:10.000 --> 00:17:12.480
They were 11 weeks and 16 weeks old.
00:17:12.720 --> 00:17:17.519
Um, and they had one surgeon who was on the console.
00:17:17.599 --> 00:17:22.880
So like they were not present in the room, but they were, you know, operating the robot.
00:17:23.119 --> 00:17:23.359
Okay.
00:17:23.599 --> 00:17:24.319
To do the operation.
00:17:24.640 --> 00:17:26.960
The robot was doing the operation, but they were operating the robot.
00:17:27.039 --> 00:17:27.119
Yeah.
00:17:27.279 --> 00:17:39.599
And there was a bedside assistant in the room who was a human who was doing things like, oh, you know, I something needs to be pulled back, something needs to be adjusted, something needs to be exposed, a camera needs to be cleaned.
00:17:39.759 --> 00:17:42.240
That's normal to happen in an operating room.
00:17:42.400 --> 00:17:43.599
Those are normal things.
00:17:43.839 --> 00:17:46.720
So that that person was human and was still in the room.
00:17:47.759 --> 00:17:52.559
And they found that there were, you know, pauses to do those kinds of things, like clean cameras.
00:17:52.640 --> 00:18:09.039
And then there were actually some longer pauses when the robot needed like recalibration or um physical repositioning because it wasn't able to do it on its own, um, like the the base or the arms relative to how it was, you know, going into the pig's body.
00:18:09.279 --> 00:18:09.680
Oh, interesting.
00:18:10.079 --> 00:18:11.759
So laparoscopic trocarcytes.
00:18:12.480 --> 00:18:20.480
And so those were much longer uh pauses because they would be like three minutes or or longer in the middle of the surgery.
00:18:21.200 --> 00:18:22.960
That seems long for a pause.
00:18:23.119 --> 00:18:30.160
For I mean, maybe maybe it's not, because if you're used to the kind of um pauses throughout the surgery, then maybe it's fine.
00:18:30.400 --> 00:18:31.200
That's that's long.
00:18:31.359 --> 00:18:33.839
I would say the short pauses are normal in a surgery.
00:18:34.240 --> 00:18:39.279
That long of a pause, um, I I don't want to say it never happens, but it would be like a bit more unusual.
00:18:39.519 --> 00:18:39.680
Right.
00:18:39.839 --> 00:18:45.359
But the surgeon, the surgeon who did it said, hey, like it was able to perform the tasks that we wanted it to.
00:18:45.440 --> 00:18:47.920
We could dissect, we could control the instruments.
00:18:48.160 --> 00:18:55.920
Um, you know, I think they did find, yeah, there were some range of motion issues, which is why they had to like stop and move the robot.
00:18:56.079 --> 00:19:00.640
Um, and that there were actually some some limitations in terms of its strength, which is interesting.
00:19:01.279 --> 00:19:01.920
Yeah.
00:19:02.319 --> 00:19:05.599
Um, and then it needed, you know, recalibrating.
00:19:05.680 --> 00:19:08.480
They actually said it it overheated sometimes.
00:19:08.640 --> 00:19:10.319
So they had to like deposit.
00:19:10.559 --> 00:19:10.799
Right.
00:19:10.960 --> 00:19:14.160
Um, which is again like a limitation, but they were able to actually carry it out.
00:19:14.240 --> 00:19:17.920
They were able to do these two gallbladder surgeries on these pigs.
00:19:18.079 --> 00:19:18.640
That's incredible.
00:19:18.720 --> 00:19:22.720
And you know, some of these limitations are uh just like generalized robotic issues, right?
00:19:22.880 --> 00:19:26.480
That can be resolved across the industry, not just for for this use case.
00:19:26.720 --> 00:19:28.960
Um, but there are some use case-specific stuff, right?
00:19:29.039 --> 00:19:34.079
About, I know they talked about sterilization, and that was a big challenge as well was how do you sterilize these things?
00:19:34.559 --> 00:19:42.640
Well, I think that was like, yeah, maybe future work that could be done because here they made it sterile by putting gloves over the arms of the robot.
00:19:42.799 --> 00:19:50.079
But if you think about an operating room, this is a place where everything has to be very sterile.
00:19:50.240 --> 00:19:54.079
Your your field, your field that you're operating in, it gets autoclaved.
00:19:54.240 --> 00:19:57.680
All the instruments um are very, you know, they're autoclaved.
00:19:58.160 --> 00:20:04.240
The the person you're doing surgery on is like draped and cleaned, everything is sterile.
00:20:04.559 --> 00:20:15.440
So I I mean, I'm not a robot expert, but I'm assuming that like when you have like sensors, um, calibration for motion, that kind of stuff.
00:20:15.599 --> 00:20:19.519
If you I don't I don't know that you can autoclave those things, you might wreck them.
00:20:19.839 --> 00:20:23.440
I'm not even sure what what what the what is involved in autoclaving.
00:20:23.839 --> 00:20:25.359
That's interesting in and of itself.
00:20:25.440 --> 00:20:33.519
But I, you know, as far as these these machines are concerned, in my head, I always think of machines being more sterile than humans, right?
00:20:34.000 --> 00:20:42.160
We're we're I mean, in some level, it's just a piece of metal or pieces of metal, and in theory, they're they can be they can be sterilized.
00:20:42.240 --> 00:20:58.160
I mean, I always again going back to these like um science fiction movies, uh, have this notion of having um a a bunch of robots in a in a in a in a in a sterile chamber or in a sterile sterile room because they they don't they don't need to be, they won't pick up bugs and they don't, they don't they don't like you know how to do something like that.
00:20:58.319 --> 00:20:59.200
Well but they could, right?
00:20:59.359 --> 00:21:01.519
If you're exposed to the universe, you could pick up anything.
00:21:02.079 --> 00:21:04.480
And like on top of the human could be anything too.
00:21:04.640 --> 00:21:04.799
Right.
00:21:04.960 --> 00:21:20.960
So the way that you clean the human and then you you drape them prior to surgery, like as a surgeon themselves, like scrubs, puts on sterile gloves that have never touched anything, puts on a sterile gown and a uh a hat and all of this stuff so that you don't introduce contamination.
00:21:21.279 --> 00:21:31.119
Um, autoclaving itself is done for like the instruments, and that's when you have like pressurized saturated steam to sterilize things.
00:21:31.279 --> 00:21:31.839
So I don't know.
00:21:31.920 --> 00:21:40.720
I'm like, in my mind, I'm like, oh, this combination of like water, water is not good for water and like no heat, right, um, and and robots.
00:21:40.880 --> 00:21:44.000
I in my mind, I'm like, oh, I don't know if the I don't know how how well that would work.
00:21:44.079 --> 00:21:50.160
But the whole point is like you want to destroy all the microorganisms so that you can reuse these critical instruments.
00:21:50.319 --> 00:21:54.000
This is done in your dental office, this is done in medical office, etc.
00:21:54.480 --> 00:21:56.160
And it's moist heat under pressure.
00:21:56.240 --> 00:21:56.799
That's how they do it.
00:21:57.039 --> 00:21:58.000
Yeah, that's a huge problem, right?
00:21:58.160 --> 00:21:58.640
For robots.
00:21:58.720 --> 00:22:09.680
So, but again, it's a that's a materials and manufacturing problem, not necessarily an AI or health um specific to the healthcare sector, right?
00:22:09.920 --> 00:22:10.400
Oh, for sure.
00:22:10.480 --> 00:22:15.839
It's not, I mean, you might need it in other locations, but in the healthcare sector is where you need things really clean.
00:22:15.920 --> 00:22:20.640
Yeah, you can't have contamination or else you're gonna get infections internally.
00:22:20.799 --> 00:22:24.480
Like, can you imagine taking out someone's gallbladder and like leaving behind a bunch of E.
00:22:24.640 --> 00:22:27.680
coli or something that then like they get an internal infection from?
00:22:27.759 --> 00:22:29.759
It's like not good, not good, not good.
00:22:30.000 --> 00:22:38.160
So I think this is it's important to call out because when if you're trying to scale something like this, it could be a very significant barrier.
00:22:38.400 --> 00:22:39.599
That's a good, that's a good point.
00:22:39.759 --> 00:22:42.640
That's a good point, but very exciting work nonetheless.
00:22:42.880 --> 00:22:44.079
Yeah, I think it's interesting.
00:22:44.160 --> 00:22:50.720
We haven't done a lot of episodes about robotics and uh specifically about humanoids.
00:22:50.799 --> 00:22:57.200
And I think it's interesting to dive into the specifics of like, hey, they were able to do this, but these were the limitations.
00:22:57.519 --> 00:23:04.240
No, I think specifically around like how it can manipulate an instrument, yes, um, or not, right?
00:23:04.480 --> 00:23:18.000
I think that was really interesting because I hadn't I hadn't necessarily thought of that before as an issue, but when you but like now that I now that I read this paper, I'm like, oh yeah, that seems very obvious that like it it's not gonna work quite the same as a human would.
00:23:18.160 --> 00:23:28.160
Um, and then you layer on top some of the things like, oh, it's taking too long to send the images back and forth, or um, we don't know how to make this sterile at scale.
00:23:28.319 --> 00:23:34.559
Uh I think there's a lot of opportunity and potential here, and there's a lot of problems that still need to be solved.
00:23:34.799 --> 00:23:35.200
Yeah.
00:23:35.440 --> 00:23:35.759
All right.
00:23:35.920 --> 00:23:37.519
With that, we will end today.
00:23:37.680 --> 00:23:38.640
Thank you for joining us.
00:23:38.880 --> 00:23:40.880
We'll see you next time on Code and Cure.