Wednesday, April 03, 2019

BOSTON DYNAMICS UPGRADES HANDLE.

In the Beginning there was Handle:





And then there came an upgrade to the Handle Logistics:





This Handle is a highly agile legs/wheels centered robot specifically designed for logistics. It is 2m high, weighs 105 kilograms, and can 'handle' a 30-kg payload. It has 10 joints and depth cameras for perception. Handle can build pallet towers, depalletize, and unload trucks in the warehouse.

I'm a bit surprised BD now resorted to a two-legged wheeled robot since it is clear that this kind of robotic dynamism requires constant dynamic counterbalancing. Given current microprocessor speeds I can imagine the software can handle this just fine - it's 'just' constantly re-calculating the equilibrium of robot and payload in function of the changing place in space, and thus momentum, of both. I guess the requirements for reacting mechanically can also easily be met. But what got me wondering is whether this type of configuration does not require an unneccessary power drain. On the videos you can clearly see how the huge pack between Handle's legs - which cannot be anything else than the battery - is constantly lifted up to provide the fitting counterbalance. The energy the battery expends for lifting itself up is energy that cannot be used for hauling payload.

Of course, guys coming up with this kind of technological marvels must be waaaaaaay smarter than I am so I assume they know what they are doing.

Also don't miss this Wired article:



"FOR INTERNET-GOERS, BOSTON Dynamics is that company that uploads insane videos of the humanoid Atlas robot doing backflips, of four-legged SpotMini opening doors and fighting off stick-wielding men, and as of last week, of a Segway-on-mescaline called Handle jetting around picking up and stacking boxes with a vacuum arm. For journalists and industry watchers, however, Boston Dynamics is that company that almost never talks about where all of this work is ultimately headed.

That’s beginning to change. The company is now teasing its ambitions as the four-legged SpotMini nears its commercial release. Today, Boston Dynamics is getting even more explicit about its vision with an announcement that it’s acquired a Silicon Valley startup called Kinema Systems, which builds vision software that helps industrial robot arms manipulate boxes. This acquisition is giving the Handle robot the gray matter it needs to follow SpotMini to market.

One of the biggest obstacles holding robots back has been their limited perception. We humans enjoy a rich constellation of senses that help us navigate our surroundings. Robots need the same, lest they destroy themselves. Go to pick up a box, for example, and you as a human probably don’t think deeply about the lighting and how it may cast shadows that throw off your hand placement.

Kinema’s software—which is robot-agnostic, meaning it already works on a range of robots beyond Handle—helps the machine through all these challenges. “Their system is able to look at a stack of boxes,” says Michael Perry, vice president of business development at Boston Dynamics, “and no matter how ordered or disordered the boxes are, or the markings on top, or the lighting conditions, they're able to figure out which boxes are discrete from each other and to plan a path for grabbing the box.”



and:



"The reason BD is able to riff on its robot shapes with relative ease boils down to one big thing: repurposed software.

When you think Boston Dynamics, you probably don’t first marvel at the code that’s running these machines—BD is famous for its hardware. But Raibert takes issue with that characterization. “I think it's a misconception that we're a hardware company,” he says. “The only reason any of our machines do what they do is because of the controls and perception and the systems that coordinate with the hardware. It's just that our hardware is so strong, that's what makes us look like that.”

Someone, after all, has to program Atlas to do those backflips. SpotMini needs software to autonomously navigate its world. And two-wheeled Handle needs finely tuned control algorithms to keep from falling on its face. BD works out these algorithms across its platforms. “There's a lot of stuff that flows,” says Raibert. “The next group uses a lot and then creates their own stuff, and then that flows back.”


Fascinating!



MFBB.

No comments: