AI News, Earthbound Robots Today Need to Take Flight

Earthbound Robots Today Need to Take Flight

The DARPA Robotics Challenge this past summer showcased how far humanoid robots have come—but also how far they have yet to go before they can tackle real-world practical applications.

Aerial drones like quadcopters and octocopters have in just the past few years emerged as a viable industrial and consumer product with substantial maneuverability, versatility, and durability.

While a few research groups today have begun exploring dexterous drone maneuvers like building structures, grabbing things on the ground, andsnagging an object mid-flight like an eagle catching a fish, the field is still wide open.

Considering how rapidly both lightweight robotic arms and drones are maturing, there are reasons to suspect $10.6 billion is a conservative estimate, especially as the concept of a dexterous drone gains popularity and more companies decide to pursue this technology.

NASA’s Assistive Free-Flyer (AFF) is a lightweight flying robotic arm that maneuvers, manipulates, and perches in microgravity for ISS applications like maintenance, human assistance, and remote operation of scientific experiments.

Though this new technology is still developing, we’ve already been approached by a customer with a large real-world application for dexterous drones—one whose solution might be generalizable across multiple industries and fields.

Its problem involves inspection of outdoor power lines, requiring sensors to be placed very close to a line or transformer or other hard-to-reach asset suspended in the air.

As robotic arms continue to get lighter and drone lift capabilities continue to improve, the biggest remaining challenge for the dexterous drone will be software.

Perhaps just as with the now rapidly developing commercial spaceflight and personal genome industries, an X-Prize-like dexterous drone contest could be a strategic next step to spur innovation.

Search and rescue, home healthcare, eldercare, forestry, agriculture, manufacturing, education, research, and security are just a few of the industries that stand to benefit once mainstream robotics realizes they’re still standing on the ground for no good reason.

Freedreno Linux Graphics Drivers and Embedded Android for Snapdragon™ Based Inforce Computing Products at the ELC this Week

We strongly believe that the Inforce 6501 Micro SOM will enable the design of sophisticated embedded products with capabilities and tiny form factors unheard of before. Early adopters of the Inforce 6501 Micro SOM are working on some of the most coolest embedded products yet to come.

So, to share my excitement about the new micro SOM, I’d like to list a few stand-out features: If you are designing the next great head-mounted display for an industrial hands-free computing application that requires support for multiple cameras, displays, and excellent image signal processors, the Inforce 6501 Micro SOM could be a great fit.

The miniaturization of the compute module will help designers integrate the latest mobile applications processors into connected portable medical imaging instruments, improving image resolution significantly and enabling faster time to results.

Microspines Make It Easy for Drones to Perch on Walls and Ceilings

Perching allows a quadrotor to shut down its power-hungry motors and let its sensors get to work acquiring data over an extended period of time, tracking parameters like the stability of a building after an earthquake, the nocturnal activity of a jaguar, or enemy troop movements.

To test out this new perching technique, Hao built a gripping system that, while unable to climb like SCAMP, has the advantage of being centrally located and capable of attaching to an inverted surface like a ceiling (a useful feature when you want to get your robot out of the rain).

After some trial and error, Hao found that he could perch successfully by simply flying the quadrotor straight into the wall: as long as the quadrotor is moving at a reasonable pace and is pitched forward (usually the case when flying forward) and squared up with the target surface, the rotors reliably bring the mechanism into contact to engage the wall using an opposed grip.

As Hao explains it, “the opposed-grip strategy for microspines is just like a human hand grasping a bottle of water, except that while humans require some macroscopic curvature to get our fingers around both sides of an object, the microspines can go deep into the micro-features of a rough surface and latch on those tiny bumps and pits.” When the frequency of small bumps and pits is high, as with stucco or cinderblock, the grip is more reliable than on surfaces like polished concrete.

The quadrotor then pivots on the tail spines backward away from the surface, and can fly away.” Speaking about challenges and future ways to address them, Hao says that, “even if the perching strategy is robust, the quadrotor can still fail to perch due to improper choices of target surfaces.

While we have achieved robust perching failure detection and recovery for indoor environments, we will investigate failure recoveries for outdoor applications, possibly with wind disturbances and surface uncertainties.” We are also interested in pursuing new gripping strategies and possibly combining microspines with dry adhesives to stick to a larger range of surfaces.

For real, outdoors: SCAMP robot can fly, perch, climb

Roboticists, however, are as focused on small robots that can function and go where the big robots cannot.

Smaller robots are robust in dealing with impacts, more capable of rapid orientation changes, and can achieve higher adhesive forces relative to their size.

'Fundamental scaling laws tend to increase the ratio of surface area to volume as size decreases, meaning that smaller robots (even primarily terrestrial ones) can interact meaningfully with the air.'

It's capable of flying, perching, climbing, recovering from failure, and taking off—using only onboard sensing and computations—they can go where Big Dog and super-sized Atlas can't.

On the lab website they talked about SCAMP, the new member of their family of bio inspired robots, calling the result 'a robot that's part woodpecker, part Daddy long-legs, and part hummingbird.'

Pope detailed its climbing mechanism, using 'one high torque-density servo to drive long steps up the wall, and one even smaller servo to actuate motion towards and away from the wall.

In effect, we've taken our 9-gram micro glass climber, modified it for speed instead of load capability, given it an extra servo to handle two-dimensional surface profiles, outfitted it with microspines, and strapped it to a tiny quadrotor.'

You Probably Shouldn't Expect City Repairing Drones Any Time Soon

The University of Leeds has been awarded £4.2 million to lead part of a national infrastructure research project in the U.K.

with the vision of using small robots to create “self-repairing cities.” The general idea is to create swarms of small robots that will be able to zip around cities, keeping out of the way of people while proactively identifying weak infrastructure and making repairs before anything actually goes wrong.

This award is part of a larger national initiative to explore “how new ways of using robotics and autonomous systems can restore the balance between engineered and natural systems in the cities of the future.” This sounds awesome, and technological optimism is great, but it’s also important to temper expectations with reality, and avoid getting swept up in the hype of a press release.

Like, that “of the future” phrase should immediately make you suspicious, because of a.) its rampant overuse in headlines by lazy tech bloggers b.) its inherently nonspecific nature.

According to the press release, “the researchers will initially develop new robot designs and technologies in three areas”: •“Perch and Repair” – research to develop drones that can perch, like birds, on structures at height and perform repair tasks, such as repairing street lights.

It seems like it might be more plausible to develop a mobile robotic boom lift: you wouldn’t have to worry about perching or stability or payload, and you could stick a pair of nice robot arms at the top along with a bunch of sensors and whatever else you might need to do repairs.

You’d either be asking it to navigate at low altitude through a highly complex and dangerous urban environment, or you’d have to invent some kind of sensor system that could locate and analyze a dark hole in a dark road from an improbably long distance.

For example, the Georgia Tech Research Institute has been developing an “Automated Pavement Crack Detection and Sealing System.” It’s a robotic trailer that gets towed by a (manned) truck, and it’s able to detect and repair cracks in asphalt continuously at 3 mph.

DARPA Autonomous Robotic Manipulation (ARM) - Phase 1

DARPA's Autonomous Robotic Manipulation (ARM) program is developing software to perform human-level tasks quickly and with minimal direction. This video shows the ARM robot performing 18...