Live data from Hacker News

MIT cheetah robot lands the running jump [video]

youtube.com

91–100 of 212 posts

Re: MIT cheetah robot lands the running jump [video]

#91
post #70

Earlier quoted context omitted.

It speaks volumes about their engineering principles - KISS is alive and well at Boston Dynamics :)

Is this related to Boston Dynamics? The work looks very similar, of course, but I don't see their name associated to it. According to this article, Boston Dynamics has it's own "Cheetah" http://spectrum.ieee.org/automaton/robotics/robotics-hardwar...

Good catch - I just assumed it was related to Boston Dynamics because the tech looks so similar. Rookie error.

Re: MIT cheetah robot lands the running jump [video]

#92
post #84

The left and right front/hind legs moving in sync looks unnatural. I wonder if this is ultimately the best way to distribute weight and balance of a four-legged object, and why living four-legged creatures do not run like this? Alternatively, would it be better if the robots also ran more life-like, or is there a benefit (besides the ease and simplicity of engineering the physics) to the robots running like this? I.e…

this is how cheetahs run http://giphy.com/gifs/animal-running-7lz6nPd56aHh6

Actually, if you slow it down, the left/right legs are stil not quite perfectly in sync (at least not in this case):

https://www.youtube.com/watch?v=NuyeVN7PuTM

Re: MIT cheetah robot lands the running jump [video]

#93
post #88

Stuart Russel of AI a Modern Approach fame ( with Norvig ) asks us to consider the ethics of AI research - killer robotics, & hunter drones. http://www.nature.com/news/robotics-ethics-of-artificial-int... He calls for a moritorium until we can get a neural net to learn Asimov's 1st Law. Should the self driving car swerve into you to avoid greater moral hazard ? Humour aside as researchers and robotocists do we have a…

I would believe there to be a significant, non-zero risk that in the R&D process of developing a 1st law neural net, a malicious neural net is created first.

Re: MIT cheetah robot lands the running jump [video]

#94
post #28

Earlier quoted context omitted.

Military research is extremely important. The use of military tech in civilian applications is the reason for a lot of stuff we use daily, as I'm sure you know.

If we had less war on this world, I would be glad to have a few stuff less we use daily. Seriously.

In a peaceful world, advanced military tech would be solely used as a metric of a country's progress and a deterrent in the worst case. That's my opinion at least.

Re: MIT cheetah robot lands the running jump [video]

#95
post #28

DARPA again. Great to see more money flowing into military research. Irony off.

Military research is extremely important. The use of military tech in civilian applications is the reason for a lot of stuff we use daily, as I'm sure you know.

As a followup, I'm a heavy proponent of military research. I'm planning to somehow start a research lab or something (think MIT's Lincoln Lab) in my home country Tunisia. Now that we have democracy, it's time to build our own infrastructure and industries, and I think military should be at the forefront of such a movement.

There's still ways to go.. I still need to finish up my BSc, get a PhD in EE, and finally gain solid experience abroad :)

Re: MIT cheetah robot lands the running jump [video]

#96
post #73

Earlier quoted context omitted.

Not enough peace-loving people to vote for a NASA-science-centric government vs the Military-Industrial government we already have.

I'd say that even if there was, that message wouldn't get through. There are many reasons that people vote for one party over another, there's nowhere on a ballot paper to indicate why the vote is being cast. If you were running a political party, the most logical assumption to make (in the absence of richer feedback) was that the people that voted for you did so because they liked your manifesto and/or believed you'…

Everyone has an opportunity to vote for more than just a party. There are primary elections where specific candidates with specific policy positions can be selected. Unfortunately, most voters don't bother getting involved with the primaries so we end up with candidates that are selected by the "establishment".

In many states, there is an opportunity for direct democracy to have an effect. Specific initiatives are put on the ballot. In practice, though, specific ballot initiatives are still implemented by the same politicians that tend to bend things to their will anyway.

Re: MIT cheetah robot lands the running jump [video]

#97

The left and right front/hind legs moving in sync looks unnatural. I wonder if this is ultimately the best way to distribute weight and balance of a four-legged object, and why living four-legged creatures do not run like this? Alternatively, would it be better if the robots also ran more life-like, or is there a benefit (besides the ease and simplicity of engineering the physics) to the robots running like this? I.e…

Rabbits run (or is it hop?) like that - front paws side by side, rear paws side by side.

Re: MIT cheetah robot lands the running jump [video]

#98

The left and right front/hind legs moving in sync looks unnatural. I wonder if this is ultimately the best way to distribute weight and balance of a four-legged object, and why living four-legged creatures do not run like this? Alternatively, would it be better if the robots also ran more life-like, or is there a benefit (besides the ease and simplicity of engineering the physics) to the robots running like this? I.e…

I noticed the opposite in this one:

https://www.youtube.com/watch?v=wE3fmFTtP9g

Which is to say, it looks more natural and more balanced with the legs out of sync.

Re: MIT cheetah robot lands the running jump [video]

#99
post #88

Stuart Russel of AI a Modern Approach fame ( with Norvig ) asks us to consider the ethics of AI research - killer robotics, & hunter drones. http://www.nature.com/news/robotics-ethics-of-artificial-int... He calls for a moritorium until we can get a neural net to learn Asimov's 1st Law. Should the self driving car swerve into you to avoid greater moral hazard ? Humour aside as researchers and robotocists do we have a…

I thought the whole point of Asimov's exploration of his three laws was that they were fundamentally insufficient for any real ethical security.

Re: MIT cheetah robot lands the running jump [video]

#100
post #6

Earlier quoted context omitted.

> this is no different Creating something with our knowledge and the ability to learn ever faster than us is very different.

Yes, but this robot is not that. It's not even a step in that direction.

Until you have achieve the desired mobility, then tweak it to walk upright instead of using 4 legs, and insert a Watson enabled chip into it.
Post reply on HN