RoboCup@Work League: Interview with Christoph Steup

RoboCup@Work League groups on the occasion in Brazil.

RoboCup is a global scientific initiative with the objective of advancing the cutting-edge of clever robots, AI and automation. The annual RoboCup occasion, the place groups collect from throughout the globe to participate in competitions throughout quite a few leagues, this yr befell in Salvador, Brazil from 15-21 July. In a sequence of interviews, we’ve been assembly a number of the RoboCup trustees, committee members, and individuals, to search out out extra about their respective leagues. Christoph Steup is an Govt Committee member and oversees the @Work League. Forward of the occasion in Brazil, we spoke to Christoph to search out out extra in regards to the @Work League, the duties that groups want to finish, and future plans for the League.

May you begin by giving us an introduction to the @Work league?

The @Work League, together with the Logistics League, varieties the Industrial League. Our objective is to imitate a number of the facets of commercial manufacturing techniques. An necessary facet of that is manufacturing unit automization and making an attempt to imitate the manufacturing unit of the long run, the place you might have autonomous robots constructing merchandise in accordance with buyer design. In these factories of the long run, a single piece could be produced individually for every buyer. Factories these days have large conveyor belts and a number of automization, with the duties principally achieved in the identical manner, and you may solely construct stuff effectively in the event you construct tens of millions of things. We’re engaged on constructing particular person items, the place automization remains to be doable, and even a single piece could be constructed successfully. However clearly, in our RoboCup competitions, we aren’t all for constructing on a manufacturing unit scale – we’re doing it on a really small scale. Which means our robots are sometimes 80 centimeters lengthy, the most important are round 70 centimeters large, and a few of them are additionally 80 centimeters excessive. So let’s say they slot in a one metre cubed field. Additionally, all our operations are achieved on the bottom. That is only for simplification as a result of constructing large tables to make it extra practical would additionally enhance the price for RoboCup and wouldn’t give a lot extra worth.

What our robots must do is transport objects from completely different workstations. So we have now a default configuration the place the sector begins, and there are workstations with objects mendacity on them, and a few of these objects should be transported to different workstations. The robotic wants to try this fully autonomously. So this is among the particular issues in regards to the @Work League, that it’s fully autonomous and there’s solely a single restart allowed per staff. So which means the robotic actually must be dependable. One of many large variations between medium groups and superb groups is that the superb groups carry out effectively on a regular basis whereas the medium groups have some good runs and a few unhealthy runs.

In addition to the article transportation that you simply talked about, and there different duties that the groups want to hold out?

There are some particular duties in our league, just like the precision placement activity the place the robotic wants to suit an object right into a cavity that’s basically the identical form and measurement as the article. It’s a bit bit like the sport that infants do to coach their dexterity.

We even have a activity that’s impressed by a conveyor belt, however we’re utilizing a desk that’s always turning. The robots want to know stuff whereas the desk is popping. This seems a bit bit foolish as a result of nobody would really put a rotating desk in a manufacturing unit, nonetheless that is our manner of really mimicking a conveyor belt. The conveyor belt itself could be actually, actually troublesome to combine into the competitors, so we simply abstracted that and use this rotating desk to truly have the identical problem however in a extra manageable manner. And it’s nonetheless a really, very laborious problem.

Then there are some particular challenges that we combine. For instance, that robots must report their state again in order that we will observe what the robotic is doing. We even have a problem the place people are within the loop. For instance, the robotic brings items to a sure workstation the place a human is current, the human assembles the items, after which the human wants to provide an indication to the robotic, after which the robotic will take the piece away and put it some other place. That is designed to actually mimic the automated manufacturing unit circulate.

Previously we additionally had a problem the place the robots wanted to open a drawer, take one thing out after which shut the drawer once more. We’ve additionally had duties the place the robotic has to deal with fragile objects, like sweets, the place the robotic actually wanted to watch out in manipulating them. So basically, what differentiates us most from the Logistics League is that we’re focusing loads on manipulation and all of the difficulties that include manipulation and unknown objects, whereas Logistics is extra tailor-made in the direction of large-scale logistics processes with all their optimization and planning.

I used to be fortunate sufficient to attend RoboCup final yr in Eindhoven and what the groups had been doing was actually spectacular. It was additionally fascinating to see how different the robots had been, and the way groups had been approaching the duties in distinct methods, with completely different grabbers and so forth.

Sure, this distinction in approaches is said to the historical past of our League, which is a bit bit just like the Logistics League. The Logistics League was initially a sponsored demonstration by Festo, which is a big firm from Germany that creates instruments, however additionally they have a didactics space the place they supply instruments to assist folks perceive manufacturing unit optimization. The @Work League was sponsored by Kuka, the robotics firm, and, to start with, they required each staff to compete with the Kuka youBot. So this was just about the default platform for our league, however sooner or later Kuka dropped from a sponsor to only an advisor to the league, and these days they aren’t a part of the league in any respect. So when the Kuka youBot was going out of fee, the groups looked for options and now we’re introduced with all kinds of robots which can be competing within the league, which I personally discover actually cool. Now we have now all these completely different robots, all these completely different approaches, and a few work higher in some eventualities and worse in others. So we actually have a scientific method to the issue and we’re actually getting some insights into how one can deal with this drawback on a number of ranges.

Have you ever seen that a number of the challenges particularly are harder basically for all of the groups?

In 2018 we launched a problem of so-called arbitrary surfaces that are surfaces unknown to the groups which can be placed on high of the workstations. The groups want to have the ability to take care of these surfaces. There are two surfaces which can be actually, actually terrible for the groups – one is grass that we just about stole from the soccer competitions! We simply thought it could be humorous to strive it, and it was a very fascinating drawback, particularly for a number of the grippers of the completely different groups. For instance, the present world champion, they’ve a inflexible gripper to allow them to have power suggestions after they grasp. Nevertheless, the grass is basically troublesome for them – due to their rigidity, they all the time grasp the grass itself after which they pull up the grass with the article. And this led to some fascinating issues, like they’re transporting the precise floor round and never solely the article. This isn’t an issue for groups utilizing a versatile gripper. Nevertheless, alternatively, the versatile gripper makes it actually troublesome to evaluate you probably have grasped the article as a result of you might have very unhealthy power suggestions. So there are two completely different approaches which have their execs and cons in numerous eventualities.

Three robots from the @Work competitors in Brazil.

Are you introducing any new duties for this yr?

Sure and no. So really we’re introducing a very new problem which is completely different from what we’ve achieved earlier than. The brand new problem is the so-called good farming problem, which is opening our league to a complete new discipline of functions, as a result of we are actually taking a look at agriculture. We’re engaged on this with Studica, a robotics firm from Canada, whose {hardware} we’re utilizing. We’ve already given it a strive on the German Open. This problem comes with some new specifics and one these is that the groups solely get the robotic shortly earlier than the competitors. In order that they don’t actually know the robotic largely upfront, and they should assemble, program and design the robotic in a really brief time. To compensate for this, we scale back the quantity of optimization and robustness that’s crucial. As a result of it’s an agriculture setting, we have now completely different objects, like fruits, that the groups must deal with. This makes it a bit bit extra difficult as a result of fruits have a extra arbitrary form and completely different ranges of ripeness that should be detected. We even have some grapes which can be hanging on a wall, which is a very completely different form of manipulation activity than earlier than, as a result of earlier than the groups simply wanted to know issues from surfaces, however now they actually need to pluck stuff from a wall in a dependable manner. So that is the brand new problem. It additionally comes with a number of software program challenges as a result of the computational energy of this robotic may be very restricted as a result of it solely has a Raspberry Pi. For instance, there’s not a number of picture processing doable, particularly in comparison with the present robots, a few of which even have GPUs embedded.

Is there a specific a part of the {hardware} or software program that you simply’ve seen a number of the largest developments in during the last yr or so?

Yeah, I believe one large change I noticed over time was a change from customized neural networks for object detection to off-the-shelf elements. So just about all groups these days use YOLO networks, which you may get pre-trained and so they simply deploy them on GPUs that they embedded into their robots. That is additionally one of many the reason why the robots actually grew in measurement over the previous couple of years as a result of they wanted house for the bigger computational energy. This really made it doable for lots of groups to reliably detect the objects. Object detection was an enormous drawback to start with of the league and these days it’s probably not an enormous difficulty – most groups are actually good at that. Generally they’re a bit bit startled with decoy objects – these are objects within the enviornment that aren’t actually a part of the duty, and they’re unknown to the groups beforehand. Generally they’re, let’s say, evil decoys that appear to be an object and there’s some mismatches that the groups do, however that is turning into very uncommon.

I believe the second large change is a change to bigger manipulators with extra levels of freedom. So to start with, everybody had a really small manipulator with solely 5 levels of freedom, which restricted the working vary, and these days just about all groups have a six diploma of freedom manipulator with a wide range. Which means that they don’t want to maneuver their robotic when they’re in entrance of a workstation, which makes them a lot quicker and likewise rather more exact.

May you discuss in regards to the future plans for the League?

There are some things we’re interested by.

As regards to the competitors itself, we had a dialogue with the groups about what they’re all for doing sooner or later. Two issues got here up that they actually wish to have. One is cellular obstacles, so they need different objects to maneuver autonomously by way of the sector. We’re within the course of of making that, in cooperation with EduArt, which is an organization from Germany that additionally offers small instructional robots. And the second factor we wish to introduce is a form of humanoid robotic that the groups can use to truly deal with particular manipulation duties that can’t be achieved merely with a robotic manipulator.

By way of creating an entry-level League, we have now been engaged on this and one potential thought is to make use of the smart-farming problem because the entry level. By way of the collaboration with Studica, we will present groups with the robotic and so they get to maintain it after the competitors. On the German Open I spoke to the Quickly-Manufactured Rescue League about this crossover between the Rescue and the Junior Leagues, and they’re very eager to collaborate.

We’re additionally speaking with the Logistics League. Their sponsor, Festo, has dropped out of their league and now they should reorganize. We’re questioning if it could be worthwhile to carry our leagues nearer collectively, and even fuse them collectively to a single RoboCup Industrial league. The Logistics League needs to do extra manipulation, and the @Work League needs to do extra planning, so we’re closing the hole naturally between the 2. Nevertheless, that is only a thought in the mean time – we have to see how the groups react to that.

About Christoph

Christoph Steup is an lively researcher specializing in numerous fields of robotics, together with swarm robotics, precision farming, and weather-resilient autonomous driving. He at present works on the Fraunhofer Institute for Transportation and Infrastructure Programs (IVI), the place he leads the Swarm Know-how Group. Previous to this function, he headed the Computational Intelligence in Robotics group on the Otto von Guericke College Magdeburg. Christoph’s involvement with RoboCup started in 2015 when he joined the robOTTO staff of Otto von Guericke College as staff chief. His contributions to the RoboCup group expanded as he grew to become a member of the Technical Committee for the @Work League in 2017. In 2019, he additional superior his participation by becoming a member of the Govt Committee of the league.