schwit1 writes: Able to move 1,600 boxes per hour using just one arm, Dill relies on humans to keep it operating efficiently Pickle Robots says that Dill's approach to the box unloading task is unique in a couple of ways. First, it can handle messy trailers filled with a jumble of boxes of different shapes, colors, sizes, and weights. And second, from the get-go it's intended to work under human supervision, relying on people to step in and handle edge cases.

We asked Meyer how much Dill costs, and to our surprise, he gave us a candid answer: Depending on the configuration, the system can cost anywhere from $50-100k to deploy and about that same amount per year to operate. Meyer points out that you can't really compare the robot to a human (or humans) simply on speed, since with the robot, you don't have to worry about injuries or improper sorting of packages or training or turnover. While Pickle is currently working on several other configurations of robots for package handling, this particular truck unloading configuration will be shipping to customers next year.

"Jensen Huang, the CEO of Nvidia, the nation's most valuable semiconductor company, with a stock price of $645 a share and a market cap of $400 billion, is out to create the metaverse," writes Time magazine.

Huang defines it as "a virtual world that is a digital twin of ours." Huang credits author Neal Stephenson's Snow Crash, filled with collectives of shared 3-D spaces and virtually enhanced physical spaces that are extensions of the Internet, for conjuring the metaverse. This is already playing out with the massively popular online games like Fortnite and Minecraft, where users create richly imagined virtual worlds. Now the concept is being put to work by Nvidia and others.

Partnering with Nvidia, BMW is using a virtual digital twin of a factory in Regensburg, Germany, to virtually plan new workflows before deploying the changes in real time in their physical factory. The metaverse, says Huang, "is where we will create the future" and transform how the world's biggest industries operate...

Not to make any value judgments about the importance of video games, but do you find it ironic that a company that has its roots in entertainment is now providing vitally important computing power for drug discovery, basic research and reinventing manufacturing?

No, not at all. It's actually the opposite. We always started as a computing company. It just turned out that our first killer app was video games...

How important is the advent and the adaptation of digital twins for manufacturing, business and society at large?

In the future, the digital world or the virtual world will be thousands of times bigger than the physical world. There will be a new New York City. There'll be a new Shanghai. Every single factory and every single building will have a digital twin that will simulate and track the physical version of it. Always. By doing so, engineers and software programmers could simulate new software that will ultimately run in the physical version of the car, the physical version of the robot, the physical version of the airport, the physical version of the building. All of the software that's going to be running in these physical things will be simulated in the digital twin first, and then it will be downloaded into the physical version. And as a result, the product keeps getting better at an exponential rate.

The second thing is, you're going to be able to go in and out of the two worlds through wormholes. We'll go into the virtual world using virtual reality, and the objects in the virtual world, in the digital world, will come into the physical world, using augmented reality. So what's going to happen is pieces of the digital world will be temporarily, or even semipermanently, augmenting our physical world. It's ultimately about the fusion of the virtual world and the physical world.
See also this possibly related story, "Nvidia's newest AI model can transform single images into realistic 3D models."

EW reports: Felix Silla's friend and former Buck Rogers in the 25th Century costar Gil Gerard reported on Twitter that Silla died Friday after a battle with pancreatic cancer.

Coming in at just under 4 feet tall and only 70 pounds, Silla was the perfect choice for the mumbling Cousin Itt on The Addams Family. For years, audiences didn't see his face, the character covered in a full-length hairpiece, sporting sunglasses and a bowler hat... Silla did not provide the distinct mumbling voice of Cousin Itt. That was added by sound engineer Tony Magro in production...

He first came to the United States in 1955 and began his career touring with the Ringling Bros. and Barnum & Bailey Circus for seven years. He worked as a trapeze artist, tumbler, and bareback horse rider. Eventually, he settled in Hollywood in 1962, where he became a stuntman. He went on to work in movies like A Ticklish Fair, TV shows like Bonanza, and appeared in the first pilot for Star Trek, "The Cage." His small stature often helped him find work, including as Cousin Itt, robot sidekick Twiki on the NBC series Buck Rogers in the 25th Century, and even as a hang-gliding Ewok in Star Wars: Return of the Jedi...

He also excelled as a stand in, double, and stuntman working on projects such as Planet of the Apes, Demon Seed, Indiana Jones and the Temple of Doom, The Towering Inferno, The Hindenburg, E.T. the Extra-Terrestrial, Poltergeist, The Golden Child, Howard the Duck, and Batman Returns.
In 2018 one Las Vegas blog spotted Silla with Gil Gerard, posting a picture of the two side by side -- just as they'd posed decades earlier on Buck Rogers in the 25th Century.

While for that show Mel Blanc had provided the voice for Twiki the robot, the blog notes that Silla himself supplied the voice of Mortimer Goth in the Sims 2 videogame.

The days of experts gathering in a sealed-off room to sip coffee and grade beans on their color, aroma and taste may be numbered. From a report: An Israeli company has developed a handheld device that is able to scan beans to determine their quality. The machine, powered by artificial intelligence, will need a human to input the quality parameters first, but after that, it will be able to classify coffee before it's even roasted. The company has completed a pilot program with Carcafe, the Colombian division of Volcafe, one of the world's largest coffee traders. A shift to computers would upend the traditional way coffee has been graded by humans, known as cupping. The well-paid and trained examiners, or Q graders, at the ICE Futures U.S. exchange in New York conduct the laborious task of determining the quality and value of the coffee beans received by the bourse. Trading houses and roasters also usually have their own graders.

Cupping is an involved process, not unlike that undertaken by wine sommeliers. Q graders weigh the coffee and grind it into a cup. They sniff the dry grounds, taking notes on the fragrance. Water heated to 200 degrees Fahrenheit (93 Celsius) is poured over the grounds and the graders smell the wet coffee. After 4 minutes, the crust that forms on top of the cup is broken and grounds and foam are removed. After waiting 15 minutes for the coffee to cool, and only then is the coffee slurped up in a spoon. "It's the human that establishes the sensorial part," said Oswaldo Aranha Neto, a coffee industry veteran who just joined Demetria as a board member. "You need to teach the robot what to do."

In his final letter to shareholders as Amazon CEO, Jeff Bezos said that the company has to "do a better job for our employees." But, as The Verge points out, the outlined strategy includes "a robotic scheme that will develop new staffing schedules using an algorithm." From the report: Bezos pushed back on the idea that, according to news reports, Amazon doesn't care for its employees. "In those reports, our employees are sometimes accused of being desperate souls and treated as robots. That's not accurate,â he wrote. To address concerns about working conditions, Bezos said the company will develop new staffing schedules "that use sophisticated algorithms to rotate employees among jobs that use different muscle-tendon groups to decrease repetitive motion and help protect employees from MSD risks." The technology will roll out throughout 2021, he said.

In addition to giving a nod to working conditions at Amazon, the letter is the first time Bezos has publicly addressed the failed union drive at its Bessemer, Alabama plant. "Does your Chair take comfort in the outcome of the recent union vote in Bessemer? No, he doesn't," Bezos wrote. "I think we need to do a better job for our employees. While the voting results were lopsided and our direct relationship with employees is strong, it's clear to me that we need a better vision for how we create value for employees -- a vision for their success."

Carbon Robotics, a Seattle company led by Isilon Systems co-founder Paul Mikesell, is unveiling its self-driving robot that uses artificial intelligence to identify weeds growing in fields of vegetables, then zaps them with precision thermal bursts from lasers. GeekWire reports: [W]hat farmers need is less a revolution in farming methods than a revolutionary tool that fits into their current farming patterns, Mikesell said. Carbon worked closely with farmers in eastern Oregon and southern Idaho, he said. As a result, Carbon's robot system -- the Autonomous Weeder -- was built about the size of a medium tractor so it would fit in the furrows between rows of common crops like onions and sweet potatoes.

It can cover up to 16 acres of cropland a day, zapping as many as 100,000 weeds an hour, Mikesell said. And since it's self-driving, all a farmer has to do is take it to the field in the morning and turn it on. "We're really intent on not making farmers have to change how they're doing things," Mikesell said. "That's been a key to our success. We fit right into their operations."

Carbon has sold out all the robots it built for the 2021 planting season, and is looking for an industrial partner who could help it build more units for 2022, Mikesell said. The company is looking to get into the hundreds of units built and shipped for next year, he said. "There's a demand for a lot more than that, tens or hundreds of thousands of them."

An anonymous reader quotes a report from Bloomberg: South Koreans must learn how to work alongside machines if they want to thrive in a post-pandemic world where many jobs will be handled by artificial intelligence and robots, according to the country's labor minister. "Automation and AI will change South Korea faster than other countries," Minister of Employment and Labor Lee Jae-kap said in an interview Tuesday. "Not all jobs may be replaced by machines, but it's important to learn ways to work well with machines through training."

While people will have to increase their adaptability to work in a fast-changing high-tech environment, policy makers will also need to play their part, Lee said. The government needs to provide support to enable workers to move from one sector of the economy to another in search of employment and find ways to increase the activity of women in the economy, he added. The minister's remarks underline the determination of President Moon Jae-in's government to press ahead with a growth strategy built around tech even if it risks alienating the country's unions -- an important base of support for the ruling camp -- in the short term. "New jobs will be created as technology advances," Lee said. "What's important in policy is how to support a worker move from a fading sector to an emerging one." The government is looking to help with this transition by expanding its employment insurance program to 21 million people, or more than 40% of the population, by 2025. "The program is part of a government initiative to provide financial support in the form of insurance for every worker in the country, whether they are artists, freelancers or deliverymen on digital platforms," adds Bloomberg.

"Separately, the government is providing stipends for young people to encourage them to keep searching for work, as their struggle to stay employed amid slowing economic growth has been made tougher by the pandemic."

Long-time Slashdot reader AmiMoJo quotes a classic article from IEEE Spectrum: A study by a team of Japanese researchers shows that, in certain situations, children are actually horrible little brats^W^W^W may not be as empathetic towards robots as we'd previously thought, with gangs of unsupervised tykes repeatedly punching, kicking, and shaking a robot in a Japanese mall...

The Japanese group didn't just document the bullying behavior, though; they wanted to find clever ways of helping the robot avoid the abusive situations. They started by developing a computer simulation and statistical model of the children's abuse towards the robot, showing that it happens primarily when the kids are in groups and no adults are nearby. Next, they designed an abuse-evading algorithm to help the robot avoid situations where tiny humans might gang up on it. Literally tiny humans: the robot is programmed to run away from people who are below a certain height and escape in the direction of taller people.

When it encounters a human, the system calculates the probability of abuse based on interaction time, pedestrian density, and the presence of people above or below 1.4 meters (4 feet 6 inches) in height. If the robot is statistically in danger, it changes its course towards a more crowded area or a taller person. This ensures that an adult is there to intervene when one of the little brats decides to pound the robot's head with a bottle (which only happened a couple times).

A group of scientists from MIT have equipped a robot with a wrist-mounted camera and an RF reader to help it find hidden objects. "As long an item has an RF tag on it, the robot can find it, even if it's hidden behind things like wrapping paper," reports Engadget. From the report: The team told MIT News the most challenging aspect of developing RF Grasp was integrating both sight and RF vision into its decision-making process. They compare the current system to how you might react to a sound in the distance by turning your head to pinpoint its source. RF Grasp will initially use its RF reader to find tagged objects, but the closer it gets to something, the more it depends on the information it collects through its camera to make a decision. Compared to a robot with only a visual system, RF Grasp can locate and pick up an object in about half as many total movements. It also has the unique ability to clean up and declutter its working space as it goes about its tasks.

The team sees RF Grasp helping companies like Amazon further automate and streamline their warehouses. "Perception and picking are two roadblocks in the industry today," said Associate Professor Alberto Rodriguez, one of the researchers who worked on the project.

A robot armed with virus-killing ultraviolet light is being tested on Swiss airplanes, yet another idea aiming to restore passenger confidence and spare the travel industry more pandemic pain. Reuters reports: UVeya, a Swiss start-up, is conducting the trials of the robots with Dubai-based airport services company Dnata inside Embraer jets from Helvetic Airways, a charter airline owned by Swiss billionaire Martin Ebner. Aircraft makers still must certify the devices and are studying the impact their UV light may have on interior upholstery, which could fade after many disinfections, UVeya co-founder Jodoc Elmiger said. Still, he's hopeful robot cleaners could reduce people's fear of flying, even as COVID-19 circulates.

Elmiger's team has built three prototypes so far, one of which he demonstrated inside a Helvetic jet at the Zurich Airport, where traffic plunged 75% last year. The robot's lights, mounted on a crucifix-shaped frame, cast everything in a soft-blue glow as it slowly moved up the Embraer's aisle. One robot can disinfect a single-aisled plane in 13 minutes, start to finish, though larger planes take longer. Dnata executives hope airplane makers will sign off on the robots -- Elmiger estimates they'll sell for $15,930 or so -- as governments require new measures to ensure air travelers don't get sick.

It can't do back flips like Atlas the humanoid robot, nor can it dance or open doors for its friends, like Spot the robotic dog can. Instead, Boston Dynamics' new robot, named Stretch, is going straight to work in a warehouse. Wired: Rolling around on a wheeled base, it's basically a large robotic arm that grabs boxes using vacuum power, and it's designed for tasks like unloading trucks or stacking pallets. If Spot and Atlas are the show-offs in the family, Stretch is the straight-up workhorse. But while these machines all look and move in wildly different ways, they actually share a lot of DNA. Stretch may seem familiar to you, because it's a sort of descendant of another machine that debuted a few years back: Handle. That robot had a similar suction arm, but it balanced on two wheels, like a Segway scooter. Handle would grab a box, scoot backward, turn 90 degrees, and roll away to stack the box somewhere else. It looked neat on video, but in practice the robot needed a lot of room to operate. It could manage unloading boxes from a truck, sure. "But it took a long time," says Kevin Blankespoor, lead of warehouse robotics at Boston Dynamics. "The truck is a pretty confined space. And so for Handle, every time it grabbed the box, it would need to roll back into some space where it could rotate freely without collisions."

Which is all to say: If Handle were a human, it'd be let go. So Boston Dynamics pivoted (sorry) to a new form factor for Stretch that slapped a similar robotic vacuum arm on a base with four wheels. Each wheel can move independently, so the robot can shift side to side or forward and backward to orient itself in, say, the back of a truck. This new base granted Stretch two powers. For one thing, resting on four wheels is a whole lot more energy efficient than trying to constantly balance on two. The same is true for animals: A dog or cat is inherently more stable than a human. (Stretch will get 8 hours of battery life, and clients will have the option to upgrade to a double battery that holds 16 hours of charge.) The second advantage is that Stretch's arm can now pivot around its base, while Handle had to pivot its whole body to turn. Stretch can shift up to 800 boxes an hour.

One of the biggest trends in machine learning right now is text generation. AI systems learn by absorbing billions of words scraped from the internet and generate text in response to a variety of prompts. It sounds simple, but these machines can be put to a wide array of tasks -- from creating fiction, to writing bad code, to letting you chat with historical figures. From a report: The best-known AI text-generator is OpenAI's GPT-3, which the company recently announced is now being used in more than 300 different apps, by "tens of thousands" of developers, and producing 4.5 billion words per day. That's a lot of robot verbiage. This may be an arbitrary milestone for OpenAI to celebrate, but it's also a useful indicator of the growing scale, impact, and commercial potential of AI text generation. OpenAI started life as a nonprofit, but for the last few years, it has been trying to make money with GPT-3 as its first salable product. The company has an exclusivity deal with Microsoft which gives the tech giant unique access to the program's underlying code, but any firm can apply for access to GPT-3's general API and build services on top of it./i

"Fans of science fiction learned last week that the word 'robot' was first used in 1920 — a full three years earlier than originally thought," according to a blog post at Archive.org. They call it "a major SciFi discovery hiding in plain sight": The "massively important yet obvious" change in date was confirmed with a search of the Internet Archive, which has a digitized first edition of the Czech play, R.U.R. Rossum's Universal Robots, published in 1920. There on the title page, hiding in plain sight in an English-language subtitle to the work, is the earliest known use of the word "robot."

This important piece of information is one of many little-known facts captured in the Historical Dictionary of Science Fiction. The project was completed this year by historian Jesse Sheidlower, who credits two things that enabled him to publish this project, decades in the making. "One, we had a pandemic so I had a lot of enforced time at home that I could spend on it," explained Sheidlower. "The second was the existence of the Internet Archive. Because it turns out the Internet Archive has the Pulp Magazine collection that holds almost all the science fiction pulps from this core period...."

The comprehensive online dictionary includes not only definitions, but also how nearly 1,800 sci-fi terms were first used, and their context over time...

The project began nearly twenty years ago at Oxford English Dictionary as the Science Fiction Citations Project.

An anonymous reader quotes a report from Gizmodo: In a mind-bending development, a team of researchers in China have managed to treat brain tumors in mice by delivering drugs to the tissues using microscopic robots. The robots jumped from the mice's bloodstreams into their brains by being coated in E. coli, which tricked the rodents' immune systems into attacking them, absorbing the robots and the cancer-fighting drugs in the process. The team's research was published today in the journal Science Robotics. It comes on the heels of previous research by members of the same team, which saw liquid-coated nanorobots remotely propelled through the jelly-like fluid of the eye. Besides being an obvious recipe for an episode of "The Magic School Bus," the research had obvious applications for ophthalmological research and medical treatments.

The crafts are magnetic, and the researchers use a rotating magnetic field to pull them around remotely. On microscales -- we're talking incremental movements about 1% the width of a hair -- the researchers were able to make the hybrid bio-bots wend paths like in the video game Snake. They're dubbed "neutrobots" because they infiltrate the brain in the casing of neutrophils, a type of white blood cell. It ultimately took Wu's team eight years to actualize the microscopic robot swarms capable of bridging the gap between the rodent bloodstream in the animal's tail, where the bots were injected, and its brain, where gliomas -- tumors that emerge from the brain's glial cells -- resided. Part of the issue is that the mice's white blood cells didn't dig the flavor of the magnetic robots. To overcome that issue, Wu's team coated the bots in bits of E. coli membrane, which the white blood cells easily recognize as a unwelcome invader. That made the robots much more palatable, and the white blood cells enveloped them. From inside those cells, the robots were then able to roll the cells toward the brain; a Trojan horse for the 21st century (in this case, one that benefits the residents of Troy). The neutrobots made it into the brains and were able to deliver the drug directly to the targeted tumors.

sciencehabit shares a report from Science Magazine: The most advanced mind-controlled devices being tested in humans rely on tiny wires inserted into the brain. Now researchers have paved the way for a less invasive option. They've used ultrasound imaging to predict a monkey's intended eye or hand movements -- information that could generate commands for a robotic arm or computer cursor. If the approach can be improved, it may offer people who are paralyzed a new means of controlling prostheses without equipment that penetrates the brain.

A key next step will be to use the computer predictions in real time to guide a robot hand or a cursor. But ultrasound could still guide a robotic arm, as long as a computer could quickly direct the arm's fine motor movements from the user's cue. The team foresees many future improvements to the technique. "The technology is absolutely not at its full potential yet." The study has been published in the journal Neuron.

An anonymous reader quotes a report from the BBC: The size of the Army is to be reduced to 72,500 soldiers by 2025 as part of a move towards drones and cyber warfare. Defence Secretary Ben Wallace said "increased deployability and technological advantage" meant greater effect could be delivered by fewer people. He set out plans for new capabilities such as electronic warfare and drones in a command paper in the Commons. Labour has warned that "size matters" when it comes to defence.

Announcing a major overhaul of the armed forces, Mr Wallace said it marked a shift from "mass mobilization to information age speed," insisting they must be able to "seek out and understand" new threats to the country's security. A cut to the size of the Army had been anticipated -- with a reduction of 10,000 widely trailed. What Defence Secretary Ben Wallace announced was a cut to the target for the number of fully trained people in the Army, from 82,040 today to 72,500 in 2025. The changes set out in the paper -- titled Defence in a Competitive Age -- include 3 billion pounds for new vehicles, long-range rocket systems, drones, electronic warfare and cyber capabilities. The UK is putting more resources into cyber warfare via the creation of the National Cyber Force based in the North West of England. It's also putting more resources ($6.6 billion for research and development) into space that may function similarly to the U.S. Space Force.

A two-armed robot is helping to prepare soba noodles at an eatery at JR Kaihimmakuhari Station in this Chiba city's Mihama Ward (in Japan), capably boiling the noodles in a strainer, rinsing them and then dipping them in iced water. From a report: The Sobaichi Perie Kaihimmakuhari eatery implemented a collaborative cooking system, with the robot cooking the food and employees adding the dipping sauce or soup and toppings. It is apparently the first time for the cooking robot to be introduced in an actual restaurant setting. Soba stands at railway stations usually have to deal with a constant stream of customers and work under time pressure, resulting in a chronic shortage of human resources. [...] The robot fetches soba noodles from a box with one arm, and places it in a strainer. Then with the other arm, it picks up the strainer and boils the noodles for a minute and 40 seconds, rinses off the viscous film on the surface and then dips the noodles in iced water to bring out their firmness. The robot can cook 150 servings in an hour, substituting the work of about one employee.

For almost 40 years, the nation's largest DDT manufacturer disposed of some of its waste product off the coast of Southern California. Now, a research boat is deploying "underwater roombas" to map the ocean floor and assess the damage. Gizmodo reports: In October, people living on Santa Catalina Island, which sits 22 miles (35 kilometers) off the coast of Southern California, were shocked to learn from a Los Angeles Times investigation that a scientist had found leaking barrels of dangerous waste strewn across the ocean floor. Residents had heard rumors that the nation's largest DDT manufacturer, which was based in Los Angeles until 1982, had disposed of some of its waste product near the island, and a huge Superfund lawsuit in 2000 had confirmed the company had disposed waste into sewers that ran into the ocean. But records unearthed by the Times confirmed that the manufacturer had filled up a ship with barrels of DDT-tainted waste and dumped it off the coast once a month for almost 40 years, something unaddressed in the Superfund lawsuit.

So how do you start cleaning up leaking barrels of toxic DDT-laced sludge? Send in the robots. A research boat staffed with a crew and two scientists set off this week on a two-week trip to assess the extent of the damage from the DDT barrels. Eric Terrill of Scripps Institution of Oceanography, who is spearheading the cleanup efforts, described the robots to the Los Angeles Times as "underwater Roombas," which is very cute. These little buddies are tricked out with sonar equipment that will help them collect data from the ocean floor. Suddenly your robotic vacuum is looking a little less cool. The robot's purpose isn't to vacuum, though, but to survey the area littered with barrels of potentially toxic waste. Over the next two weeks, the aquatic robotic explorers will run between 12 and 16 hours a day, mapping out the ocean floor to ascertain the barrels' location and pinpoint areas for future study.

nickwinlund77 shares a report from Bloomberg: There's nothing unusual looking about the 38-foot-long cargo plane that's been flying around Northern California for the past month. But the insides of the Cessna 208 have undergone a sci-fi makeover, resulting in a plane that's been taxiing, taking off, maneuvering in the air, and landing without a pilot. The machinery and software that let it fly on its own come from a startup called Reliable Robotics Corp., which has spent four years working on autonomous flight. The company has a grand total of two planes, but its long-term plan is to fill the sky with pilotless aircraft transporting cargo and passengers.

Reliable's story begins with the self-doubt of its co-founder and Chief Executive Officer Robert Rose. His attempt to become a pilot in college ended for lack of money, but by 2016 he'd earned enough to give the cockpit another shot. Rose, who'd spent his career building autonomous cars and spacecraft for Tesla Inc. and SpaceX, expected that planes would have modernized since he last hopped in a cockpit. But the one he took up had decades-old technology. The shock of how much the flight still relied on a human pilot hit Rose midair as he contemplated his rusty skills and mortality. "My first thought was, 'Wow, it's insane that a private person is allowed to do this,'" he says. "You have all this navigation that you need to manage and all the communications you have to do between other planes and taking instructions from air traffic control. There's layers and layers of stuff. All the while, you are one mistake away from a fatal accident. I kept thinking, 'How is this OK?'"

Rose founded Reliable in 2017 with Juerg Frefel, an old buddy from SpaceX. The pair set up shop in Rose's garage in Los Altos, Calif., planning to make improved autopilot technology. They hoped to tap into the mechanical and positioning systems available on most planes, buy a couple of off-the-shelf sensors, and tie everything together with clever software that could make the types of decisions usually expected of pilots. Each step of the way, however, they discovered the existing gear for sale wasn't resilient enough for the job. "You just could not have a serious conversation about removing the human from the plane with these parts," Rose says. "That meant we had to build."

In a bid to prove that its robot drivers are safer than humans, Waymo simulated dozens of real-world fatal crashes that took place in Arizona over nearly a decade. From a report: The Google spinoff discovered that replacing either vehicle in a two-car crash with its robot-guided minivans would nearly eliminate all deaths, according to data it publicized today. The results are meant to bolster Waymo's case that autonomous vehicles operate more safely than human-driven ones. With millions of people dying in auto crashes globally every year, AV operators are increasingly leaning on this safety case to spur regulators to pass legislation allowing more fully autonomous vehicles on the road.

But that case has been difficult to prove out, thanks to the very limited number of autonomous vehicles operating on public roads today. To provide more statistical support for its argument, Waymo has turned to counterfactuals, or "what if?" scenarios, meant to showcase how its robot vehicles would react in real-world situations. Last year, the company published 6.1 million miles of driving data in 2019 and 2020, including 18 crashes and 29 near-miss collisions. In those incidents where its safety operators took control of the vehicle to avoid a crash, Waymo's engineers simulated what would have happened had the driver not disengaged the vehicle's self-driving system to generate a counterfactual. The company has also made some of its data available to academic researchers.