Tag Archives: students

#436126 Quantum Computing Gets a Boost From AI ...

Illustration: Greg Mably

Anyone of a certain age who has even a passing interest in computers will remember the remarkable breakthrough that IBM made in 1997 when its Deep Blue chess-playing computer defeated Garry Kasparov, then the world chess champion. Computer scientists passed another such milestone in March 2016, when DeepMind (a subsidiary of Alphabet, Google’s parent company) announced that its AlphaGo program had defeated world-champion player Lee Sedol in the game of Go, a board game that had vexed AI researchers for decades. Recently, DeepMind’s algorithms have also bested human players in the computer games StarCraft IIand Quake Arena III.

Some believe that the cognitive capacities of machines will overtake those of human beings in many spheres within a few decades. Others are more cautious and point out that our inability to understand the source of our own cognitive powers presents a daunting hurdle. How can we make thinking machines if we don’t fully understand our own thought processes?

Citizen science, which enlists masses of people to tackle research problems, holds promise here, in no small part because it can be used effectively to explore the boundary between human and artificial intelligence.

Some citizen-science projects ask the public to collect data from their surroundings (as eButterfly does for butterflies) or to monitor delicate ecosystems (as Eye on the Reef does for Australia’s Great Barrier Reef). Other projects rely on online platforms on which people help to categorize obscure phenomena in the night sky (Zooniverse) or add to the understanding of the structure of proteins (Foldit). Typically, people can contribute to such projects without any prior knowledge of the subject. Their fundamental cognitive skills, like the ability to quickly recognize patterns, are sufficient.

In order to design and develop video games that can allow citizen scientists to tackle scientific problems in a variety of fields, professor and group leader Jacob Sherson founded ScienceAtHome (SAH), at Aarhus University, in Denmark. The group began by considering topics in quantum physics, but today SAH hosts games covering other areas of physics, math, psychology, cognitive science, and behavioral economics. We at SAH search for innovative solutions to real research challenges while providing insight into how people think, both alone and when working in groups.

It is computationally intractable to completely map out a higher-dimensional landscape: It is called the curse of high dimensionality, and it plagues many optimization problems.

We believe that the design of new AI algorithms would benefit greatly from a better understanding of how people solve problems. This surmise has led us to establish the Center for Hybrid Intelligence within SAH, which tries to combine human and artificial intelligence, taking advantage of the particular strengths of each. The center’s focus is on the gamification of scientific research problems and the development of interfaces that allow people to understand and work together with AI.

Our first game, Quantum Moves, was inspired by our group’s research into quantum computers. Such computers can in principle solve certain problems that would take a classical computer billions of years. Quantum computers could challenge current cryptographic protocols, aid in the design of new materials, and give insight into natural processes that require an exact solution of the equations of quantum mechanics—something normal computers are inherently bad at doing.

One candidate system for building such a computer would capture individual atoms by “freezing” them, as it were, in the interference pattern produced when a laser beam is reflected back on itself. The captured atoms can thus be organized like eggs in a carton, forming a periodic crystal of atoms and light. Using these atoms to perform quantum calculations requires that we use tightly focused laser beams, called optical tweezers, to transport the atoms from site to site in the light crystal. This is a tricky business because individual atoms do not behave like particles; instead, they resemble a wavelike liquid governed by the laws of quantum mechanics.

In Quantum Moves, a player manipulates a touch screen or mouse to move a simulated laser tweezer and pick up a trapped atom, represented by a liquidlike substance in a bowl. Then the player must bring the atom back to the tweezer’s initial position while trying to minimize the sloshing of the liquid. Such sloshing would increase the energy of the atom and ultimately introduce errors into the operations of the quantum computer. Therefore, at the end of a move, the liquid should be at a complete standstill.

To understand how people and computers might approach such a task differently, you need to know something about how computerized optimization algorithms work. The countless ways of moving a glass of water without spilling may be regarded as constituting a “solution landscape.” One solution is represented by a single point in that landscape, and the height of that point represents the quality of the solution—how smoothly and quickly the glass of water was moved. This landscape might resemble a mountain range, where the top of each mountain represents a local optimum and where the challenge is to find the highest peak in the range—the global optimum.

Illustration: Greg Mably

Researchers must compromise between searching the landscape for taller mountains (“exploration”) and climbing to the top of the nearest mountain (“exploitation”). Making such a trade-off may seem easy when exploring an actual physical landscape: Merely hike around a bit to get at least the general lay of the land before surveying in greater detail what seems to be the tallest peak. But because each possible way of changing the solution defines a new dimension, a realistic problem can have thousands of dimensions. It is computationally intractable to completely map out such a higher-dimensional landscape. We call this the curse of high dimensionality, and it plagues many optimization problems.

Although algorithms are wonderfully efficient at crawling to the top of a given mountain, finding good ways of searching through the broader landscape poses quite a challenge, one that is at the forefront of AI research into such control problems. The conventional approach is to come up with clever ways of reducing the search space, either through insights generated by researchers or with machine-learning algorithms trained on large data sets.

At SAH, we attacked certain quantum-optimization problems by turning them into a game. Our goal was not to show that people can beat computers in this arena but rather to understand the process of generating insights into such problems. We addressed two core questions: whether allowing players to explore the infinite space of possibilities will help them find good solutions and whether we can learn something by studying their behavior.

Today, more than 250,000 people have played Quantum Moves, and to our surprise, they did in fact search the space of possible moves differently from the algorithm we had put to the task. Specifically, we found that although players could not solve the optimization problem on their own, they were good at searching the broad landscape. The computer algorithms could then take those rough ideas and refine them.

Herbert A. Simon said that “solving a problem simply means representing it so as to make the solution transparent.” Apparently, that’s what our games can do with their novel user interfaces.

Perhaps even more interesting was our discovery that players had two distinct ways of solving the problem, each with a clear physical interpretation. One set of players started by placing the tweezer close to the atom while keeping a barrier between the atom trap and the tweezer. In classical physics, a barrier is an impenetrable obstacle, but because the atom liquid is a quantum-mechanical object, it can tunnel through the barrier into the tweezer, after which the player simply moved the tweezer to the target area. Another set of players moved the tweezer directly into the atom trap, picked up the atom liquid, and brought it back. We called these two strategies the “tunneling” and “shoveling” strategies, respectively.

Such clear strategies are extremely valuable because they are very difficult to obtain directly from an optimization algorithm. Involving humans in the optimization loop can thus help us gain insight into the underlying physical phenomena that are at play, knowledge that may then be transferred to other types of problems.

Quantum Moves raised several obvious issues. First, because generating an exceptional solution required further computer-based optimization, players were unable to get immediate feedback to help them improve their scores, and this often left them feeling frustrated. Second, we had tested this approach on only one scientific challenge with a clear classical analogue, that of the sloshing liquid. We wanted to know whether such gamification could be applied more generally, to a variety of scientific challenges that do not offer such immediately applicable visual analogies.

We address these two concerns in Quantum Moves 2. Here, the player first generates a number of candidate solutions by playing the original game. Then the player chooses which solutions to optimize using a built-in algorithm. As the algorithm improves a player’s solution, it modifies the solution path—the movement of the tweezer—to represent the optimized solution. Guided by this feedback, players can then improve their strategy, come up with a new solution, and iteratively feed it back into this process. This gameplay provides high-level heuristics and adds human intuition to the algorithm. The person and the machine work in tandem—a step toward true hybrid intelligence.

In parallel with the development of Quantum Moves 2, we also studied how people collaboratively solve complex problems. To that end, we opened our atomic physics laboratory to the general public—virtually. We let people from around the world dictate the experiments we would run to see if they would find ways to improve the results we were getting. What results? That’s a little tricky to explain, so we need to pause for a moment and provide a little background on the relevant physics.

One of the essential steps in building the quantum computer along the lines described above is to create the coldest state of matter in the universe, known as a Bose-Einstein condensate. Here millions of atoms oscillate in synchrony to form a wavelike substance, one of the largest purely quantum phenomena known. To create this ultracool state of matter, researchers typically use a combination of laser light and magnetic fields. There is no familiar physical analogy between such a strange state of matter and the phenomena of everyday life.

The result we were seeking in our lab was to create as much of this enigmatic substance as was possible given the equipment available. The sequence of steps to accomplish that was unknown. We hoped that gamification could help to solve this problem, even though it had no classical analogy to present to game players.

Images: ScienceAtHome

Fun and Games: The
Quantum Moves game evolved over time, from a relatively crude early version [top] to its current form [second from top] and then a major revision,
Quantum Moves 2 [third from top].
Skill Lab: Science Detective games [bottom] test players’ cognitive skills.

In October 2016, we released a game that, for two weeks, guided how we created Bose-Einstein condensates in our laboratory. By manipulating simple curves in the game interface, players generated experimental sequences for us to use in producing these condensates—and they did so without needing to know anything about the underlying physics. A player would generate such a solution, and a few minutes later we would run the sequence in our laboratory. The number of ultracold atoms in the resulting Bose-Einstein condensate was measured and fed back to the player as a score. Players could then decide either to try to improve their previous solution or to copy and modify other players’ solutions. About 600 people from all over the world participated, submitting 7,577 solutions in total. Many of them yielded bigger condensates than we had previously produced in the lab.

So this exercise succeeded in achieving our primary goal, but it also allowed us to learn something about human behavior. We learned, for example, that players behave differently based on where they sit on the leaderboard. High-performing players make small changes to their successful solutions (exploitation), while poorly performing players are willing to make more dramatic changes (exploration). As a collective, the players nicely balance exploration and exploitation. How they do so provides valuable inspiration to researchers trying to understand human problem solving in social science as well as to those designing new AI algorithms.

How could mere amateurs outperform experienced experimental physicists? The players certainly weren’t better at physics than the experts—but they could do better because of the way in which the problem was posed. By turning the research challenge into a game, we gave players the chance to explore solutions that had previously required complex programming to study. Indeed, even expert experimentalists improved their solutions dramatically by using this interface.

Insight into why that’s possible can probably be found in the words of the late economics Nobel laureate Herbert A. Simon: “Solving a problem simply means representing it so as to make the solution transparent [PDF].” Apparently, that’s what our games can do with their novel user interfaces. We believe that such interfaces might be a key to using human creativity to solve other complex research problems.

Eventually, we’d like to get a better understanding of why this kind of gamification works as well as it does. A first step would be to collect more data on what the players do while they are playing. But even with massive amounts of data, detecting the subtle patterns underlying human intuition is an overwhelming challenge. To advance, we need a deeper insight into the cognition of the individual players.

As a step forward toward this goal, ScienceAtHome created Skill Lab: Science Detective, a suite of minigames exploring visuospatial reasoning, response inhibition, reaction times, and other basic cognitive skills. Then we compare players’ performance in the games with how well these same people did on established psychological tests of those abilities. The point is to allow players to assess their own cognitive strengths and weaknesses while donating their data for further public research.

In the fall of 2018 we launched a prototype of this large-scale profiling in collaboration with the Danish Broadcasting Corp. Since then more than 20,000 people have participated, and in part because of the publicity granted by the public-service channel, participation has been very evenly distributed across ages and by gender. Such broad appeal is rare in social science, where the test population is typically drawn from a very narrow demographic, such as college students.

Never before has such a large academic experiment in human cognition been conducted. We expect to gain new insights into many things, among them how combinations of cognitive abilities sharpen or decline with age, what characteristics may be used to prescreen for mental illnesses, and how to optimize the building of teams in our work lives.

And so what started as a fun exercise in the weird world of quantum mechanics has now become an exercise in understanding the nuances of what makes us human. While we still seek to understand atoms, we can now aspire to understand people’s minds as well.

This article appears in the November 2019 print issue as “A Man-Machine Mind Meld for Quantum Computing.”

About the Authors
Ottó Elíasson, Carrie Weidner, Janet Rafner, and Shaeema Zaman Ahmed work with the ScienceAtHome project at Aarhus University in Denmark. Continue reading

Posted in Human Robots

#435824 A Q&A with Cruise’s head of AI, ...

In 2016, Cruise, an autonomous vehicle startup acquired by General Motors, had about 50 employees. At the beginning of 2019, the headcount at its San Francisco headquarters—mostly software engineers, mostly working on projects connected to machine learning and artificial intelligence—hit around 1000. Now that number is up to 1500, and by the end of this year it’s expected to reach about 2000, sprawling into a recently purchased building that had housed Dropbox. And that’s not counting the 200 or so tech workers that Cruise is aiming to install in a Seattle, Wash., satellite development center and a handful of others in Phoenix, Ariz., and Pasadena, Calif.

Cruise’s recent hires aren’t all engineers—it takes more than engineering talent to manage operations. And there are hundreds of so-called safety drivers that are required to sit in the 180 or so autonomous test vehicles whenever they roam the San Francisco streets. But that’s still a lot of AI experts to be hiring in a time of AI engineer shortages.

Hussein Mehanna, head of AI/ML at Cruise, says the company’s hiring efforts are on track, due to the appeal of the challenge of autonomous vehicles in drawing in AI experts from other fields. Mehanna himself joined Cruise in May from Google, where he was director of engineering at Google Cloud AI. Mehanna had been there about a year and a half, a relatively quick career stop after a short stint at Snap following four years working in machine learning at Facebook.

Mehanna has been immersed in AI and machine learning research since his graduate studies in speech recognition and natural language processing at the University of Cambridge. I sat down with Mehanna to talk about his career, the challenges of recruiting AI experts and autonomous vehicle development in general—and some of the challenges specific to San Francisco. We were joined by Michael Thomas, Cruise’s manager of AI/ML recruiting, who had also spent time recruiting AI engineers at Google and then Facebook.

IEEE Spectrum: When you were at Cambridge, did you think AI was going to take off like a rocket?

Mehanna: Did I imagine that AI was going to be as dominant and prevailing and sometimes hyped as it is now? No. I do recall in 2003 that my supervisor and I were wondering if neural networks could help at all in speech recognition. I remember my supervisor saying if anyone could figure out how use a neural net for speech he would give them a grant immediately. So he was on the right path. Now neural networks have dominated vision, speech, and language [processing]. But that boom started in 2012.

“In the early days, Facebook wasn’t that open to PhDs, it actually had a negative sentiment about researchers, and then Facebook shifted”

I didn’t [expect it], but I certainly aimed for it when [I was at] Microsoft, where I deliberately pushed my career towards machine learning instead of big data, which was more popular at the time. And [I aimed for it] when I joined Facebook.

In the early days, Facebook wasn’t that open to PhDs, or researchers. It actually had a negative sentiment about researchers. And then Facebook shifted to becoming one of the key places where PhD students wanted to do internships or join after they graduated. It was a mindset shift, they were [once] at a point in time where they thought what was needed for success wasn’t research, but now it’s different.

There was definitely an element of risk [in taking a machine learning career path], but I was very lucky, things developed very fast.

IEEE Spectrum: Is it getting harder or easier to find AI engineers to hire, given the reported shortages?

Mehanna: There is a mismatch [between job openings and qualified engineers], though it is hard to quantify it with numbers. There is good news as well: I see a lot more students diving deep into machine learning and data in their [undergraduate] computer science studies, so it’s not as bleak as it seems. But there is massive demand in the market.

Here at Cruise, demand for AI talent is just growing and growing. It might be is saturating or slowing down at other kinds of companies, though, [which] are leveraging more traditional applications—ad prediction, recommendations—that have been out there in the market for a while. These are more mature, better understood problems.

I believe autonomous vehicle technologies is the most difficult AI problem out there. The magnitude of the challenge of these problems is 1000 times more than other problems. They aren’t as well understood yet, and they require far deeper technology. And also the quality at which they are expected to operate is off the roof.

The autonomous vehicle problem is the engineering challenge of our generation. There’s a lot of code to write, and if we think we are going to hire armies of people to write it line by line, it’s not going to work. Machine learning can accelerate the process of generating the code, but that doesn’t mean we aren’t going to have engineers; we actually need a lot more engineers.

Sometimes people worry that AI is taking jobs. It is taking some developer jobs, but it is actually generating other developer jobs as well, protecting developers from the mundane and helping them build software faster and faster.

IEEE Spectrum: Are you concerned that the demand for AI in industry is drawing out the people in academia who are needed to educate future engineers, that is, the “eating the seed corn” problem?

Mehanna: There are some negative examples in the industry, but that’s not our style. We are looking for collaborations with professors, we want to cultivate a very deep and respectful relationship with universities.

And there’s another angle to this: Universities require a thriving industry for them to thrive. It is going to be extremely beneficial for academia to have this flourishing industry in AI, because it attracts more students to academia. I think we are doing them a fantastic favor by building these career opportunities. This is not the same as in my early days, [when] people told me “don’t go to AI; go to networking, work in the mobile industry; mobile is flourishing.”

IEEE Spectrum: Where are you looking as you try to find a thousand or so engineers to hire this year?

Thomas: We look for people who want to use machine learning to solve problems. They can be in many different industries—in the financial markets, in social media, in advertising. The autonomous vehicle industry is in its infancy. You can compare it to mobile in the early days: When the iPhone first came out, everyone was looking for developers with mobile experience, but you weren’t going to find them unless you went to straight to Apple, [so you had to hire other kinds of engineers]. This is the same type of thing: it is so new that you aren’t going to find experts in this area, because we are all still learning.

“You don’t have to be an autonomous vehicle expert to flourish in this world. It’s not too late to move…now would be a great time for AI experts working on other problems to shift their attention to autonomous vehicles.”

Mehanna: Because autonomous vehicle technology is the new frontier for AI experts, [the number of] people with both AI and autonomous vehicle experience is quite limited. So we are acquiring AI experts wherever they are, and helping them grow into the autonomous vehicle area. You don’t have to be an autonomous vehicle expert to flourish in this world. It’s not too late to move; even though there is a lot of great tech developed, there’s even more innovation ahead, so now would be a great time for AI experts working on other problems or applications to shift their attention to autonomous vehicles.

It feels like the Internet in 1980. It’s about to happen, but there are endless applications [to be developed over] the next few decades. Even if we can get a car to drive safely, there is the question of how can we tune the ride comfort, and then applying it all to different cities, different vehicles, different driving situations, and who knows to what other applications.

I can see how I can spend a lifetime career trying to solve this problem.

IEEE Spectrum: Why are you doing most of your development in San Francisco?

Mehanna: I think the best talent of the world is in Silicon Valley, and solving the autonomous vehicle problem is going to require the best of the best. It’s not just the engineering talent that is here, but [also] the entrepreneurial spirit. Solving the problem just as a technology is not going to be successful, you need to solve the product and the technology together. And the entrepreneurial spirit is one of the key reasons Cruise secured 7.5 billion in funding [besides GM, the company has a number of outside investors, including Honda, Softbank, and T. Rowe Price]. That [funding] is another reason Cruise is ahead of many others, because this problem requires deep resources.

“If you can do an autonomous vehicle in San Francisco you can do it almost anywhere.”

[And then there is the driving environment.] When I speak to my peers in the industry, they have a lot of respect for us, because the problems to solve in San Francisco technically are an order of magnitude harder. It is a tight environment, with a lot of pedestrians, and driving patterns that, let’s put it this way, are not necessarily the best in the nation. Which means we are seeing more problems ahead of our competitors, which gets us to better [software]. I think if you can do an autonomous vehicle in San Francisco you can do it almost anywhere.

A version of this post appears in the September 2019 print magazine as “AI Engineers: The Autonomous-Vehicle Industry Wants You.” Continue reading

Posted in Human Robots

#435804 New AI Systems Are Here to Personalize ...

The narratives about automation and its impact on jobs go from urgent to hopeful and everything in between. Regardless where you land, it’s hard to argue against the idea that technologies like AI and robotics will change our economy and the nature of work in the coming years.

A recent World Economic Forum report noted that some estimates show automation could displace 75 million jobs by 2022, while at the same time creating 133 million new roles. While these estimates predict a net positive for the number of new jobs in the coming decade, displaced workers will need to learn new skills to adapt to the changes. If employees can’t be retrained quickly for jobs in the changing economy, society is likely to face some degree of turmoil.

According to Bryan Talebi, CEO and founder of AI education startup Ahura AI, the same technologies erasing and creating jobs can help workers bridge the gap between the two.

Ahura is developing a product to capture biometric data from adult learners who are using computers to complete online education programs. The goal is to feed this data to an AI system that can modify and adapt their program to optimize for the most effective teaching method.

While the prospect of a computer recording and scrutinizing a learner’s behavioral data will surely generate unease across a society growing more aware and uncomfortable with digital surveillance, some people may look past such discomfort if they experience improved learning outcomes. Users of the system would, in theory, have their own personalized instruction shaped specifically for their unique learning style.

And according to Talebi, their systems are showing some promise.

“Based on our early tests, our technology allows people to learn three to five times faster than traditional education,” Talebi told me.

Currently, Ahura’s system uses the video camera and microphone that come standard on the laptops, tablets, and mobile devices most students are using for their learning programs.

With the computer’s camera Ahura can capture facial movements and micro expressions, measure eye movements, and track fidget score (a measure of how much a student moves while learning). The microphone tracks voice sentiment, and the AI leverages natural language processing to review the learner’s word usage.

From this collection of data Ahura can, according to Talebi, identify the optimal way to deliver content to each individual.

For some users that might mean a video tutorial is the best style of learning, while others may benefit more from some form of experiential or text-based delivery.

“The goal is to alter the format of the content in real time to optimize for attention and retention of the information,” said Talebi. One of Ahura’s main goals is to reduce the frequency with which students switch from their learning program to distractions like social media.

“We can now predict with a 60 percent confidence interval ten seconds before someone switches over to Facebook or Instagram. There’s a lot of work to do to get that up to a 95 percent level, so I don’t want to overstate things, but that’s a promising indication that we can work to cut down on the amount of context-switching by our students,” Talebi said.

Talebi repeatedly mentioned his ambition to leverage the same design principles used by Facebook, Twitter, and others to increase the time users spend on those platforms, but instead use them to design more compelling and even addictive education programs that can compete for attention with social media.

But the notion that Ahura’s system could one day be used to create compelling or addictive education necessarily presses against a set of justified fears surrounding data privacy. Growing anxiety surrounding the potential to misuse user data for social manipulation is widespread.

“Of course there is a real danger, especially because we are collecting so much data about our users which is specifically connected to how they consume content. And because we are looking so closely at the ways people interact with content, it’s incredibly important that this technology never be used for propaganda or to sell things to people,” Talebi tried to assure me.

Unsurprisingly (and worrying), using this AI system to sell products to people is exactly where some investors’ ambitions immediately turn once they learn about the company’s capabilities, according to Talebi. During our discussion Talebi regularly cited the now infamous example of Cambridge Analytica, the political consulting firm hired by the Trump campaign to run a psychographically targeted persuasion campaign on the US population during the most recent presidential election.

“It’s important that we don’t use this technology in those ways. We’re aware that things can go sideways, so we’re hoping to put up guardrails to ensure our system is helping and not harming society,” Talebi said.

Talebi will surely need to take real action on such a claim, but says the company is in the process of identifying a structure for an ethics review board—one that carries significant influence with similar voting authority as the executive team and the regular board.

“Our goal is to build an ethics review board that has teeth, is diverse in both gender and background but also in thought and belief structures. The idea is to have our ethics review panel ensure we’re building things ethically,” he said.

Data privacy appears to be an important issue for Talebi, who occasionally referenced a major competitor in the space based in China. According to a recent article from MIT Tech Review outlining the astonishing growth of AI-powered education platforms in China, data privacy concerns may be less severe there than in the West.

Ahura is currently developing upgrades to an early alpha-stage prototype, but is already capturing data from students from at least one Ivy League school and a variety of other places. Their next step is to roll out a working beta version to over 200,000 users as part of a partnership with an unnamed corporate client who will be measuring the platform’s efficacy against a control group.

Going forward, Ahura hopes to add to its suite of biometric data capture by including things like pupil dilation and facial flushing, heart rate, sleep patterns, or whatever else may give their system an edge in improving learning outcomes.

As information technologies increasingly automate work, it’s likely we’ll also see rapid changes to our labor systems. It’s also looking increasingly likely that those same technologies will be used to improve our ability to give people the right skills when they need them. It may be one way to address the challenges automation is sure to bring.

Image Credit: Gerd Altmann / Pixabay Continue reading

Posted in Human Robots

#435779 This Robot Ostrich Can Ride Around on ...

Proponents of legged robots say that they make sense because legs are often required to go where humans go. Proponents of wheeled robots say, “Yeah, that’s great but watch how fast and efficient my robot is, compared to yours.” Some robots try and take advantage of wheels and legs with hybrid designs like whegs or wheeled feet, but a simpler and more versatile solution is to do what humans do, and just take advantage of wheels when you need them.

We’ve seen a few experiments with this. The University of Michigan managed to convince Cassie to ride a Segway, with mostly positive (but occasionally quite negative) results. A Segway, and hoverboard-like systems, can provide wheeled mobility for legged robots over flat terrain, but they can’t handle things like stairs, which is kind of the whole point of having a robot with legs anyway.

Image: UC Berkeley

From left, a Segway, a hovercraft, and hovershoes, with complexity in terms of user control increasing from left to right.

At UC Berkeley’s Hybrid Robotics Lab, led by Koushil Sreenath, researchers have taken things a step further. They are teaching their Cassie bipedal robot (called Cassie Cal) to wheel around on a pair of hovershoes. Hovershoes are like hoverboards that have been chopped in half, resulting in a pair of motorized single-wheel skates. You balance on the skates, and control them by leaning forwards and backwards and left and right, which causes each skate to accelerate or decelerate in an attempt to keep itself upright. It’s not easy to get these things to work, even for a human, but by adding a sensor package to Cassie the UC Berkeley researchers have managed to get it to zip around campus fully autonomously.

Remember, Cassie is operating autonomously here—it’s performing vSLAM (with an Intel RealSense) and doing all of its own computation onboard in real time. Watching it jolt across that cracked sidewalk is particularly impressive, especially considering that it only has pitch control over its ankles and can’t roll its feet to maintain maximum contact with the hovershoes. But you can see the advantage that this particular platform offers to a robot like Cassie, including the ability to handle stairs. Stairs in one direction, anyway.

It’s a testament to the robustness of UC Berkeley’s controller that they were willing to let the robot operate untethered and outside, and it sounds like they’re thinking long-term about how legged robots on wheels would be real-world useful:

Our feedback control and autonomous system allow for swift movement through urban environments to aid in everything from food delivery to security and surveillance to search and rescue missions. This work can also help with transportation in large factories and warehouses.

For more details, we spoke with the UC Berkeley students (Shuxiao Chen, Jonathan Rogers, and Bike Zhang) via email.

IEEE Spectrum: How representative of Cassie’s real-world performance is what we see in the video? What happens when things go wrong?

Cassie’s real-world performance is similar to what we see in the video. Cassie can ride the hovershoes successfully all around the campus. Our current controller allows Cassie to robustly ride the hovershoes and rejects various perturbations. At present, one of the failure modes is when the hovershoe rolls to the side—this happens when it goes sideways down a step or encounters a large obstacle on one side of it, causing it to roll over. Under these circumstances, Cassie doesn’t have sufficient control authority (due to the thin narrow feet) to get the hovershoe back on its wheel.

The Hybrid Robotics Lab has been working on robots that walk over challenging terrain—how do wheeled platforms like hovershoes fit in with that?

Surprisingly, this research is related to our prior work on walking on discrete terrain. While locomotion using legs is efficient when traveling over rough and discrete terrain, wheeled locomotion is more efficient when traveling over flat continuous terrain. Enabling legged robots to ride on various micro-mobility platforms will offer multimodal locomotion capabilities, improving the efficiency of locomotion over various terrains.

Our current research furthers the locomotion ability for bipedal robots over continuous terrains by using a wheeled platform. In the long run, we would like to develop multi-modal locomotion strategies based on our current and prior work to allow legged robots to robustly and efficiently locomote in our daily life.

Photo: UC Berkeley

In their experiments, the UC Berkeley researchers say Cassie proved quite capable of riding the hovershoes over rough and uneven terrain, including going down stairs.

How long did it take to train Cassie to use the hovershoes? Are there any hovershoe skills that Cassie is better at than an average human?

We spent about eight months to develop our whole system, including a controller, a path planner, and a vision system. This involved developing mathematical models of Cassie and the hovershoes, setting up a dynamical simulation, figuring out how to interface and communicate with various sensors and Cassie, and doing several experiments to slowly improve performance. In contrast, a human with a good sense of balance needs a few hours to learn to use the hovershoes. A human who has never used skates or skis will probably need a longer time.

A human can easily turn in place on the hovershoes, while Cassie cannot do this motion currently due to our algorithm requiring a non-zero forward speed in order to turn. However, Cassie is much better at riding the hovershoes over rough and uneven terrain including riding the hovershoes down some stairs!

What would it take to make Cassie faster or more agile on the hovershoes?

While Cassie can currently move at a decent pace on the hovershoes and navigate obstacles, Cassie’s ability to avoid obstacles at rapid speeds is constrained by the sensing, the controller, and the onboard computation. To enable Cassie to dynamically weave around obstacles at high speeds exhibiting agile motions, we need to make progress on different fronts.

We need planners that take into account the entire dynamics of the Cassie-Hovershoe system and rapidly generate dynamically-feasible trajectories; we need controllers that tightly coordinate all the degrees-of-freedom of Cassie to dynamically move while balancing on the hovershoes; we need sensors that are robust to motion-blur artifacts caused due to fast turns; and we need onboard computation that can execute our algorithms at real-time speeds.

What are you working on next?

We are working on enabling more aggressive movements for Cassie on the hovershoes by fully exploiting Cassie’s dynamics. We are working on approaches that enable us to easily go beyond hovershoes to other challenging micro-mobility platforms. We are working on enabling Cassie to step onto and off from wheeled platforms such as hovershoes. We would like to create a future of multi-modal locomotion strategies for legged robots to enable them to efficiently help people in our daily life.

“Feedback Control for Autonomous Riding of Hovershoes by a Cassie Bipedal Robot,” by Shuxiao Chen, Jonathan Rogers, Bike Zhang, and Koushil Sreenath from the Hybrid Robotics Lab at UC Berkeley, has been submitted to IEEE Robotics and Automation Letters with option to be presented at the 2019 IEEE RAS International Conference on Humanoid Robots. Continue reading

Posted in Human Robots

#435752 T-RHex Is a Hexapod Robot With ...

In Aaron Johnson’s “Robot Design & Experimentation” class at CMU, teams of students have a semester to design and build an experimental robotic system based on a theme. For spring 2019, that theme was “Bioinspired Robotics,” which is definitely one of our favorite kinds of robotics—animals can do all kinds of crazy things, and it’s always a lot of fun watching robots try to match them. They almost never succeed, of course, but even basic imitation can lead to robots with some unique capabilities.

One of the projects from this year’s course, from Team ScienceParrot, is a new version of RHex called T-RHex (pronounced T-Rex, like the dinosaur). T-RHex comes with a tail, but more importantly, it has tiny tapered toes, which help it grip onto rough surfaces like bricks, wood, and concrete. It’s able to climb its way up very steep slopes, and hang from them, relying on its toes to keep itself from falling off.

T-RHex’s toes are called microspines, and we’ve seen them in all kinds of robots. The most famous of these is probably JPL’s LEMUR IIB (which wins on sheer microspine volume), although the concept goes back at least 15 years to Stanford’s SpinyBot. Robots that use microspines to climb tend to be fairly methodical at it, since the microspines have to be engaged and disengaged with care, limiting their non-climbing mobility.

T-RHex manages to perform many of the same sorts of climbing and hanging maneuvers without losing RHex’s ability for quick, efficient wheel-leg (wheg) locomotion.

If you look closely at T-RHex walking in the video, you’ll notice that in its normal forward gait, it’s sort of walking on its ankles, rather than its toes. This means that the microspines aren’t engaged most of the time, so that the robot can use its regular wheg motion to get around. To engage the microspines, the robot moves its whegs backwards, meaning that its tail is arguably coming out of its head. But since all of T-RHex’s capability is mechanical in nature and it has no active sensors, it doesn’t really need a head, so that’s fine.

The highest climbable slope that T-RHex could manage was 55 degrees, meaning that it can’t, yet, conquer vertical walls. The researchers were most surprised by the robot’s ability to cling to surfaces, where it was perfectly happy to hang out on a slope of 135 degrees, which is a 45 degree overhang (!). I have no idea how it would ever reach that kind of position on its own, but it’s nice to know that if it ever does, its spines will keep doing their job.

Photo: CMU

T-RHex uses laser-cut acrylic legs, with the microspines embedded into 3D-printed toes. The tail is needed to prevent the robot from tipping backward.

For more details about the project, we spoke with Team ScienceParrot member (and CMU PhD student) Catherine Pavlov via email.

IEEE Spectrum: We’re used to seeing RHex with compliant, springy legs—how do the new legs affect T-RHex’s mobility?

Catherine Pavlov: There’s some compliance in the legs, though not as much as RHex—this is driven by the use of acrylic, which was chosen for budget/manufacturing reasons. Matching the compliance of RHex with acrylic would have made the tines too weak (since often only a few hold the load of the robot during climbing). It definitely means you can’t use energy storage in the legs the way RHex does, for example when pronking. T-RHex is probably more limited by motor speed in terms of mobility though. We were using some borrowed Dynamixels that didn’t allow for good positioning at high speeds.

How did you design the climbing gait? Why not use the middle legs, and why is the tail necessary?

The gait was a lot of hand-tuning and trial-and-error. We wanted a left/right symmetric gait to enable load sharing among more spines and prevent out-of-plane twisting of the legs. When using all three pairs, you have to have very accurate angular positioning or one leg pair gets pushed off the wall. Since two legs should be able to hold the full robot gait, using the middle legs was hurting more than it was helping, with the middle legs sometimes pushing the rear ones off of the wall.

The tail is needed to prevent the robot from tipping backward and “sitting” on the wall. During static testing we saw the robot tip backward, disengaging the front legs, at around 35 degrees incline. The tail allows us to load the front legs, even when they’re at a shallow angle to the surface. The climbing gait we designed uses the tail to allow the rear legs to fully recirculate without the robot tipping backward.

Photo: CMU

Team ScienceParrot with T-RHex.

What prevents T-RHex from climbing even steeper surfaces?

There are a few limiting factors. One is that the tines of the legs break pretty easily. I think we also need a lighter platform to get fully vertical—we’re going to look at MiniRHex for future work. We’re also not convinced our gait is the best it can be, we can probably get marginal improvements with more tuning, which might be enough.

Can the microspines assist with more dynamic maneuvers?

Dynamic climbing maneuvers? I think that would only be possible on surfaces with very good surface adhesion and very good surface strength, but it’s certainly theoretically possible. The current instance of T-RHex would definitely break if you tried to wall jump though.

What are you working on next?

Our main target is exploring the space of materials for leg fabrication, such as fiberglass, PLA, urethanes, and maybe metallic glass. We think there’s a lot of room for improvement in the leg material and geometry. We’d also like to see MiniRHex equipped with microspines, which will require legs about half the scale of what we built for T-RHex. Longer-term improvements would be the addition of sensors e.g. for wall detection, and a reliable floor-to-wall transition and dynamic gait transitions.

[ T-RHex ] Continue reading

Posted in Human Robots