At ICRA 2022, Competitions are a core a part of the convention. We shine a highlight on influential competitions in Robotics. On this episode, Dr Liam Paull talks in regards to the Duckietown Competitors, the place robots drive round Rubber Ducky passengers in an autonomous driving observe.
Dr. Liam Paull
Liam Paull is an assistant professor at l’Université de Montréal and the pinnacle of the Montreal Robotics and Embodied AI Lab (REAL). His lab focuses on robotics issues together with constructing representations of the world (similar to for simultaneous localization and mapping), modeling of uncertainty, and constructing higher workflows to show robotic brokers new duties (similar to via simulation or demonstration). Earlier to this, Liam was a analysis scientist at CSAIL MIT the place he led the TRI funded autonomous automotive undertaking. He was additionally a postdoc within the marine robotics lab at MIT the place he labored on SLAM for underwater robots. He obtained his PhD from the College of New Brunswick in 2013 the place he labored on sturdy and adaptive planning for underwater automobiles. He’s a co-founder and director of the Duckietown Basis, which is devoted to creating partaking robotics studying experiences accessible to everybody. The Duckietown class was initially taught at MIT however now the platform is used at quite a few establishments worldwide.
Abate: [00:00:00] Good day everyone. That is Abate. Subsequent week is ICRA and a core a part of this 12 months’s convention goes to be robotics competitions. So we’re going to deep dive into a number of the influential robotics competitions on the market. with a few brief spotlights on a number of totally different ones this week, we’ll be speaking to Dr. Liam Paul, the co-founder of the Duckietown competitors.
Hey Liam, welcome to Robohub. Might you give us a bit of little bit of background about your self?
Dr. Liam Paull: Certain. My title’s Liam Paul. I’m a professor on the college of Montreal. I’m additionally the president of the Duckietown basis and one of many co-founders of that undertaking.
I did my PhD in in new Brunswick. After which I did a postdoc in MIT, which is the place this Duckietown factor began. And now I’ve been a proffer about 5 years or so.
Abate: Yeah. So as we speak really we actually wish to dive into the Duckietown competitors. Um, so may you give us a bit of little bit of [00:01:00] details about the way you began it, what your motivations had been?
Dr. Liam Paull: Yeah. So, I imply, the Duckietown factor is one thing that’s type of taken on a lifetime of its personal, for positive. It began as a category firstly, it was used for academic functions, however then sooner or later alongside the way in which we thought that it could have additionally worth as, as a scientific benchmark. And so we began to see if we may reformulate and repurpose the platform to host these these competitions.
And the primary one was it NeurIPS. And I wish to say 2018 after which we’d finished a minimum of one at ICRA and some at NeurIPS and it’s kind of one thing that’s actually actually gathered the motivation, I feel actually is it’s all about attempting to scrupulously benchmark robotic algorithms. And this can be a fairly, it’s really a fairly [00:02:00] exhausting process.
Loads of robotic analysis is completed in some particular lab with a really particular setup and is sort of exhausting to breed. And so we wished to construct a really standardized however very accessible platform that individuals may simply get their fingers on, simply, put their algorithms on, and that we may in some way like evaluate all kinds of algorithms in some.
Standardized and like honest, honest method.
Abate: Yeah. So what’s the precise problem that they’re competing for and the way does it, how does it look?
Dr. Liam Paull: Yeah, so that is developed through the years, however the fundamental premise is, is, is. Principally the identical. In order a part of the Duckietown platform, now we have the automobiles, that are these little, little automobiles that you would be able to construct, however then there’s additionally an atmosphere during which they function.
And the atmosphere is [00:03:00] made up of like yoga mats and duct tape and indicators that we’ve like printed and stuff. Um, however the concept is that it’s very standardized and really reproducible. To you or me, like, it appears like a small metropolis. Prefer it’s a really simplified view of a metropolis, however it’s one thing that approximates in some way a small metropolis and the challenges are very in complexity, however largely concerned the robots navigating on this metropolis.
And we are able to. we are able to differ the complexity by having totally different typologies of town intersections. We will have totally different obstacles, we are able to produce other automobiles. And so the complexity can actually develop. Um, however probably the most type of like fundamental, basic, like a PR factor that an agent ought to be capable of do is like drive down the highway within the metropolis, keep away from obstacles and keep of their lane type of factor.
Abate: Yeah. So what was the motivation behind the title Duckietown?
Dr. Liam Paull: That’s an [00:04:00] fascinating, that’s an fascinating one as effectively, really. So just like the ducky not too many individuals know this, however the ducky branding, not solely does it, it predates the Duckietown undertaking, however it additionally has an ICRA connection. So the opposite co-founder of the undertaking his title’s Andrea Censi and now he’s at ETH Zurich.
And I feel the 12 months earlier than Duckietown began, he was… I overlook precisely what the title was, however it at present this push for everyone to submit movies they usually had been going to try to sew all of those movies collectively to make like a promo video for the, for the convention. And Andrea got here up with the concept each video ought to have a rubber ducky in it kind of for plenty of causes.
However I feel that partially, it was like for scale and likewise for like some type of coherence between the totally different movies. So they may do like enjoyable cuts and stuff in between the movies, however in some way the branding of it identical to completely exploded. After which once we began this undertaking, [00:05:00] like earlier than the rest, the one constraint was that it needed to have like rubber duckies concerned.
I… I don’t know… Simply kind of occurred that method.
no, it’s nice. As a result of once you like grounded in one thing, that’s like a enjoyable idea it makes it way more partaking for individuals to, to wish to do it.
Dr. Liam Paull: Yeah. And there’s additionally a facet of I imply, my view is that some, some robotics specifically is type of portrayed in a sure method.
And I feel that like Hollywood has one thing to do with this. Scary, not like both it’s like Terminator are going to come back and kill you, or it’s scary within the sense that it’s going to take your jobs or no matter. And I feel, yeah, in the long run a part of, a part of the motivation behind this like type of enjoyable, playful type of factor was that we might break this mildew a bit of little bit of attempting to make one thing that’s tremendous quick and tremendous scary and tremendous large or no matter that possibly this might attraction to.
Totally different people who find themselves possibly not [00:06:00] interested in the, like, let’s construct a giant, quick, scary factor, however as an alternative, you realize, additionally need to have the ability to like specific themselves in some way via like via their work. And I feel yeah, I feel that’s additionally been, been a part of it and has been type of, type of profitable.
Abate: And so the competitors now it’s been working for, is it a decade or two?
Dr. Liam Paull: It’s not, no, it’s not that lengthy. I feel it’s, I feel the primary iteration was in 2018. So I feel we’re at like, across the five-year mark. Um, however the five-year time. Yeah. The primary iteration of the category at MIT would have been one thing round 2016.
I feel. So the undertaking itself has in all probability been round for six or seven years, however the, the, the competitors itself possibly solely 4. Hm. Yeah.
Abate: So what have been a number of the, the real-world advantages that that you simply’ve seen out of the competitors?
Dr. Liam Paull: Yeah, that’s an important query. I imply, I feel with Roberta [00:07:00] robotics, I imply, a part of our you realize, philosophy is that robotics ought to contain a robotic.
And I feel particularly in newer previous, there’s been this big pattern in direction of like machine studying and deep studying. Sort of algorithms. And I feel these algorithms actually have big potential, however once you try to put a few of these algorithms on robots, you see a number of the, a number of the type of nitty-gritty particulars that you simply possibly didn’t take into consideration actually have a huge impact, you realize, like how the latency of your system you realize, the way it’s coping with.
asynchronous singles versus synchronous indicators, like treating time, you realize, non-model defects and issues like friction and slippage and issues like this. And so for lots of the oldsters, I feel like the actual, like the actual world profit has been that, wow, they actually have gotten an appreciation for simply how, how powerful it’s [00:08:00] to, to construct these programs.
After which once you have a look at like what, though we’re not all the way in which to having, you realize industrial, autonomous automobiles. I feel that you would be able to get some type of an appreciation for simply how outstanding, what has already been achieved. You already know, it truly is when you think about all of the totally different items that need to work collectively and the way sturdy all of them need to be.
Abate: And I can think about through the years, you realize, totally different applied sciences have taken extra curiosity within the eyes of roboticists and that the method that the totally different individuals competing has modified fairly a bit as effectively.
Dr. Liam Paull: Oh, for positive. Yeah. Initially, I imply, we very a lot noticed fairly conventional what I might name like classical.
Not as a result of they’re previous, however simply because it’s like the way in which that issues was finished, type of like stacked that had the very commonplace abstractions of like, you realize, notion and state estimation and planning and management, and now way more we’re seeing rivals [00:09:00] try to remedy this. And to finish machine studying sort of strategies, whether or not they’re primarily based on extra like imitation studying paradigm leveraging information that we make out there, or whether or not they’re utilizing the simulator primarily.
And simply attempting to do like reinforcement studying stuff. Type method after which switch their brokers that the actual, the actual robotic, these, I, I nonetheless assume it’s like stays to be seen at this level at this juncture, like which one is definitely higher at fixing the duty. However one factor that’s positively true is that the scholars within the rivals appear to be way more they discover the, like, I feel the machine studying type of method is extra interesting at this level.
It’s type of like this sizzling, sizzling subject, I suppose.
Abate: Oh, that’s fascinating. So it’s possibly it’s extra interesting, however possibly it’s not essentially as of proper now leading to a extra success for the rivals.
Dr. Liam Paull: Yeah. I imply, the way in which that I view it, particularly like from a say a scientific standpoint is that [00:10:00] particularly on this atmosphere, all the pieces’s very well specified a very well engineered answer with little or no studying goes to be very exhausting to be.
you realize, the potential advantages of extra studying primarily based programs or that they need to be capable of be extra sturdy to various circumstances, be capable of generalize in kind of a extra, a clean, extra S easier solution to totally different environments. And so, yeah, it’s, it’s not, it’s not all the time simple. It’s not all the time simple to love now we have now we have to consider carefully about even simply what the metrics we’re going to make use of.
to match, you realize, these totally different algorithms, like, is that simply the one which, you realize, drives the quickest? I’m unsure that’s the perfect, you realize, that’s the perfect metric. Um, there’s all these different elements about like robustness and skill to generalize, to totally different like eventualities and issues like that.
And in these instances, the [00:11:00] machine studying options possibly do a bit.
Abate: Yeah, no, it’s an fascinating level about overfitting your answer to particularly the competitors atmosphere, aside from like whether or not or not that’s one thing that you simply actually wish to do as a decide to say whether or not or not this can be a higher answer, it is perhaps higher on this competitors as a result of it was quicker… however ought to the impediment course change a bit, the topology change, now, possibly it’s not so sturdy.
Dr. Liam Paull: I feel that is really the central problem in constructing robotic competitions. It’s very tough to construct a robotic competitors. That’s like not hackable in some sense that you would be able to’t win by simply actually overfitting to the specifics of that exact of that exact setup.
And so, yeah, I imply, I feel. You hit the nail on the pinnacle there it’s that is the large problem for positive. And [00:12:00] attempting to construct like actually good robotic benchmarks.
Abate: Yeah. In order you, as you consider subsequent 12 months’s competitions have you ever guys ever thought of possibly doing a not releasing the map and having it’s a bit extra of a shock and have a bit of extra randomness related?
Dr. Liam Paull: Yeah. So we, now we have, now we have usually finished that. Like, now we have a kind of a, like a, a validation set that individuals get the outcomes they usually can see all the pieces. After which what they’re really evaluated on as like a held out check set that they don’t see. However what we’re fascinated with doing this 12 months, So usually what we’ve finished is we’ve had kind of like possibly two or three principal challenges, just like the lane following problem, the lane following with obstacles, problem, and the lane following with intersections problem or no matter.
And every one in all these challenges is, has its personal outlined metrics. Like how lengthy you survive for, or how far you’re touring in a sure period of time, kind of like commonplace stuff. What we’re going to do that [00:13:00] 12 months is we’re going to. Have a sequence of ranges successfully which can be simply more and more complicated and more and more tough.
And every one in all them possibly has like some, some stage by way of the metrics that you need to obtain to ensure that it to be handed. However what we’re attempting to do is definitely alleviate the overfitting to any particular type of like particular process and stage. You’re going to have an excessive amount of extra. B constructing a normal objective agent that’s in a position to do fairly effectively in a, like a very like various like environments of various complexity and growing complexity.
And so I, that is our, that is our subsequent try, really at type of attempting to alleviate this, like over-fitting to the specifics of the, of the the precise like problem or no matter.
tags:, , , , ,
Founding father of Fluid Dev, Hiring Platform for Robotics
Abate De Mey
Founding father of Fluid Dev, Hiring Platform for Robotics