MIT’s self-propelled block robots can now manage basic swarm coordination

MIT’s Computer Science and Artificial Intelligence Laboratory has come up with a clever way for its small cube-like robots, which can move on their own, to communicate and coordinate with one another for self-assembly. The behavior is described by MIT researchers as somewhat “hive-like;” in the video above you can see what they mean by that.

These cube bots can roll across the ground, navigate up and across each other and even jump short distances. And thanks to recent improvements made by the team working on the project, they also can communicate in a basic way using unique barcode identifiers on the faces of the blocks to allow them to identify one another. These 16 blocks can now use their communication system and their ability to move themselves around to perform tasks including producing various shapes, or even following arrows or light signals.

Their current abilities are pretty limited, but the researchers envision a time when a larger and more advanced version of this system could be used to deploy efficiently self-assembling bots that can create structures like bridges, ramps or even staircases for use in disaster response or rescue scenarios. Of course, they also theorize these things might be pretty attractive for more mundane applications, like gaming, too.

This robot relies on human reflexes to keep its balance

As much as we’d like to think that we’re entering an era of autonomous robots, they’re actually still pretty helpless. To keep them from falling down all the time, a human’s fast reflexes could be the solution. But the human has to feel what the robot is feeling — and that’s just what these researchers are testing.

Bipedal robots are excellent in theory for navigating human environments, but naturally are more prone to falling than quadrupedal or wheeled robots. Although they often have sophisticated algorithms that help keep them upright, in some situations those just might not be enough.

As a way to bridge that gap, researchers at MIT and the University of Illinois-Champaign put together a sort of hybrid human-robot system reminiscent of either Pacific Rim or Evangelion, depending on your nerd alignment (or Robot Jox, if you want to go that way).

Although the references may be sci-fi, the need for this kind of thing is real, explained U of I’s João Ramos, co-creator of the system with MIT’s Sangbae Kim.

“We were motivated by watching the 2011 Tohoku, Japan, earthquake, tsunami and subsequent Fukushima Dai-ichi nuclear plant disaster unfold. We thought that if a robot could have entered the power plant after the disaster, things could have ended differently,” Ramos said in a U of I news release.

The robot they created is a small bipedal one they call Little Hermes, and it is hooked up directly to a human operator, who stands on a pressure-sensing plate and wears a force-feedback vest.

hermes

The robot generally follows the operator’s movements, not in a 1:1 sense (especially as the robot is much smaller than a person), but after interpreting those movements in terms of center of gravity and force vectors, makes a corresponding one almost simultaneously. (The MIT writeup goes into a bit more detail, as does the video below.)

Meanwhile, if the robot were to, say, encounter an unexpected slope or obstacle, those forces are conveyed to the operator via the vest. Feeling pressure indicating a leftward lean, the operator will reflexively take a step in that direction using those excellent instincts we animals have developed. Naturally the robot does the same thing and, hopefully, catches itself.

This feedback loop could make on-site rescue robots and others on uncertain footing more reliable. The technology is not limited to legs, though, or even to Little Hermes. The team wants to set up similar feedback systems for feet and hands, so mobility and grip can be further improved.

The team published their work today in the journal Science Robotics.

MIT uses shadows to help autonomous vehicles see around corners

We’re still not at the point where autonomous vehicles systems can best human drivers in all scenarios, but the hope is that eventually, technology being incorporated into self-driving cars will be capable of things humans can’t even fathom – like seeing around corners. There’s been a lot of work and research put into this concept over the years, but MIT’s newest system uses relatively affordable and readily available technology to pull off this seeming magic trick.

MIT researchers (in a research project backed by Toyota Research Institute) created a system that uses minute changes in shadows to predict whether or not a vehicle can expect a moving object to come around a corner, which could be an effective system for use not only in self-driving cars, but also in robots that navigated shared spaces with humans – like autonomous hospital attendants, for instance.

This system employs standard optical cameras, and monitors changes in the strength and intensity of light using a series of computer vision techniques to arrive at a final determination of whether shadows are being projected by moving or stationary objects, and what the path of said object might be.

In testing so far, this method has actually been able to best similar systems already in use that employ LiDAR imaging in place of photographic cameras and that don’t work around corners. In fact, it beats the LiDAR method by over half a second, which is a long time in the world of self-driving vehicles, and could mean the difference between avoiding an accident and, well, not.

For now, though, the experiment is limited: It has only been tested in indoor lighting conditions, for instance, and the team has to do quite a bit of work before they can adapt it to higher speed movement and highly variable outdoor lighting conditions. Still, it’s a promising step and eventually might help autonomous vehicles better anticipate, as well as react to, the movement of pedestrians, cyclists and other cars on the road.

NASA’s VIPER lunar rover will hunt water on the Moon in 2022

NASA is looking for liquid gold on the Moon — not oil, but plain-old water. If we’re going to have a permanent presence there, we’ll need it, so learning as much as we can about it is crucial. That’s why the agency is sending a rover called VIPER to the Moon’s south pole — its first long-term surface mission since 1972.

VIPER, or the Volatiles Investigating Polar Exploration Rover, will touch down in December 2022 if all goes according to plan. Its mission: directly observe and quantify the presence of water in the permanently shadowed polar regions.

These perennially dark areas of the Moon have been collecting water ice for millions of years, since there’s no sunlight to melt or vaporize it. NASA already confirmed the presence of water ice by crashing a probe into the general area, but that’s a bit crude, isn’t it? Better to send a robot in to take some precise measurements.

VIPER will be about the size of a golf cart, and will be equipped with what amounts to prospecting gear. Its Neutron Spectrometer System (mentioned yesterday by NASA Administrator Jim Bridenstine ahead of this announcement) will let the rover detect water beneath the surface.

When it’s over a water deposit, VIPER will deploy… The Regolith and Ice Drill for Exploring New Terrain, or TRIDENT. Definitely the best acronym I’ve encountered this week. TRIDENT is a meter-long drill that will bring up samples for analysis by the rover’s two other instruments, a pair of spectrometers that will evaluate the contents of the soil.

By doing this systematically over a large area, the team hopes to create a map of water deposits below the surface that can be analyzed for larger patterns — perhaps leading to a more systematic understanding of our favorite substance’s presence on the Moon.

waterhunt

A visualization of Moon-based water ice under the surface being mapped by the VIPER rover

The rover is currently in development, as you can see from the pictures at the top — the right image is its “mobility testbed,” which as you might guess lets the team test out how it will get around.

VIPER is a limited-time mission; operating at the poles means there’s no sunlight to harvest with solar panels, so the rover will carry all the power it needs to last about a hundred days there. That’s longer than the U.S. has spent on the Moon’s surface in a long time — although China has for the last few years been actively deploying rovers all over the place.

Interestingly, the rover is planned for deployment via a Commercial Lunar Payload Services contract, meaning one of these companies may be building the lander that takes it from orbit to the surface. Expect to hear more as we get closer to launch.

Hyundai is launching Botride, a robotaxi service in California with Pony.ai and Via

A fleet of electric, autonomous Hyundai Kona crossovers — equipped with a self-driving system from Chinese autonomous startup Pony .ai and Via’s ride-hailing platform, will start shuttling customers on public roads next week.

The robotaxi service called BotRide will operate on public roads in Irvine, California, beginning November 4. This isn’t a driverless service; there will be a human safety driver behind the wheel at all times. But it is one of the few ride-hailing pilots on California roads. Only four companies, AutoX, Pony.ai, Waymo and Zoox have permission to operate a ride-hailing service using autonomous vehicles in the state of the California.

Customers will be able to order rides through a smartphone app, which will direct passengers to nearby stops for pick up and drop off. Via’s expertise is on shared rides, and this platform aims for the same multiple rider goal. Via’s platform handles the on-demand ride-hailing features such as booking, passenger and vehicle assignment and vehicle identification (QR code). Via has two sides to its business. The company operates consumer-facing shuttles in Chicago, Washington, D.C. and New York. It also partners with cities and transportation authorities — and now automakers launching robotaxi services — giving clients access to their platform to deploy their own shuttles.

Hyundai said BotRide is “validating its user experience in preparation for a fully driverless future.” Hyundai didn’t explain when this driverless future might arrive. Whatever this driverless future ends up looking like, Hyundai sees this pilot as a critical marker along the way.

Coverage area of Hyundai robotaxi pilot

Hyundai said it is using BotRide to study consumer behavior in an autonomous ride-sharing environment, according to Christopher Chang, head of business development, strategy and technology division, Hyundai Motor Company .

“The BotRide pilot represents an important step in the deployment and eventual commercialization of a growing new mobility business,” said Daniel Han, manager, Advanced Product Strategy, Hyundai Motor America.

Hyundai might be the household name behind BotRide, but Pony.ai and Via are doing much of the heavy lifting. Pony.ai is a relative newcomer to the AV world, but it has already raised $300 million on a $1.7 billion valuation and locked in partnerships with Toyota and Hyundai.

The company, which has operations in China and California and about 500 employees globally, was founded in late 2016 with backing from Sequoia Capital China, IDG Capital and Legend Capital.

It’s also one of the few autonomous vehicle companies to have both a permit with the California Department of Motor Vehicles to test AVs on public roads and permission from the California Public Utilities Commission to use these vehicles in a ride-hailing service. Under rules established by the CPUC, Pony.ai cannot charge for rides.

NASA’s Mars 2020 rover rests on its own six wheels for the first time

NASA’s Mars 2020 rover will have to operate on its own in a harsh environment, hundred of millions of miles from the nearest mechanic. But for now, it’s still in development at NASA’s Jet Propulsion Lab – and every milestone is an important one. Including supporting its own weight, fully assembled and resting on its own six wheels, which is what the rover managed this week.

This stand-up test is one of many the rover is undergoing, including testing its nuclear-powered engine, its ability to move its wheels, its sensor arrays and navigation systems. The six-wheeled robotic exploration platform is readying for its scheduled July 2020 launch, which will see it sent to the Red Planet to carry on and augment the mission of the Mars Curiosity rover.

Mars2020 rover 2

NASA’s Mars 2020 Rover. Credit: NASA

Curiosity launched in 2011, and landed on Mars in August of 2012. This earlier rover was designed for a two-year mission, but it got an indefinite mission extension in 2012, and it’s still operational after switching computers earlier this year following a crash – a full seven years after its original landing.

The Mars 2020 rover has received a number of upgrades vs. Curiosity, which you’d probably expect given that the team developing the newer rover has the benefit of multiple years of experience running a robotic rover platform on the surface of Mars. Mars 2020 features upgrades like improved environmental durability, and it’ll carry a host of different scientific and research equipment to complement Curiosity’s capabilities.

Elon Musk says Tesla “early access” full self-driving could arrive by end of year

Tesla CEO Elon Musk said on the company’s earnings call today that the company’s full self-driving mode, in a feature-complete release, could arrive as early as the end of this year. That would be made available in an ‘early access’ mode which is essentially a limited beta, and Musk qualified that this isn’t a sure thing.

“While it’s going to be tight, it still does appear that will be at least in limited in early access release of a feature complete self-driving feature this year,” he said on the call.

He added that it’s “not for sure,” but that it “appears to be on track” for a limited private beta by year’s end.

This follows the release of Tesla’s Smart Summon automated parking lot driverless parking lot hailing feature. It allows Tesla owners to call their cars from their parking spots to pick them up from a curbside within the parking lot. The feature has been used plenty of times with mixed results reported from early use, but Musk also said that the company will be releasing an updated version of the software with improvements in the next “week or so.”

The Smart Summon update is an improvement built on the data taken from the “over a million” uses of the feature by Tesla owners already since its release at the end of September.

To make use of the full self-driving mode that Tesla plans to introduce, vehicle owners will have to own the FSD upgrade package, which is a $7,000 upgrade after it increased from $6,000 in August.

Tesla began shipping its new full self-driving computer hardware in all new vehicles beginning in April, moving to its own custom chip. This was to ensure that enabling the FSD feature would be a software-only update, which is something the company had claimed would be possible with a previous generation of self-driving computing hardware, but the challenge has clearly been more difficult than expected – estimated timelines for the feature’s deployment have also slipped multiple times.

Legged lunar rover startup Spacebit taps Latin American partners for Moon mission

UK-based lunar rover startup Spacebit, a company developing robotic exploration hardware for use on the Moon, announced two new partners that will help it develop and finalize its technology ahead of its target mission date of 2021. The Ecuadorian Civilian Space Agency (EXA) and Mexico’s Dereum will be providing the technology that Spacebit will employ on both its deployer and the robot rover it’s preparing for use on the Moon.

This marks the first time that Latin American companies will participate in a mission to the lunar surface, and Spacebit CEO Pavlo Tanasyuk was joined by Dereum CEO Carlos Mariscal and EXA COO Ronnie Nader to talk about the news at the International Astronautical Congress in Washington, D.C.

“We have Ecuador, and Mexico as our technical partners,” Tanasyuk said. “So in addition to this being the first lunar mission from the UK, it also is the first Latin American mission with a consortium of Latin American countries participating along with the UK.”

Both the EXA and Dereum have strong technical chops when it comes to spacecraft and space-based robotics, with the EXA sousing on developing technology that is “efficient, cheap and reliable,” according to Nader, while Dereum’s Mariscal said that his organization is well-known globally for its work on building robots for use in space, with an extensive track record. Their expertise should help a lot in Spacebit’s efforts to build, test and validate its robotic lunar rover, which employs a novel walking system for getting around, whereas all rovers to date have used wheels for transportation.

Spacebit CEO Pavlo Tanasyuk

Spacebit CEO Pavlo Tanasyuk

“We are planning on doing a swarm technology exploration plan, where we have multiple small spider walking rovers deployed from a wheeled mothership, along with being able to have some redundancy and the ability to do 3D LIDAR scanning of the interior  lunar caves and lava tubes,” Tanasyuk said.

“It’s essentially a data as a service business model,” he added, explaining how they’ll seek to monetize the business. “Our primary focus for early missions are to do exploration and mapping of lunar lava tubes to be able to characterize the lunar subsurface environment for potential suitability for future human habitation.”

Spacebit, founded in 2014, is funded privately via Tanasyuk himself, along with a couple of other private investors. He said that his company is fully funded through its first mission, a berth aboard the Peregrine Moon lander being launched by Astrobotic in 2021 (which itself has a price tag of $1.7 million he said). The first mission won’t be an entire swarm, but a single rover sent up as a demonstration unit to prove out its technology.

Volvo creates a dedicated business for autonomous industrial and commercial transport

Volvo Group has established a new dedicated business group focused on autonomous transportation, with a mandate that covers industry segments like mining, ports and moving goods between logistics hubs of all kinds. The vehicle maker has already been active in putting autonomous technology to work in these industries, with self-driving projects including at a few quarries and mines, and in the busy port located at Gothenburg, Sweden.

The company sees demand for this kind of autonomous technology use growing, and decided to establish an entire business unit to address it. The newly-formed group will be called Volvo Autonomous Solutions, and its official mission is to “accelerate the development, commercialization and sales of autonomous transport solutions,” focused on the kind of transportation “where there is a need to move large volumes of goods and material on pre-defeined routes, in receptive flows.”

Their anticipation of the growth of this sector comes in part from direct customer feedback, the automaker notes. It’s seen “significant increase in inquires from customers,” according to a statement from Martin Lundstedt, Volvo Group’s President and CEO.

Officially, Volvo Autonomous Solutions won’t be a formal new business area under its parent company until January 2020, but the company is looking for a new head of the unit already, and it’s clear they see a lot of potential in this bourgeoning market.

Unlike autonomous driving for consumer automobiles, this kind of self-driving for fixed route goods transportation is a nice match to the capabilities of technology as they exist today. These industrial applications eliminate a lot of the chaos and complexity of driving in, say, urban environments and with a lot of other human-driven vehicles on the road, and their routes are predictable and repeatable.

The Station: A new self-driving car startup, Inside Tesla’s V10 software, Lilium’s big round

If you haven’t heard, TechCrunch has officially launched a weekly newsletter dedicated to all the ways people and goods move from Point A to Point B — today and in the future — whether it’s by bike, bus, scooter, car, train, truck, flying car, robotaxi or rocket. Heck, maybe even via hyperloop.

Earlier this year, we piloted a weekly transportation newsletter. Now, we’re back with a new name and a format that will be delivered into your inbox every Saturday morning. We’re calling it The Station, your hub of all things transportation. I’m your host, senior transportation reporter Kirsten Korosec.

Portions of the newsletter will be published as an article on the main site after it has been emailed to subscribers (that’s what you’re reading now). To get everything, you have to sign up. And it’s free. To subscribe, go to our newsletters page and click on The Station.

This isn’t a solo effort. Expect analysis and insight from senior reporter Megan Rose Dickey, who has been covering micromobility. TechCrunch reporter Jake Bright will occasionally provide insight into electric motorcycles, racing and the startup scene in Africa. And then of course, there are other TechCrunch staffers who will weigh in from their stations in the U.S., Europe and Asia.

We love the reader feedback. Keep it coming. Email me at [email protected] to share thoughts, opinions or tips or send a direct message to @kirstenkorosec.

A new autonomous vehicle company on the scene

the station autonomous vehicles1

Deeproute.ai is the newest company to receive a permit from the California Department of Motor Vehicles to test autonomous vehicles on public roads.

Here is what we know so far. The Chinese startup just raised $50 million in a pre-Series A funding round led by Fozun RZ Capital, the Beijing-based venture capital arm of Chinese conglomerate Fosun International. The company has research centers in Shenzhen, Beijing and Silicon Valley and is aiming to build a full self-driving stack that can handle Level 4 automation, a designation by the SAE that means the vehicle can handle all aspects of driving in certain conditions without human intervention.

Deeproute.ai is also a supplier for China’s second-largest automaker Dongfeng Motor, according to TechNode. The startup plans to offer robotaxi services in partnership with Dongfeng Motor for the Military World Games in the city of Wuhan next month.

Snapshot: Tesla Smart Summon

the station electric vehicles1Remember way back in September when Tesla started rolling out its V10 software update? The software release was highly anticipated in large part because it included Smart Summon, an autonomous parking feature that allows owners to use their app to summon their vehicles from a parking space.

We have some insight into the rollout, courtesy of TezLab, a Brooklyn-based startup that developed a free app that’s like a Fitbit for a Tesla vehicle. Tesla owners who download the app can track their efficiency, total trip miles and use it to control certain functions of the vehicle, such as locking and unlocking the doors, and heating and air conditioning. TezLab, which has 20,000 active users and logs more than 1 million events a day, has become a massive repository of Tesla data.

TezLab shared the data set below that shows the ebb and flow of Tesla’s software updates. The X axis shows the date (of every other bar) and a timestamp of midnight. (Because this is a screenshot, you can’t toggle over it to see the time.)

Screen Shot 2019 10 11 at 3.52.53 PM

This data shows when Tesla started pushing out the V10 software as well as when it held it back. The upshot? Notice the pop on September 27. That’s when the public rollout began in earnest, then dipped, then spiked again on October 3 and then dropped for almost a week. That lull followed a slew of social media postings demonstrating and complaining about the Smart Summon feature, suggesting that Tesla slowed the software release.

A geofencing bright spot

Speaking of Smart Summon, you might have seen the Consumer Reports review of the feature. In short, the consumer advocacy group called it “glitchy” and wondered if it offered any benefits to customers. I spoke to CR and learned a bit more. CR notes that Tesla is clear in its manual about the limitations of this beta product. The organization’s criticism is that people don’t have insight into these limitations when they buy the “Full Self-Driving” feature, which costs thousands of dollars. (CEO Elon Musk just announced the price will go up another $1,000 on November 1.)

One encouraging sign is that CR determined that the Smart Summon feature was able (most of the time) to recognize when it was on a public road. Smart Summon is only supposed to be used in private areas. “This is the first we’ve seen Tesla geofence this technology and that is a bright spot,” CR told me.

Deal of the week

money the station

There were plenty of deals in the past week, but the one that stood out — for a variety of reasons — involved German urban air mobility startup Lilium . Editor Ingrid Lunden had the scoop that Lilium has been talking to investors to raise between $400 million and $500 million. The size of this yet-to-be-closed round and who might be investing is what got our attention.

Lilium has already raised more than $100 million in financing from investors, including WeChat owner and Chinese internet giant Tencent, Atomico, which was founded by Skype co-founder Niklas Zennström, and Obvious Ventures, the early-stage VC fund co-founded by Twitter’s Ev Williams. International private banking and asset management group LGT and Freigeist (formerly called e42) are also investors.

TechCrunch is still hunting down details about who might be investing, as well as Lilium’s valuation. (You can always reach out with a tip.)

Lunden was able to ferret out a few important nuggets from sources, including that Tencent is apparently in this latest round and the startup has been pitching new investors since at least this spring. The round has yet to close. Lilium isn’t the only urban air mobility — aka flying cars — startup that been shaking the investor trees for money the past six months. Lilium’s challenge is attempting to raise a bigger round than others in an unproven market.

A little bird

blinky cat bird green

We hear a lot. But we’re not selfish. Let’s share. For the unfamiliar, a little bird is where we pass along insider tips and what we’re hearing or finding from reliable, informed sources in the industry. This isn’t a place for unfounded gossip. Sometimes, like this week, we’re just helping to connect the dots to determine where a company is headed.

Aurora, an autonomous vehicle startup backed by Sequoia Capital and Amazon, published a blog post that lay outs its plans to integrate its self-driving stack into multiple vehicle platforms. Those plans now include long-haul trucks.

Self-driving trucks are so very hot right now. Aurora is banking on its recent acquisition of lidar company Blackmore to give it an edge. Aurora has integrated into a Class 8 truck its self-driving stack known as “Aurora Driver.” We hear that Aurora isn’t announcing any partnerships — at least not now — but it’s signaling a plan to push into this market.

Got a tip or overheard something in the world of transportation? Email me at [email protected] to share thoughts, opinions or tips or send a direct message to @kirstenkorosec.

Keep (self) truckin’

the station semi truck

Ike, the autonomous trucking startup founded by veterans of Apple, Google and Uber Advanced Technologies Group’s self-driving truck program, has always cast itself as the cautious-we’ve-been-around-the-block-already company.

That hasn’t changed. Last week, Ike released a lengthy safety report and accompanying blog post. It’s beefy. But here are a few of the important takeaways. Ike is choosing not to test on public roads after a year of development, unlike most others in the space. Ike has a fleet of four Class 8 trucks outfitted with its self-driving stack as well as a Toyota Prius used for mapping and data collection. The trucks are driven manually, (a second engineer always in the passenger seat) on public roads. The automation system is then tested on a track.

There are strong incentives to demonstrate rapid progress with autonomous vehicle technology, and testing on public roads has been part of that playbook. And Ike’s founders are taking a different path; and we hear that the approach was embraced, not rejected, by investors. 

Screen Shot 2019 10 12 at 7.56.36 AM

In the next issue of the newsletter, check out snippets from an interview with Randol Aikin, the head of systems engineering at Ike. We dig into the company’s approach, which is based on a methodology developed at MIT called Systems Theoretic Process Analysis (STPA) as the foundation for Ike’s product development.

In other AV truck-related news, Kodiak Robotics just hired Jamie Hoffacker as its head of hardware. Hoffacker came from Lyft’s Level 5 self-driving vehicle initiative and also worked on Google’s Street View vehicles. The company tells me that Hoffacker is key to its aim of building a product that can be manufactured, not just a prototype. Check out Hoffacker’s blog post to get his perspective.

Nos vemos la próxima vez.