[venachescu]

This is nerd fever dreaming conspiracy bullshit, if they were really building such scary capable war machines for the defense department they would have been bought long, long ago by a big defense contactor (and likely that would be the last we'd publically hear about it!).

Fact is that Boston Dynamics does one thing, really, really well engineered dynamic locomotion. From what I understand there's very little ML/AI to it, just really good modeling and engineering.

However, no one has quite figured out exactly where this technology will be most useful or practical in the near future. Even (maybe especially) when they were owned by Alphabet.

[clairity]

> Fact is that Boston Dynamics does one thing, really, really well engineered dynamic locomotion. From what I understand there's very little ML/AI to it, just really good modeling and engineering.

as someone who did a bit of graduate research in that area, i would debate the "really, really well engineered" part of that statement. they brute-forced the engineering and developed energetically expensive machines that were great as demos but not practical as products. compare how long one of their robots last vs any legged creature of comparable size, and the poor energetics are obvious.

i would speculate that their company was a bet that battery packs would become light enough yet have a high enough energy density that it's robots could one day become viable products, but it doesn't seem like they're winning that bet.

that's in contrast to the segway, which was a bet that computing power was fast enough to dynamically adjust and balance human scale motion with high dynamic stability. they won the technical bet, but still lost the productization bet.

[varjag]

The energetics of the robots are constrained by size, weight and power requirements of the components on the market. As such sure, mechanical walkers will always be much less energy efficient than wheeled vehicles of the same era. Their competition on the rough terrain however is not Segway but flying drones, which are much less energy efficient than walkers still.

There isn't any particular inefficiency in their walker balancing implementation.

[taneq]

Can you suggest another company that produces legged platforms with similar capabilities and better energy efficiency?

[TeMPOraL]

Maybe there's still merit to BD's approach. The rule is: first make it work, then make it good, then make it fast (i.e. optimize). It's probably easier to find plenty of ways to incrementally improve on a working platform than to dream up those improvements completely from scratch.

[namlem]

Their newest robot, the one with wheels for feet, is quite efficient. You need legs to traverse complex terrain. Adding wheels for efficiency after you've developed decent legs just makes sense.

[Animats]

The military version, the Legged Squad Support System, was tested by the USMC at Quantico. They decided not to buy it. Too noisy for combat, too hard to fix in the field, not that useful to a Marine squad.[1]

The US Army was also trying some exoskeleton designs. The Raytheon XOS [2] was quite capable but needed an external power cable. The Lockheed HULC [3] finally reached a self-powered configuration, but battery life was too short.

None of these will be fielded. Maybe the next generation.

The Army's next big "mobility" buy is a replacement for the HUMMV, an armored truck from Oskosh. Smaller than the MRAP, but a comparable level of protection. Boring, but useful.

[1] http://www.military.com/daily-news/2015/12/22/marine-corps-s...

[2] https://www.youtube.com/watch?v=V87lSB5XWVs

[3] https://www.youtube.com/watch?v=kat8I5UM_Vs

[ethbro]

Strapping a high-density power source to a man (or machine) in a bullet ridden environment sounds like a terrible idea.

I imagine we'll see progress on this front when there's a breakthrough there. Barring that, you get some analog of the rocket equation: power source + fuel requires armor (for survivability) which means more power and fuel is required, etc etc