Boston Dynamics is amazingly impressive as always. But I can't help but feel that they are a lot like the people doing computer vision with hand-written features back in the day. It seems inevitable to me that The Bitter Lesson is coming for their control theory approach. (<a href="http://www.incompleteideas.net/IncIdeas/BitterLesson.html" rel="nofollow">http://www.incompleteideas.net/IncIdeas/BitterLesson.html</a>)<p>Possibly the reason it hasn't happened yet is the inaccessibility of robot hardware; nobody else can try different approaches to compete because nobody else has anything like Atlas. Maybe that moat can keep them ahead for a long time, but if the hardware ever becomes cheap enough for real applications, it will be cheap enough for plenty of competition. They will have to adopt more ML methods or be disrupted. Of course maybe they already are, it's not like I actually know how their stuff works in detail, but consensus seems to be that it's still mostly control theory in there.
Jackie Chan, the HK actor, filmmaker, martial artist, and stuntman, ended films with a blooper real. It showed stunts being practiced, and failing, with injuries. A reality check, a "what you've seen today was staged", a "don't think this was real, and then make poor life choices". I liked the integrity of that.<p>Lots of people only see BD's demo videos, and not their making-of videos. Or don't have the expertise to interpret those. So each time BD does another demo video, I think of Chan's films, and wonder if BD might do better.
people are saying this is "fake" because the overall motions were programmed ahead of time.<p>However, picking stuff up perfectly, placing it, and jumping, just using sensors - which is what this is really illustrating - is not that fake to me.<p>I could imagine this robot being used by airlines to move baggage. A confined set of pre-programmed movements with the only variable being the luggage on a cart, and a human supervisor. It reduced the back-breaking task of moving luggage to a just a normal "stand there and press buttons" type of job. Easier to higher for, maintain that crew member, and less injuries to baggage handlers.
I think for atlas (and similar robots) to be widely useful[1], you basically need AGI. You need to be able to explain it the task with words as you would a human, and be able to do it by itself. Otherwise if it requires a significant effort to program each task, it's just easier to have a human. If the task is very narrow, you might as well use traditional robotics.<p>I think the current hardware is more than enough to replace a human for a huge number of tasks, if it had AGI capabilities.<p>[1] Useful outside of niche scenarios, or scenarios where you MUST use a robot because or safety or similar.
I wish Boston Dynamics would put some googly eyes on their robots or find some Japanese engineers to help design them or something. The Skynet vibes from their videos are always off the charts.
This robot might have a better box jump than me.<p>I want to see a comparison between it and some professional athletes, I think it can seriously compete with them now. I can't wait for the day we have robot (american) football and boxing
Something I like to understand:<p>Is every single movement pre-programmed? Or does the Atlas interpret more general commands, such as "move to point b, grab rectangular object a, move to point c, throw object a to position d"?
AI and robotics are progressing way too fast.<p>I have 30-35 years of productive work life left. I worry if I’ll ever be able to work all those 35 years.
That's impressive. Although, like their previous dancing video, it looks choreographed.<p>The problem with building humanoid robots is finding a sugar daddy to pay for them. Nobody makes money at this. A few companies have reached the point of having a saleable research product. There's Nao. Sony had something. You can buy those on eBay. Boston Dynamics has had a 40 year string of sugar daddies - DARPA, Google, Softbank, and now Hyundai.<p>Their electric powered dog robot is more useful. Good mobility, not too heavy, useful for going into trouble spots and looking around. Especially since it can open doors,
which small flying drones cannot do.<p>Today you can put a good sensor suite, good batteries, and good actuators into a reasonably priced package, for used-car values of reasonably priced. There are hobbyist humanoids, but they usually suffer from being built with R/C servo actuators, which are not good devices when you need springy legs.
Is the two leg robot good because it will look like a human or there are real advantages? The 4 leg dog looks more useful, I wonder though if 3 or 6 legs might be better but for some reasons they're trying to copy nature.
How long until Construction Bot can build me a house?<p>I wonder what the programming workflow was comprised of to make the robot do all the moves in this video.<p>Edit: Thanks trekkie1024, I'd watched bits of it but this confirms that the process involves choreographing every little detail. Guess it'll be awhile before generalized solutions become even a remote possibility. Could be a long while.
Would be interesting to combine a Boston Dynamics-type robot with (1) a GPT-like language model, (2) deep learning algorithms that analyze human movement (a la Dall-E but for human motion rather than images), and (3) text-to-speech, so that you can say "dance like a child" and it can generate a child-like dance.
Seeing the movement so fluid, I am wondering whether there is intentional "nudge" of the way it moves to have certain feels other than just optimal mechanically. Of course excluding those flips.
Based on this video and Moore's Law, I can predict that robot movers (moving you from one dwelling to another) WILL be a thing. Billed only for (robot-count) x (time spent), so high-rises with elevators will be cheaper than those without. Load up the (probably-) robotic vehicle(s) and off goes your stuff. One stays behind and switches to housecleaning mode. Optionally they can leave your mother-in-law behind too :)
I think I'll just ask my (human) grunt coworker to hand me my tools, a man who:<p>1. is cheap at $11/hr<p>2. is voice-activated (with no pre-programming required!)<p>3. is much better company<p>...but thanks.
A VC once told me that the best thing that Boston Dynamics makes are viral videos. Founded in 1992 with three major corporate owners who couldn't figure out how to monetize their R&D. As a University lab it would be grant funded.
"The dream of humanoids is that they should be able to do all the things that we do, right?" "we" is a stretch here, since the speaker has never worked at any of the activities their robot can play-act at doing.
Are there any solid examples of production uses of these bots that are as impressive as the demos?<p>I’ve been completely blown away by years of these amazing demos. But I don’t think I’m aware of one real world example.
Every time this robot does a little more, there's another minimum wage job it can replace. 24 hrs and a multi-year financing deal with service, no social security tax, immigration concerns, theft concerns, long spans of unavailability, or sexual harassment lawsuits -- it doesn't take that much to replace some jobs. People aren't just expensive, they're complicated. It also doesn't seem to need building or equipment changes, so the robot can show up as soon as it's convenient.<p>Imagine McDonald's specializing these for line cook positions and providing financing to franchises.<p>Or an autonomous truck with one of these in the back to load/unload.
Given all the hoopla lately that self-driving cars aren't really and demos are staged, isn't it realistic to believe truly autonomous robots are a decade away?
First thought: if I get in the path of the robot I could get seriously damaged. Somehow I do know that when there is machinery around I need to keep distance and be careful. When it comes to robots, since they have human shape and human behaviour, my senses are not in an "alert" state. I guess we'll have to learn and teach our kids "Hey! Be careful! There is a robot around"
BD is making breakthroughs. Son/Softbank selling it to Hyundai will be one of the biggest tip to the Korean manufacturing scene. I am sure Elon Musk would have rather bought BD (40 times over) instead of burning $44B on Twitter. It’s also why he faked his stupid robot launch shortly after the BD acquisition.
Money would have perhaps been spent better if Elon bought BD instead. These robots would make excellent workers to prep Mars for colonization and beyond.
Cool video for sure.<p>Wasn’t there a post the other day about Tesla’s self driving video was staged since it was the best take on multiple attempts?<p>Does anyone think this was not “staged” and carefully preprogrammed for a specific demo?<p>Not that it’s not impressive but still. I can’t have “staged” robots in my warehouse.