Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MIT cheetah robot lands the running jump [video]

youtube.com

Post reply on HN
Print view View original

121–130 of 212 posts

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

#121

Post by jmagoon »

DanBC wrote: post #22
xixixao wrote: post #20

Earlier quoted context omitted.

I wish there was no reason for stupid warfare, but: Aren't they better off than the Vietnamese who lived under the fear of Napalm bombardment? (or, for that matter, Japanese fearing the atomic bomb) I don't think that robotics has significant negative impact on warfare (and I wonder whether it has a positive impact).

Yes, in one sense people are better off with drones than they would be with land mines or cluster bombs or "shock and awe" style area-bombing. Those are (pretty clearly, IMO) war crimes. But still, it's useful to be worried about the potential "desensitising effect" of remote warfare. Is someone operating a drone subject to the same psychological pressure to avoid killing other humans as someone pulling a trigger? (T…

Drone operators have the same type of psychological pressure and results as ground troops: http://www.nytimes.com/2013/02/23/us/drone-pilots-found-to-g...

In terms of their superiors, isn't that how warfare has always been?

My guess would be that ground troops replaced by robots would likely still have a pilot with a "finger on the trigger" for a long time. If the reaction is this mixed Hacker News, how do you think extremely conservative military commanders would feel about "AI" controlled soldiers?

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

#122

Post by IgorPartola »

rebootthesystem wrote: post #119

All of this is neat stuff. That said, for some reason I am still bothered by the use of laser range finders. To me it makes it all feel like a parlor trick. The easiest way to produce machines that can be used in "Oh, wow! Look at that!" videos that continue to bring in grants. These robots should use binocular vision and nothing else. Oh, wait a minute, that's hard, isn't it? Yup.

Why should they use binocular vision?

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

#123

Post by kbenson »

Lawtonfogle wrote: post #111
deepnet wrote: 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…

>He calls for a moritorium until we can get a neural net to learn Asimov's 1st Law. Consider the worst things that governments will do to get an advantage. I mean the downright most inhumane things they have actually done. Now given this, what chance is there that they will respect a moratorium on research. If violating basic human rights for a small advantage is part of their MO, then it would be foolish to think th…

I think another important facet of making the technology widely available is that the general public then understands it more, and how to use it effectively and how to mitigate the problems it presents. I suspect the ostrich strategy rarely works out well in the end.

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

#124

Post by snowwrestler »

vlasev wrote: post #31

No one seems to be discussing how this can be improved! Here are a few points: 1. Real cheetahs don't run like that. The action of both pairs of legs is staggered for smoother motion and control. Check this out - https://www.youtube.com/watch?v=131wvVGjZUc 2. Looking at this jumping-over-obstacles video, it seems like the robot is lacking flexibility. The real life cheetah's hind legs go quite a bit underneath in pre…

The biggest difference is that the spine on this robot is not articulated. Most of a cheetah's power for running comes from the strength and flexibility of the muscles along its spine.

It's just hard to beat the density and flexibility of a living mammal with a bunch of servos, chips, and batteries. We probably never will.

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

#125

Post by ionwake »

joeblau wrote: post #83

edit: Spoiler Alert! I just watched Ex-Machina and for some reason, I just pictured the robot running out of the building after its last test without the safety harness and setting itself free.

I waited months to watch this and read your spoiler. I don't think your comment has added any benefit to mankind.

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

#126

Post by kbenson »

posnet wrote: post #24
icebraining wrote: post #14

Earlier quoted context omitted.

using something that's ground-based to impose control? I think we have that, they're called soldiers.

Which leads to the appeal of a mechanized infantry that never gets tired, never gets sick, kills without remorse, follows orders invariantly, doesn't eat or drink, has an upgrade path but most importantly can't be killed only destroyed or broken. Sure the first generation won't replace all soldiers and they may never replace them all. We will need logistics and support people of course. Its not a perfect solution. Bu…

I'm all for this, not just for our soldiers, but also for the remote population. Part of the problem of actual people in these situations is that they fear for their lives, so make decisions based on their own fear and keeping themselves alive. Eventually, robotic soldiers can hopefully be better than human soldiers at identifying a threat, even if it's just because they are programmed to take more time to do so. There will be a lot of incentives to make them as cautious as possible when categorizing civilian and soldiers in the instances where the only threat is to themselves.

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

#127

Post by danielvf »

tgb wrote: post #70
SuddsMcDuff wrote: post #64

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...

DARPA is providing Boston Robotics hardware platforms to some university teams.

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

#128

Post by jotux »

LesZedCB wrote: post #99
deepnet wrote: 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.

I think the only interaction most people have with Asimov's laws is just reading them and thinking they seem reasonable. If people actually read the stories they'd learn that the robots are constantly put into situations that pose exceptions to the laws or force the robots to make decisions that fundamentally break them.

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

#129

Post by shabble »

kaybe wrote: post #114
chinathrow wrote: post #49

Earlier quoted context omitted.

Those expensive machines makes not a single child soldier go away - why should it?

I think the point is that humans are a lot cheaper than machines, as harsh as that is, especially if you do not care about them at all.

I suspect (but cannot point to hard numbers) that machines might actually be cheaper if you are (politically or otherwise) forced to look after your human soldiers to a reasonable standard, especially in 1st world countries.

Consider the initial training expenses, equipment, career-appropriate salary along with possibly reenlistment bonuses, along with (in the worst case) medevac, multiple complex surgeries, and lifelong treatment/disability pension for some injury. Not to mention the logistic costs of transporting them to various places around hte world, and maintaining an acceptable standard of living there.

Per-machine costs would be high, but there's comparatively little training. Maintenance would be expensive, but rehab/repair decisions would be much less politically charged. Not sure how logistics costs would compare - "life-support" is probably lower, but sourcing power & spares might be greater.

I wonder if anyone has done an economic analysis on this sort of thing.

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

#130

Post by shabble »

onion2k wrote: post #27
tugberkk wrote: post #3

Aside from being a great development; I am really scared that robotics is improving this much. It feels like we are creating our own potential enemy.

This is an understandable reaction considering how much like the robots in films it is. It's movement is Terminator-like, perhaps unsurprisingly given what James Cameron was trying to evoke when he directed the film. That slow, juddering, 'unstoppable' machine type of movement reminds us of things that are more powerful than we are - heavy machines, trucks, industrial equipment. If it was more rounded and animalish,…

I imagine as the tech matures, some sort of flexible skin will be developed, to protect the actuators from weather and mud/sand, and to muffle the sound of the motors and valves. If you wanted to get really fancy, eInk squid-like camouflage could be embedded in the outer layer.

Longish fur might actually work quite well for those 2 purposes, they're not entirely dissimilar from the requirements imposed on real animals who evolved it.

Post reply on HN