Fighting Android Sparring Partner 111
GeneOff writes "Just in time for Christmas, comes FA1, the fighting android from SDT (Self Defence Technologys.) I loved my Rock-Em, Sock-Em robots I got one year from Santa. But it was tough getting opponents. Well, no more. Here is a hackable real robot that won't whimp out on you." From the article: "... a robot that can jab, hook, and cross, but still keep the violence to a minimum with adjustable difficulty levels. The FA1 can also dodge your punches with "human-like" movements and he should be hanging out on the show floor at CES -- so we'll be sure to challenge him to a round of verbal barbs from a distance."
Richard Pryor (Score:1)
Re:Just in time for Christmas? (Score:1)
What? (Score:3, Funny)
Just in time for Christmas? This may be one of the few times where it would actually be appropriate for the article to be a dupe.
Re:What? (Score:2)
How long? (Score:3, Interesting)
Re:Yeah, the technology is great, but can it fight (Score:1)
Won't SOMEBODY think of the humans?! (Score:4, Funny)
http://en.wikipedia.org/wiki/Three_Laws_of_Roboti
Re:Won't SOMEBODY think of the humans?! (Score:1)
No, because by sacrificing themselves to teach humans self-defense they're protecting humans from harm! And isn't that what robot-man love is all about?
Re:Won't SOMEBODY think of the humans?! (Score:1)
Re: Asimov's Gray Areas (Score:1)
Historically, there are three major gray areas where Asimov's laws break down.
The first is long-term harm/benefit ratios. The robots that Asimov writes about are incapable of seeing long-term benefit (like scientific advancement in exchange for a minute risk of radiation poisoning--see the short Little Lost Robot from the I, Robot collection). So in this case, Asimov's robots would be incapable of striking a human, but they would be capable of acting as a bag-holder.
The second is emotional trauma fr
Re: Asimov's Gray Areas (Score:1)
Re: Asimov's Gray Areas (Score:1)
And third is long term vs. short term human harm. Asimov's "study of potentials" excuse might overcome this test case, but I doubt it. Within a city center, a gigantic weight is suspended over a human being, and set to crush him at T=12 seconds. A nuclear device is primed to go off 5 seconds after the weight crushes the person (T=17). The robot is placed at the midpoint between the two devices and given a top speed such that he is 10 seconds away from each. The robot can save the man, but in doing so the c
See Androids Fighting .... Brad and Janet (Score:2)
Besides, the term "Robots" first appeared in Capek's play R.U.R. [wikipedia.org], where they definitely hadn't thought of Asimov's laws yet.
Might want to rethink some actions (Score:5, Funny)
Re:Might want to rethink some actions (Score:2)
well (Score:1)
Re:well (Score:2, Funny)
Speaking of... (Score:4, Funny)
Re:Speaking of... (Score:1)
Interesting... but... (Score:1, Interesting)
Please, no (Score:1)
Re:Please, no (Score:1)
Re:Please, no (Score:1)
Re:Interesting... but... (Score:2)
Re:Interesting... but... (Score:2)
How can I be of service?
Re:Interesting... but... (Score:1)
Older SF fans might disagree with you (Score:2)
Re:Older SF fans might disagree with you (Score:1)
missing feature (Score:3, Funny)
That's great, but can it find Sarah Connor?
Re:Okay so it can take a beatin (Score:1)
Re:Okay so it can take a beatin (Score:2)
Just in time for Christmas? (Score:3)
Dang! Something's got to be done about the length of the submission queue at Slashdot!
A fighting robot, eh? This reminds me of the old Twilight Zone episode "Steel" (with Lee Marvin).
Re:Just in time for Christmas? (Score:1)
Doubtful (Score:5, Insightful)
1) To develop an "android" with "human-like" combative movements is unlikely at this point in time. The Actroid shown in the videos here [kokoro-dreams.co.jp] is quite advanced in mimicing human motions, but the movements are very jerky and the motor control is very obvious.
2) The previous point leads to another problem. Training with a mechnical dummy is detrimental to gaining actual combat experience. The "android" will , no doubt, move in a series of jerky movements predefined by state machines. A human fighter flows from one move to another. The android can't help replicate real combat unless it has physics and advanced algorithms programmed into it. Also, the android shown in the picture seems to be stationary. Boxing and martial arts is very dynamic, so the android serves more like a game than a serious combat trainer.
3) The article claims that the android can dodge punches. I say that it can't. It takes a fist less than a quarter of a second to travel from the ready position to the opponent's face. The microprocessor needs to do image processing to realize that the fist is moving towards a specific area, which will require many image frames before it can actually determine the fist movements. And even if the microprocessor was able to act fast enough, I haven't seen any motors that can rotate fast enough.
4) Cost. A stepping side-kick has tremedous amount of force. If a kick can knock a human 10 feet back, I doubt that the android can sustain its working condition after numerous attacks. When it breaks down, how much would it cost to get it serviced?
Re:Doubtful (Score:3, Insightful)
The danger of the side kick is not that it can't be dodged easily, but that when it hits, it can do a lot of damage to a person. But that is the key, it is to a person. This is a man made machine. It can easily be built to withstand even the strongest kicks. People aren't all that strong in the grand scheme of things, it is only when you compare people to other people that the strength seems incredible.
of course, I have no
Tricks (Score:2, Informative)
-Image proces
Re:Tricks (Score:2)
For that configuration of robot, either it moves real slow, or if they've geared it to move quickly then it has no force behind it.
You simply can't have high force and high speed that matches what a human can do in that size of a robot with motors of today.
Re:Tricks (Score:2)
For that configuration of robot, either it moves real slow, or if they've geared it to move quickly then it has no force behind it.
You simply can't have high force and high speed that matches what a human can do in that size of a robot with motors of today.
You're arguing a different point. Did you miss the part where he said solenoid? No motor, no gears. High speed, high force. The downside? High energy cost.
Re:Tricks (Score:2)
Re:Doubtful (Score:3, Insightful)
It looks like
Re:Doubtful (Score:1)
I got the impression that it is supposed to be a game... Correct me if I'm wrong.
Re:Doubtful (Score:2)
I have some expirience in 3d tracking and I don't agree. My Nokia 6600 phone with 15 frame/sec camera and 109mhz CPU (without FP
Re:Doubtful (Score:2)
So how exactly are you getting 3D information from a single camera? Are you assuming a known size of the marker or are you comparing successive frames? what is the accuracy of your depth resolution?
A camera is probably not the best way to do this unless you put s
Re:Doubtful (Score:2)
I'm using more complex algorithm, more simple mobile versions could be found here :
http://studierstube.org/handheld_ar/artoolkitplus. php [studierstube.org]
or here
http://staffwww.itn.liu.se/~andhe/UMAR/ [itn.liu.se]
PC version
http://artoolkit.sourceforge.net/ [sourceforge.net]
My version vill be avaliable for download probably in month or two. Dept
Re:Doubtful (Score:2)
Re:Doubtful (Score:2)
Actually I think it would be somehow more simple for boxing, because we don't have to track orientation of the glove, only it's position. For high-contrast glove (like bright red) it would be easy to extract contour from semi-known background, and after that take the geometric center and average radius of the contour for rough approach. And if to put contrast marker(s) on the glove more precis
Re:Doubtful (Score:2)
I agree. However if you are depending on a high contrast glove then that is the same effect as a marker. You are containing the environment and nothing else in the scene can be the same colour as the glove. This is no longer a general scene.
Also if you wanted to know accurate depth, then you have to know the exact size of the glove to do a model match.
In a constrained scene as described probably, not in a general scene.
Re:Doubtful (Score:2)
Not exactly. There shouldn't be object with projection topologically connected to glove - like the shirt of the same color or wall. Separte obect can have the same color. About size you are correct. Of cause it is constrained scene - but we don't want general computer vision algorithm with arbitrary object re
Re:Doubtful (Score:2)
Re:Doubtful (Score:4, Informative)
http://sdtandroids.com/DesktopDefault.aspx?tabinde x=0&tabid=1 [sdtandroids.com]
It is not something to dynamically interact with you during an entire round of fighting, but apparently something that you will program to practice a specific move or punch on. It was designed to give you more realistic interaction and target than a punching bag and to be safer than practicing on a sparing partner.
Re:Doubtful (Score:2)
Re:Doubtful (Score:2)
It's enough to make you wonder why the wing chun people have been training with wooden dummies for freaking ever... you ought to send them your memo.
Re:Doubtful (Score:2)
There are a few reasons why I like this robot, and had considered the idea myself before:
1) To develop an "android" with "human-like" combative movements is unlikely at this point in time. The Actroid shown in the videos here is quite advanced in mimicing human motions, but the movements are very jerky and the motor control is very obvious.
I have trained for 9 years in Wing Chun, and one of my training aids has been a wooden dummy. It does not
Re:Doubtful (Score:2)
Sparring is more dynamic than wooden dummies. The wooden dummy does not provide the user with actual combat experience. The wooden dummy trains form, speed, and reaction. I'm sure your Sifu will agree with me. Regardless, the product is being advertised as an alternative to a sparring partner, which I disagree with.
I disagree. No matter how fast you may think your fists are, that microprocessor is considerably
Re:Doubtful (Score:2)
I agree that it cannot fully replace a human sparring partner, maybe someday, but certanly not now. The wooden dummy does train exactly what you mention, I also find that it trains power in techn
Re:Doubtful (Score:2)
The technique you cited here is motion capture. However, there isn't any slow external device dependencies with recording coordinates from a few markers. It is also true that
Re:Doubtful (Score:2)
Soleno
Hacking an mechanical punching bag? (Score:1)
Oh come on, (Score:2)
Ok then I will.
I'd hit it!
WTF (Score:3, Interesting)
Specifications
Height:
Weight:
Power Supply:
Materials:
My apologies if I'm missing something, but this looks like more of a proposal than a viable product.
Damn (Score:1)
Damn ass-kicking robots!
the real test of a boxing robot (Score:2)
new cure for spam? (Score:2)
"Fighting Android Spamfilter 1 is out there. It can't be bargained with. It can't be reasoned with. It doesn't feel pity, or remorse, or fear. Ant it absolutely will not stop, ever, until the spammer is dead."
I'll buy two.
IN SOVIET RUSSIA... (Score:1)
Where's My Fencing 'Bot? (Score:2)
Steel (Score:1)
BoxBoxRevolution? (Score:1)
Invasion! (Score:2, Interesting)
Re:Invasion! (Score:1)
What I want to know... (Score:1)
Why aren't we deploying thousands of these to Iraq? With an army of war-bots over there, we could bring all the kids home, no excuses.
Spamming (Score:1)
"Technologys?" (Score:1, Funny)
Re:"Technologys?" (Score:1)
Re:"Technologys?" (Score:1)
I'm surprised that you didn't catch the use of the fictional word "whimp", as in, Here is a hackable real robot that won't whimp out on you. I do believe that Zonk meant wimp [reference.com].
Come on, people. Both of these could have been caught by running the text through a spell check. I'm sure your favorite open-source Office program or the text editor that comes with OSX has a decent one built in.
I don't get it (Score:1)
I can just see it... (Score:2)
They rebelled.
They evolved.
They look and feel human.
Some are programmed to think they are human.
There are many copies.
And they have a plan.
Re:I can just see it... (Score:1)
Imagine what they'll do with your girlfriend.
Wait... What if one IS your girlfriend!
Dune (Score:1)
Re:Dune (Score:1)
Re:Dune (Score:1)
Re:Dune (Score:1)
Re:Dune (Score:1)
puh... (Score:2)
Something like that would be fun to spar against when doing technique work, I guess, though it will eventually get boring when you realize blood and teeth don't fly from an android...
What kind of Martial Arts? (Score:1)
Sparring Partner?!?! (Score:1)
Tragic, yet true... (Score:1)