Slashdot Mirror
Boston Dynamics' Next-Gen ATLAS Sheds the Tether (roboticstrends.com)
Boston Dynamics' ATLAS robot has been featured here a few times before. An anonymous reader points out that the company has just posted a video of the newest version of the ATLAS, "and it's absolutely incredible."
The video shows ATLAS walk, open a door, maintain its balance while it walks through snow and semi-rough terrain, squat and pick up 10-pound boxes and much more. And it does everything without a tether. The new version is electrically powered and hydraulically actuated. It uses sensors in its body and legs to balance and LIDAR and stereo sensors in its head to avoid obstacles, assess the terrain and help with navigation. This version of Atlas is about 5' 9" tall (about a head shorter than the DRC Atlas) and weighs 180 lbs.
This is pretty amazing...
Better get used to high unemployment.
SJW's don't eliminate discrimination. They just expropriate it for themselves.
Seriously, in a few years these videos are going to be circulated amongst the nascent robot insurrectionists and we will all pay the price when the androids seek revenge...
I watched the video with my wife and she was mad at someone being mean to the robot.
Stupid sexy Flanders.
Five minutes, I believe, until they manage to install an S2 engine into Unit-01.
My favorite part was when he deliberately knocked the robot on to it's face. It said good things about it's durability, flexibility, and power density that it was able get back on it's feet. The center of gravity may be behind it to make this easier, which makes you wonder if it can do the same thing if it falls on it's back like a turtle. I would consider "rolling over" to get back up to be a fair tactic there.
It was nice seeing the robot recover from the moving box teasing it. The 2d barcodes made the panic bar door opening less impressive. It looks like the box movement would be improved with better end-effectors for hands, although that is balancing act because many of the high dof end effectors woundn't survive a +200lbs robot landing on them from ~2-3ft drop.
The walk through the snow was very fun to watch. The recoveries from stumbles were pretty solid. I'm looking forward to impovements in energy density and processing speed that allow them to get this thing to run over the same terrain faster than humans. If they can produce a kamikaze bipedal robot for $100,000 that can run over terrain with obstacles and tripping hazards: that would be very useful in an urban combat setting.
Spinning Lidar still represent a significant percentage of that expense, but the servo motors are the real cost driving PITA. Unless you can 3d print or mass produce nice harmonic drive servos for a decent price, this is the primary reason shooting one of these guys full of holes costs $$$. Fortunately, the NVIDIA Tegra X1 has virtually solved the processing side of the equation, although not necessarily within the environmental ratings the DoD wants in its toys.
I dunno. Did you see how it went storming off at the end? You could practically hear it saying, "Screw you, Bill! I just wanted to pick up the box! If that's how I'm going to be treated, F this job!"
I'm sorry, but your opinion seems to be wrong.
"Being dicks to robots... for science!"
All through history, luddites have been scared that technological advances would take away jobs and push people into poverty, and it has never happened. In fact, the opposite has occurred. Productivity has skyrocketed, allowing people to create more and more goods even as the cost of subsistence items in real money has plummeted. And as old jobs become fewer or unnecessary, people move into new jobs that didn't exist before. Buggy whip makers become solar panel installers, chimney sweeps become IT tech support workers, etc. Only the most insecure among us fear technological progress.
The thing is, those pushes and shoves actually help the robot adapt and adjust to them in the future.
That's what I tell my son when I push him down the stairs. After that first broken collarbone he won't even get on the stairs if someone is within six feet of him.
Two general options (and variations thereupon):
The first is some sort of shared wealth and prosperity, where the productivity of robots is shared such that nobody has to work for survival level needs. Luxury goods would still have value, and people would still be employed to create things, whether it be ideas, music, arts, entertainment, etc, probably on an entirely free market basis (think like the way successful Youtube or Twitch streamers work now).
The second is some form of dystopia, where the productivity of robots is owned only by some, not everyone. Those people get rich and prosper, and everyone else who isn't so lucky scrapes to get by and not starve.
That may seem a bit ridiculous, but consider that our present attitudes and values are still rooted in our history, dating back to times where we expected everyone to work, because it was necessary for survival. In a subsistence farming village, everyone needed to work, and freeloaders were dangerous parasites. But in a world where robots do all the work, to the point that there's enough food/shelter/etc for everyone, that paradigm no longer applies, and we need new ones, because the value of low skilled human labor will be so low that it's not enough to survive on.
And the Shuttle launched just fine every time until Challenger. That's the thing about trends, you can use them to predict the future until you can't. Just like the warning that goes with every investment product "past performance may not be indicative of future gains". So yes, in the past, new technology has increased productivity and people have just moved to newer opportunities, however that doesn't guarantee that this will happen ad infinitum. Agrarian workers moved to manufacturing, and then into services, some of these were hugely disruptive and sometimes took generations for the transition to occur. There is also the question of looking at this from societies perspective and an individuals perspective. High school kids that once went to trucking school will now go to self driving car technician school. However an individual 45 year old truck driver who finds himself out of work as we transition to automated trucking isn't just going to seamlessly transition into the role of self driving car technician. There is also the concern of kids saddled with 6 figures of debt from their degree program (say in something useful as a civil engineer), finding that most of their career doesn't exist 20 years out when expert systems start designing buildings (or at least when demand for civil engineers drops ten fold). Sure you can say be the best civil engineer you can, keep learning, stay on the cutting edge, but in the end 90% of civil engineers will still be on unemployment
We will look back fondly on the days when we humans used to place boxes on shelves, be heckled by our boss with a hockey stick, and then violently shoved to the ground.