Tag Archives: blocks

#437769 Q&A: Facebook’s CTO Is at War With ...

Photo: Patricia de Melo Moreira/AFP/Getty Images

Facebook chief technology officer Mike Schroepfer leads the company’s AI and integrity efforts.

Facebook’s challenge is huge. Billions of pieces of content—short and long posts, images, and combinations of the two—are uploaded to the site daily from around the world. And any tiny piece of that—any phrase, image, or video—could contain so-called bad content.

In its early days, Facebook relied on simple computer filters to identify potentially problematic posts by their words, such as those containing profanity. These automatically filtered posts, as well as posts flagged by users as offensive, went to humans for adjudication.

In 2015, Facebook started using artificial intelligence to cull images that contained nudity, illegal goods, and other prohibited content; those images identified as possibly problematic were sent to humans for further review.

By 2016, more offensive photos were reported by Facebook’s AI systems than by Facebook users (and that is still the case).

In 2018, Facebook CEO Mark Zuckerberg made a bold proclamation: He predicted that within five or ten years, Facebook’s AI would not only look for profanity, nudity, and other obvious violations of Facebook’s policies. The tools would also be able to spot bullying, hate speech, and other misuse of the platform, and put an immediate end to them.

Today, automated systems using algorithms developed with AI scan every piece of content between the time when a user completes a post and when it is visible to others on the site—just fractions of a second. In most cases, a violation of Facebook’s standards is clear, and the AI system automatically blocks the post. In other cases, the post goes to human reviewers for a final decision, a workforce that includes 15,000 content reviewers and another 20,000 employees focused on safety and security, operating out of more than 20 facilities around the world.

In the first quarter of this year, Facebook removed or took other action (like appending a warning label) on more than 9.6 million posts involving hate speech, 8.6 million involving child nudity or exploitation, almost 8 million posts involving the sale of drugs, 2.3 million posts involving bullying and harassment, and tens of millions of posts violating other Facebook rules.

Right now, Facebook has more than 1,000 engineers working on further developing and implementing what the company calls “integrity” tools. Using these systems to screen every post that goes up on Facebook, and doing so in milliseconds, is sucking up computing resources. Facebook chief technology officer Mike Schroepfer, who is heading up Facebook’s AI and integrity efforts, spoke with IEEE Spectrum about the team’s progress on building an AI system that detects bad content.

Since that discussion, Facebook’s policies around hate speech have come under increasing scrutiny, with particular attention on divisive posts by political figures. A group of major advertisers in June announced that they would stop advertising on the platform while reviewing the situation, and civil rights groups are putting pressure on others to follow suit until Facebook makes policy changes related to hate speech and groups that promote hate, misinformation, and conspiracies.

Facebook CEO Mark Zuckerberg responded with news that Facebook will widen the category of what it considers hateful content in ads. Now the company prohibits claims that people from a specific race, ethnicity, national origin, religious affiliation, caste, sexual orientation, gender identity, or immigration status are a threat to the physical safety, health, or survival of others. The policy change also aims to better protect immigrants, migrants, refugees, and asylum seekers from ads suggesting these groups are inferior or expressing contempt. Finally, Zuckerberg announced that the company will label some problematic posts by politicians and government officials as content that violates Facebook’s policies.

However, civil rights groups say that’s not enough. And an independent audit released in July also said that Facebook needs to go much further in addressing civil rights concerns and disinformation.

Schroepfer indicated that Facebook’s AI systems are designed to quickly adapt to changes in policy. “I don’t expect considerable technical changes are needed to adjust,” he told Spectrum.

This interview has been edited and condensed for clarity.

IEEE Spectrum: What are the stakes of content moderation? Is this an existential threat to Facebook? And is it critical that you deal well with the issue of election interference this year?

Schroepfer: It’s probably existential; it’s certainly massive. We are devoting a tremendous amount of our attention to it.

The idea that anyone could meddle in an election is deeply disturbing and offensive to all of us here, just as people and citizens of democracies. We don’t want to see that happen anywhere, and certainly not on our watch. So whether it’s important to the company or not, it’s important to us as people. And I feel a similar way on the content-moderation side.

There are not a lot of easy choices here. The only way to prevent people, with certainty, from posting bad things is to not let them post anything. We can take away all voice and just say, “Sorry, the Internet’s too dangerous. No one can use it.” That will certainly get rid of all hate speech online. But I don’t want to end up in that world. And there are variants of that world that various governments are trying to implement, where they get to decide what’s true or not, and you as a person don’t. I don’t want to get there either.

My hope is that we can build a set of tools that make it practical for us to do a good enough job, so that everyone is still excited about the idea that anyone can share what they want, and so that Facebook is a safe and reasonable place for people to operate in.

Spectrum: You joined Facebook in 2008, before AI was part of the company’s toolbox. When did that change? When did you begin to think that AI tools would be useful to Facebook?

Schroepfer: Ten years ago, AI wasn’t commercially practical; the technology just didn’t work very well. In 2012, there was one of those moments that a lot of people point to as the beginning of the current revolution in deep learning and AI. A computer-vision model—a neural network—was trained using what we call supervised training, and it turned out to be better than all the existing models.

Spectrum: How is that training done, and how did computer-vision models come to Facebook?

Image: Facebook

Just Broccoli? Facebook’s image analysis algorithms can tell the difference between marijuana [left] and tempura broccoli [right] better than some humans.

Schroepfer: Say I take a bunch of photos and I have people look at them. If they see a photo of a cat, they put a text label that says cat; if it’s one of a dog, the text label says dog. If you build a big enough data set and feed that to the neural net, it learns how to tell the difference between cats and dogs.

Prior to 2012, it didn’t work very well. And then in 2012, there was this moment where it seemed like, “Oh wow, this technique might work.” And a few years later we were deploying that form of technology to help us detect problematic imagery.

Spectrum: Do your AI systems work equally well on all types of prohibited content?

Schroepfer: Nudity was technically easiest. I don’t need to understand language or culture to understand that this is either a naked human or not. Violence is a much more nuanced problem, so it was harder technically to get it right. And with hate speech, not only do you have to understand the language, it may be very contextual, even tied to recent events. A week before the Christchurch shooting [New Zealand, 2019], saying “I wish you were in the mosque” probably doesn’t mean anything. A week after, that might be a terrible thing to say.

Spectrum: How much progress have you made on hate speech?

Schroepfer: AI, in the first quarter of 2020, proactively detected 88.8 percent of the hate-speech content we removed, up from 80.2 percent in the previous quarter. In the first quarter of 2020, we took action on 9.6 million pieces of content for violating our hate-speech policies.

Image: Facebook

Off Label: Sometimes image analysis isn’t enough to determine whether a picture posted violates the company’s policies. In considering these candy-colored vials of marijuana, for example, the algorithms can look at any accompanying text and, if necessary, comments on the post.

Spectrum: It sounds like you’ve expanded beyond tools that analyze images and are also using AI tools that analyze text.

Schroepfer: AI started off as very siloed. People worked on language, people worked on computer vision, people worked on video. We’ve put these things together—in production, not just as research—into multimodal classifiers.

[Schroepfer shows a photo of a pan of Rice Krispies treats, with text referring to it as a “potent batch”] This is a case in which you have an image, and then you have the text on the post. This looks like Rice Krispies. On its own, this image is fine. You put the text together with it in a bigger model; that can then understand what’s going on. That didn’t work five years ago.

Spectrum: Today, every post that goes up on Facebook is immediately checked by automated systems. Can you explain that process?

Image: Facebook

Bigger Picture: Identifying hate speech is often a matter of context. Either the text or the photo in this post isn’t hateful standing alone, but putting them together tells a different story.

Schroepfer: You upload an image and you write some text underneath it, and the systems look at both the image and the text to try to see which, if any, policies it violates. Those decisions are based on our Community Standards. It will also look at other signals on the posts, like the comments people make.

It happens relatively instantly, though there may be times things happen after the fact. Maybe you uploaded a post that had misinformation in it, and at the time you uploaded it, we didn’t know it was misinformation. The next day we fact-check something and scan again; we may find your post and take it down. As we learn new things, we’re going to go back through and look for violations of what we now know to be a problem. Or, as people comment on your post, we might update our understanding of it. If people are saying, “That’s terrible,” or “That’s mean,” or “That looks fake,” those comments may be an interesting signal.

Spectrum: How is Facebook applying its AI tools to the problem of election interference?

Schroepfer: I would split election interference into two categories. There are times when you’re going after the content, and there are times you’re going after the behavior or the authenticity of the person.

On content, if you’re sharing misinformation, saying, “It’s super Wednesday, not super Tuesday, come vote on Wednesday,” that’s a problem whether you’re an American sitting in California or a foreign actor.

Other times, people create a series of Facebook pages pretending they’re Americans, but they’re really a foreign entity. That is a problem on its own, even if all the content they’re sharing completely meets our Community Standards. The problem there is that you have a foreign government running an information operation.

There, you need different tools. What you’re trying to do is put pieces together, to say, “Wait a second. All of these pages—Martians for Justice, Moonlings for Justice, and Venusians for Justice”—are all run by an administrator with an IP address that’s outside the United States. So they’re all connected, even though they’re pretending to not be connected. That’s a very different problem than me sitting in my office in Menlo Park [Calif.] sharing misinformation.

I’m not going to go into lots of technical detail, because this is an area of adversarial nature. The fundamental problem you’re trying to solve is that there’s one entity coordinating the activity of a bunch of things that look like they’re not all one thing. So this is a series of Instagram accounts, or a series of Facebook pages, or a series of WhatsApp accounts, and they’re pretending to be totally different things. We’re looking for signals that these things are related in some way. And we’re looking through the graph [what Facebook calls its map of relationships between users] to understand the properties of this network.

Spectrum: What cutting-edge AI tools and methods have you been working on lately?

Schroepfer: Supervised learning, with humans setting up the instruction process for the AI systems, is amazingly effective. But it has a very obvious flaw: the speed at which you can develop these things is limited by how fast you can curate the data sets. If you’re dealing in a problem domain where things change rapidly, you have to rebuild a new data set and retrain the whole thing.

Self-supervision is inspired by the way people learn, by the way kids explore the world around them. To get computers to do it themselves, we take a bunch of raw data and build a way for the computer to construct its own tests. For language, you scan a bunch of Web pages, and the computer builds a test where it takes a sentence, eliminates one of the words, and figures out how to predict what word belongs there. And because it created the test, it actually knows the answer. I can use as much raw text as I can find and store because it’s processing everything itself and doesn’t require us to sit down and build the information set. In the last two years there has been a revolution in language understanding as a result of AI self-supervised learning.

Spectrum: What else are you excited about?

Schroepfer: What we’ve been working on over the last few years is multilingual understanding. Usually, when I’m trying to figure out, say, whether something is hate speech or not I have to go through the whole process of training the model in every language. I have to do that one time for every language. When you make a post, the first thing we have to figure out is what language your post is in. “Ah, that’s Spanish. So send it to the Spanish hate-speech model.”

We’ve started to build a multilingual model—one box where you can feed in text in 40 different languages and it determines whether it’s hate speech or not. This is way more effective and easier to deploy.

To geek out for a second, just the idea that you can build a model that understands a concept in multiple languages at once is crazy cool. And it not only works for hate speech, it works for a variety of things.

When we started working on this multilingual model years ago, it performed worse than every single individual model. Now, it not only works as well as the English model, but when you get to the languages where you don’t have enough data, it’s so much better. This rapid progress is very exciting.

Spectrum: How do you move new AI tools from your research labs into operational use?

Schroepfer: Engineers trying to make the next breakthrough will often say, “Cool, I’ve got a new thing and it achieved state-of-the-art results on machine translation.” And we say, “Great. How long does it take to run in production?” They say, “Well, it takes 10 seconds for every sentence to run on a CPU.” And we say, “It’ll eat our whole data center if we deploy that.” So we take that state-of-the-art model and we make it 10 or a hundred or a thousand times more efficient, maybe at the cost of a little bit of accuracy. So it’s not as good as the state-of-the-art version, but it’s something we can actually put into our data centers and run in production.

Spectrum: What’s the role of the humans in the loop? Is it true that Facebook currently employs 35,000 moderators?

Schroepfer: Yes. Right now our goal is not to reduce that. Our goal is to do a better job catching bad content. People often think that the end state will be a fully automated system. I don’t see that world coming anytime soon.

As automated systems get more sophisticated, they take more and more of the grunt work away, freeing up the humans to work on the really gnarly stuff where you have to spend an hour researching.

We also use AI to give our human moderators power tools. Say I spot this new meme that is telling everyone to vote on Wednesday rather than Tuesday. I have a tool in front of me that says, “Find variants of that throughout the system. Find every photo with the same text, find every video that mentions this thing and kill it in one shot.” Rather than, I found this one picture, but then a bunch of other people upload that misinformation in different forms.

Another important aspect of AI is that anything I can do to prevent a person from having to look at terrible things is time well spent. Whether it’s a person employed by us as a moderator or a user of our services, looking at these things is a terrible experience. If I can build systems that take the worst of the worst, the really graphic violence, and deal with that in an automated fashion, that’s worth a lot to me. Continue reading

Posted in Human Robots

#437693 Video Friday: Drone Helps Explore ...

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!):

ICRES 2020 – September 28-29, 2020 – Taipei, Taiwan
AUVSI EXPONENTIAL 2020 – October 5-8, 2020 – [Online Conference]
IROS 2020 – October 25-29, 2020 – Las Vegas, Nev., USA
CYBATHLON 2020 – November 13-14, 2020 – [Online Event]
ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA
Let us know if you have suggestions for next week, and enjoy today's videos.

Clearpath Robotics and Boston Dynamics were obviously destined to partner up with Spot, because Spot 100 percent stole its color scheme from Clearpath, which has a monopoly on yellow and black robots. But seriously, the news here is that thanks to Clearpath, Spot now works seamlessly with ROS.

[ Clearpath Robotics ]

A new video created by Swisscom Ventures highlights a research expedition sponsored by Moncler to explore the deepest ice caves in the world using Flyability’s Elios drone. […] The expedition was sponsored by apparel company Moncler and took place over two weeks in 2018 on the Greenland ice sheet, the second largest body of ice in the world after Antarctica. Research focused on an area about 80 kilometers east of Kangerlussuaq, where scientists wanted to study the movement of water deep underground to better understand the effects of climate change on the melting ice.

[ Flyability ]

Shane Wighton of the “Stuff Made Here” YouTube channel, whose terrifying haircut machine we featured a few months ago, has improved on his robotic basketball hoop. It’s actually more than an improvement: It’s a complete redesign that nearly drove Wighton insane. But the result is pretty cool. It’s fun to watch him building a highly complicated system while always seeking simple and elegant designs for its components.

[ Stuff Made Here ]

SpaceX rockets are really just giant, explosion-powered drones that go into space sometimes. So let's watch more videos of them! This one is sped up, and puts a flight into just a couple of minutes.

[ SpaceX ]

Neato Robotics makes some solid autonomous vacuums, and these incremental upgrades feature improved battery life and better air filters.

[ Neato Robotics ]

A full-scale engineering model of NASA's Perseverance Mars rover now resides in a garage facing the Mars Yard at NASA's Jet Propulsion Laboratory in Southern California.

This vehicle system test bed rover (VSTB) is also known as OPTIMISM, which stands for Operational Perseverance Twin for Integration of Mechanisms and Instruments Sent to Mars. OPTIMISM was built in a warehouselike assembly room near the Mars Yard – an area that simulates the Red Planet's rocky surface. The rover helps the mission test hardware and software before it’s transmitted to the real rover on Mars. OPTIMISM will share the space with the Curiosity rover's twin MAGGIE.

[ JPL ]

Heavy asset industries like shipping, oil and gas, and manufacturing are grounded in repetitive tasks like locating items on large industrial sites — a tedious task that can take as long 45 minutes to find critical items like a forklift in an area that spans the size of multiple football fields. Not only is this work boring, it’s dangerous and inefficient. Robots like Spot, however, love this sort of work.

Spot can provide real-time updates on the location of assets and complete other mundane tasks. In this case, Spot is using software from Cognite to roam the vast shipyard to locate and manage more than 100,000 assets stored across the facility. What used to take humans hours can be managed on an ongoing basis by Spot — leaving employees to focus on more strategic tasks.

[ Cognite ]

The KNEXT Barista system helps high volume premium coffee providers who want to offer artisan coffee specialities in consistent quality.

[ Kuka ]

In this paper, we study this idea of generality in the locomotion domain. We develop a learning framework that can learn sophisticated locomotion behavior for a wide spectrum of legged robots, such as bipeds, tripeds, quadrupeds and hexapods, including wheeled variants. Our learning framework relies on a data-efficient, off-policy multi-task RL algorithm and a small set of reward functions that are semantically identical across robots.

[ DeepMind ]

Thanks Dave!

Even though it seems like the real risk of COVID is catching it from another person, robotics companies are doing what they can with UVC disinfecting systems.

[ BlueBotics ]

Aeditive develop robotic 3D printing solutions for the production of concrete components. At the heart of their production plant are two large robots that cooperate to manufacture the component. The automation technology they build on is a robotic shotcrete process. During this process, they apply concrete layer by layer and thus manufacture complete components. This means that their customers no longer dependent on formwork, which is expensive and time-consuming to create. Instead, their customers can manufacture components directly on a steel pallet without these moulds.

[ Aeditive ]

Something BIG is coming next month from Robotiq!

My guess: an elephant.

[ Robotiq ]

TurtleBot3 is a great little home robot, as long as you have a TurtleBot3-sized home.

[ Robotis ]

How do you calculate the coordinated movements of two robot arms so they can accurately guide a highly flexible tool? ETH researchers have integrated all aspects of the optimisation calculations into an algorithm. The hot-​wire cutter will be used, among other things, to develop building blocks for a mortar-​free structure.

[ ETH Zurich ]

And now, this.

[ RobotStart ] Continue reading

Posted in Human Robots

#437592 Coordinated Robotics Wins DARPA SubT ...

DARPA held the Virtual Cave Circuit event of the Subterranean Challenge on Tuesday in the form of a several hour-long livestream. We got to watch (along with all of the competing teams) as virtual robots explored virtual caves fully autonomously, dodging rockfalls, spotting artifacts, scoring points, and sometimes running into stuff and falling over.

Expert commentary was provided by DARPA, and we were able to watch multiple teams running at once, skipping from highlight to highlight. It was really very well done (you can watch an archive of the entire stream here), but they made us wait until the very end to learn who won: First place went to Coordinated Robotics, with BARCS taking second, and third place going to newcomer Team Dynamo.

Huge congratulations to Coordinated Robotics! It’s worth pointing out that the top three teams were separated by an incredibly small handful of points, and on a slightly different day, with slightly different artifact positions, any of them could have come out on top. This doesn’t diminish Coordinated Robotics’ victory in the least—it means that the competition was fierce, and that the problem of autonomous cave exploration with robots has been solved (virtually, at least) in several different but effective ways.

We know Coordinated Robotics pretty well at this point, but here’s an introduction video:

You heard that right—Coordinated Robotics is just Kevin Knoedler, all by himself. This would be astonishing, if we weren’t already familiar with Kevin’s abilities: He won NASA’s virtual Space Robotics Challenge by himself in 2017, and Coordinated Robotics placed first in the DARPA SubT Virtual Tunnel Circuit and second in the Virtual Urban Circuit. We asked Kevin how he managed to do so spectacularly well (again), and here’s what he told us:

IEEE Spectrum: Can you describe what it was like to watch your team of robots on the live stream, and to see them score the most points?

Kevin Knoedler: It was exciting and stressful watching the live stream. It was exciting as the top few scores were quite close for the cave circuit. It was stressful because I started out behind and worked my way up, but did not do well on the final world. Luckily, not doing well on the first and last worlds was offset by better scores on many of the runs in between. DARPA did a very nice job with their live stream of the cave circuit results.

How did you decide on the makeup of your team, and on what sensors to use?

To decide on the makeup of the team I experimented with quite a few different vehicles. I had a lot of trouble with the X2 and other small ground vehicles flipping over. Based on that I looked at the larger ground vehicles that also had a sensor capable of identifying drop-offs. The vehicles that met those criteria for me were the Marble HD2, Marble Husky, Ozbot ATR, and the Absolem. Of those ground vehicles I went with the Marble HD2. It had a downward looking depth camera that I could use to detect drop-offs and was much more stable on the varied terrain than the X2. I had used the X3 aerial vehicle before and so that was my first choice for an aerial platform.

What were some things that you learned in Tunnel and Urban that you were able to incorporate into your strategy for Cave?

In the Tunnel circuit I had learned a strategy to use ground vehicles and in the Urban circuit I had learned a strategy to use aerial vehicles. At a high level that was the biggest thing I learned from the previous circuits that I was able to apply to the Cave circuit. At a lower level I was able to apply many of the development and testing strategies from the previous circuits to the Cave circuit.

What aspect of the cave environment was most challenging for your robots?

I would say it wasn't just one aspect of the cave environment that was challenging for the robots. There were quite a few challenging aspects of the cave environment. For the ground vehicles there were frequently paths that looked good as the robot started on the path, but turned into drop-offs or difficult boulder crawls. While it was fun to see the robot plan well enough to slowly execute paths over the boulders, I was wishing that the robot was smart enough to try a different path rather than wasting so much time crawling over the large boulders. For the aerial vehicles the combination of tight paths along with large vertical spaces was the biggest challenge in the environment. The large open vertical areas were particularly challenging for my aerial robots. They could easily lose track of their position without enough nearby features to track and it was challenging to find the correct path in and out of such large vertical areas.

How will you be preparing for the SubT Final?

To prepare for the SubT Final the vehicles will be getting a lot smarter. The ground vehicles will be better at navigation and communicating with one another. The aerial vehicles will be better able to handle large vertical areas both from a positioning and a planning point of view. Finally, all of the vehicles will do a better job coordinating what areas have been explored and what areas have good leads for further exploration.

Image: DARPA

The final score for the DARPA SubT Cave Circuit virtual competition.

We also had a chance to ask SubT program manager Tim Chung a few questions at yesterday’s post-event press conference, about the course itself and what he thinks teams should have learned from the competition:

IEEE Spectrum: Having looked through some real caves, can you give some examples of some of the most significant differences between this simulation and real caves? And with the enormous variety of caves out there, how generalizable are the solutions that teams came up with?

Tim Chung: Many of the caves that I’ve had to crawl through and gotten bumps and scrapes from had a couple of different features that I’ll highlight. The first is the variations in moisture— a lot of these caves were naturally formed with streams and such, so many of the caves we went to had significant mud, flowing water, and such. And so one of the things we're not capturing in the SubT simulator is explicitly anything that would submerge the robots, or otherwise short any of their systems. So from that perspective, that's one difference that's certainly notable.

And then the other difference I think is the granularity of the terrain, whether it's rubble, sand, or just raw dirt, friction coefficients are all across the board, and I think that's one of the things that any terrestrial simulator will both struggle with and potentially benefit from— that is, terramechanics simulation abilities. Given the emphasis on mobility in the SubT simulation, we’re capturing just a sliver of the complexity of terramechanics, but I think that's probably another take away that you'll certainly see— where there’s that distinction between physical and virtual technologies.

To answer your second question about generalizability— that’s the multi-million dollar question! It’s definitely at the crux of why we have eight diverse worlds, both in size verticality, dimensions, constraint passageways, etc. But this is eight out of countless variations, and the goal of course is to be able to investigate what those key dependencies are. What I'll say is that the out of the seventy three different virtual cave tiles, which are the building blocks that make up these virtual worlds, quite a number of them were not only inspired by real world caves, but were specifically designed so that we can essentially use these tiles as unit tests going forward. So, if I want to simulate vertical inclines, here are the tiles that are the vertical vertical unit tests for robots, and that’s how we’re trying to to think through how to tease out that generalizability factor.

What are some observations from this event that you think systems track teams should pay attention to as they prepare for the final event?

One of the key things about the virtual competition is that you submit your software, and that's it. So you have to design everything from state management to failure mode triage, really thinking about what could go wrong and then building out your autonomous capabilities either to react to some of those conditions, or to anticipate them. And to be honest I think that the humans in the loop that we have in the systems competition really are key enablers of their capability, but also could someday (if not already) be a crutch that we might not be able to develop.

Thinking through some of the failure modes in a fully autonomous software deployed setting are going to be incredibly valuable for the systems competitors, so that for example the human supervisor doesn't have to worry about those failure modes as much, or can respond in a more supervisory way rather than trying to joystick the robot around. I think that's going to be one of the greatest impacts, thinking through what it means to send these robots off to autonomously get you the information you need and complete the mission

This isn’t to say that the humans aren't going to be useful and continue to play a role of course, but I think this shifting of the role of the human supervisor from being a state manager to being more of a tactical commander will dramatically highlight the impact of the virtual side on the systems side.

What, if anything, should we take away from one person teams being able to do so consistently well in the virtual circuit?

It’s a really interesting question. I think part of it has to do with systems integration versus software integration. There's something to be said for the richness of the technologies that can be developed, and how many people it requires to be able to develop some of those technologies. With the systems competitors, having one person try to build, manage, deploy, service, and operate all of those robots is still functionally quite challenging, whereas in the virtual competition, it really is a software deployment more than anything else. And so I think the commonality of single person teams may just be a virtue of the virtual competition not having some of those person-intensive requirements.

In terms of their strong performance, I give credit to all of these really talented folks who are taking upon themselves to jump into the competitor pool and see how well they do, and I think that just goes to show you that whether you're one person or ten people people or a hundred people on a team, a good idea translated and executed well really goes a long way.

Looking ahead, teams have a year to prepare for the final event, which is still scheduled to be held sometime in fall 2021. And even though there was no cave event for systems track teams, the fact that the final event will be a combination of tunnel, urban, and cave circuits means that systems track teams have been figuring out how to get their robots to work in caves anyway, and we’ll be bringing you some of their stories over the next few weeks.

[ DARPA SubT ] Continue reading

Posted in Human Robots

#437583 Video Friday: Attack of the Hexapod ...

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):

IROS 2020 – October 25-25, 2020 – [Online]
ROS World 2020 – November 12, 2020 – [Online]
CYBATHLON 2020 – November 13-14, 2020 – [Online]
ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA
Let us know if you have suggestions for next week, and enjoy today’s videos.

Happy Halloween from HEBI Robotics!

Thanks Hardik!

[ HEBI Robotics ]

Happy Halloween from Berkshire Grey!

[ Berkshire Grey ]

These are some preliminary results of our lab’s new work on using reinforcement learning to train neural networks to imitate common bipedal gait behaviors, without using any motion capture data or reference trajectories. Our method is described in an upcoming submission to ICRA 2021. Work by Jonah Siekmann and Yesh Godse.

[ OSU DRL ]

The northern goshawk is a fast, powerful raptor that flies effortlessly through forests. This bird was the design inspiration for the next-generation drone developed by scientifics of the Laboratory of Intelligent Systems of EPFL led by Dario Floreano. They carefully studied the shape of the bird’s wings and tail and its flight behavior, and used that information to develop a drone with similar characteristics.

The engineers already designed a bird-inspired drone with morphing wing back in 2016. In a step forward, their new model can adjust the shape of its wing and tail thanks to its artificial feathers. Flying this new type of drone isn’t easy, due to the large number of wing and tail configurations possible. To take full advantage of the drone’s flight capabilities, Floreano’s team plans to incorporate artificial intelligence into the drone’s flight system so that it can fly semi-automatically. The team’s research has been published in Science Robotics.

[ EPFL ]

Oopsie.

[ Roborace ]

We’ve covered MIT’s Roboats in the past, but now they’re big enough to keep a couple of people afloat.

Self-driving boats have been able to transport small items for years, but adding human passengers has felt somewhat intangible due to the current size of the vessels. Roboat II is the “half-scale” boat in the growing body of work, and joins the previously developed quarter-scale Roboat, which is 1 meter long. The third installment, which is under construction in Amsterdam and is considered to be “full scale,” is 4 meters long and aims to carry anywhere from four to six passengers.

[ MIT ]

With a training technique commonly used to teach dogs to sit and stay, Johns Hopkins University computer scientists showed a robot how to teach itself several new tricks, including stacking blocks. With the method, the robot, named Spot, was able to learn in days what typically takes a month.

[ JHU ]

Exyn, a pioneer in autonomous aerial robot systems for complex, GPS-denied industrial environments, today announced the first dog, Kody, to successfully fly a drone at Number 9 Coal Mine, in Lansford, PA. Selected to carry out this mission was the new autonomous aerial robot, the ExynAero.

Yes, this is obviously a publicity stunt, and Kody is only flying the drone in the sense that he’s pushing the launch button and then taking a nap. But that’s also the point— drone autonomy doesn’t get much fuller than this, despite the challenge of the environment.

[ Exyn ]

In this video object instance segmentation and shape completion are combined with classical regrasp planning to perform pick-place of novel objects. It is demonstrated with a UR5, Robotiq 85 parallel-jaw gripper, and Structure depth sensor with three rearrangement tasks: bin packing (minimize the height of the packing), placing bottles onto coasters, and arrange blocks from tallest to shortest (according to the longest edge). The system also accounts for uncertainty in the segmentation/completion by avoiding grasping or placing on parts of the object where perceptual uncertainty is predicted to be high.

[ Paper ] via [ Northeastern ]

Thanks Marcus!

U can’t touch this!

[ University of Tokyo ]

We introduce a way to enable more natural interaction between humans and robots through Mixed Reality, by using a shared coordinate system. Azure Spatial Anchors, which already supports colocalizing multiple HoloLens and smartphone devices in the same space, has now been extended to support robots equipped with cameras. This allows humans and robots sharing the same space to interact naturally: humans can see the plan and intention of the robot, while the robot can interpret commands given from the person’s perspective. We hope that this can be a building block in the future of humans and robots being collaborators and coworkers.

[ Microsoft ]

Some very high jumps from the skinniest quadruped ever.

[ ODRI ]

In this video we present recent efforts to make our humanoid robot LOLA ready for multi-contact locomotion, i.e. additional hand-environment support for extra stabilization during walking.

[ TUM ]

Classic bike moves from Dr. Guero.

[ Dr. Guero ]

For a robotics company, iRobot is OLD.

[ iRobot ]

The Canadian Space Agency presents Juno, a preliminary version of a rover that could one day be sent to the Moon or Mars. Juno can navigate autonomously or be operated remotely. The Lunar Exploration Analogue Deployment (LEAD) consisted in replicating scenarios of a lunar sample return mission.

[ CSA ]

How exactly does the Waymo Driver handle a cat cutting across its driving path? Jonathan N., a Product Manager on our Perception team, breaks it all down for us.

Now do kangaroos.

[ Waymo ]

Jibo is hard at work at MIT playing games with kids.

Children’s creativity plummets as they enter elementary school. Social interactions with peers and playful environments have been shown to foster creativity in children. Digital pedagogical tools often lack the creativity benefits of co-located social interaction with peers. In this work, we leverage a social embodied robot as a playful peer and designed Escape!Bot, a game involving child-robot co-play, where the robot is a social agent that scaffolds for creativity during gameplay.

[ Paper ]

It’s nice when convenience stores are convenient even for the folks who have to do the restocking.

Who’s moving the crates around, though?

[ Telexistence ]

Hi, fans ! Join the ROS World 2020, opening November 12th , and see the footage of ROBOTIS’ ROS platform robots 🙂

[ ROS World 2020 ]

ML/RL methods are often viewed as a magical black box, and while that’s not true, learned policies are nonetheless a valuable tool that can work in conjunction with the underlying physics of the robot. In this video, Agility CTO Jonathan Hurst – wearing his professor hat at Oregon State University – presents some recent student work on using learned policies as a control method for highly dynamic legged robots.

[ Agility Robotics ]

Here’s an ICRA Legged Robots workshop talk from Marco Hutter at ETH Zürich, on Autonomy for ANYmal.

Recent advances in legged robots and their locomotion skills has led to systems that are skilled and mature enough for real-world deployment. In particular, quadrupedal robots have reached a level of mobility to navigate complex environments, which enables them to take over inspection or surveillance jobs in place like offshore industrial plants, in underground areas, or on construction sites. In this talk, I will present our research work with the quadruped ANYmal and explain some of the underlying technologies for locomotion control, environment perception, and mission autonomy. I will show how these robots can learn and plan complex maneuvers, how they can navigate through unknown environments, and how they are able to conduct surveillance, inspection, or exploration scenarios.

[ RSL ] Continue reading

Posted in Human Robots

#437267 This Week’s Awesome Tech Stories From ...

ARTIFICIAL INTELLIGENCE
OpenAI’s New Language Generator GPT-3 Is Shockingly Good—and Completely Mindless
Will Douglas Heaven | MIT Technology Review
“‘Playing with GPT-3 feels like seeing the future,’ Arram Sabeti, a San Francisco–based developer and artist, tweeted last week. That pretty much sums up the response on social media in the last few days to OpenAI’s latest language-generating AI.”

ROBOTICS
The Star of This $70 Million Sci-Fi Film Is a Robot
Sarah Bahr | The New York Times
“Erica was created by Hiroshi Ishiguro, a roboticist at Osaka University in Japan, to be ‘the most beautiful woman in the world’—he modeled her after images of Miss Universe pageant finalists—and the most humanlike robot in existence. But she’s more than just a pretty face: Though ‘b’ is still in preproduction, when she makes her debut, producers believe it will be the first time a film has relied on a fully autonomous artificially intelligent actor.”

VIRTUAL REALITY
My Glitchy, Glorious Day at a Conference for Virtual Beings
Emma Grey Ellis | Wired
“Spectators spent much of the time debating who was real and who was fake. …[Lars Buttler’s] eyes seemed awake and alive in a way that the faces of the other participants in the Zoom call—venture capitalist, a tech founder, and an activist, all of them puppeted by artificial intelligence—were not. ‘Pretty sure Lars is human,’ a (real-person) spectator typed in the in-meeting chat room. ‘I’m starting to think Lars is AI,’ wrote another.”

FUTURE OF FOOD
KFC Is Working With a Russian 3D Bioprinting Firm to Try to Make Lab-Produced Chicken Nuggets
Kim Lyons | The Verge
“The chicken restaurant chain will work with Russian company 3D Bioprinting Solutions to develop bioprinting technology that will ‘print’ chicken meat, using chicken cells and plant material. KFC plans to provide the bioprinting firm with ingredients like breading and spices ‘to achieve the signature KFC taste’ and will seek to replicate the taste and texture of genuine chicken.”

BIOTECH
A CRISPR Cow Is Born. It’s Definitely a Boy
Megan Molteni | Wired
“After nearly five years of research, at least half a million dollars, dozens of failed pregnancies, and countless scientific setbacks, Van Eenennaam’s pioneering attempt to create a line of Crispr’d cattle tailored to the needs of the beef industry all came down to this one calf. Who, as luck seemed sure to have it, was about to enter the world in the middle of a global pandemic.”

GOVERNANCE
Is the Pandemic Finally the Moment for a Universal Basic Income?
Brooks Rainwater and Clay Dillow | Fast Company
“Since February, governments around the globe—including in the US—have intervened in their citizens’ individual financial lives, distributing direct cash payments to backstop workers sidelined by the COVID-19 pandemic. Some are considering keeping such direct assistance in place indefinitely, or at least until the economic shocks subside.”

SCIENCE
How Gödel’s Proof Works
Natalie Wolchover | Wired
“In 1931, the Austrian logician Kurt Gödel pulled off arguably one of the most stunning intellectual achievements in history. Mathematicians of the era sought a solid foundation for mathematics: a set of basic mathematical facts, or axioms, that was both consistent—never leading to contradictions—and complete, serving as the building blocks of all mathematical truths. But Gödel’s shocking incompleteness theorems, published when he was just 25, crushed that dream.”

Image credit: Pierre Châtel-Innocenti / Unsplash Continue reading

Posted in Human Robots