Toyota Unveils Violin-Playing Robot

eldavojohn writes "Toyota has unveiled a robot that can play the violin. From the article: 'Toyota said it planned to further advance the robot's dexterity to enable it to use tools and assist with domestic duties and nursing and medical care. The robot has 17 joints in both of its hands and arms now.' It seems there have been small — or maybe even strange, impractical — advances in robotics repeatedly with demonstrations of robots performing a specialized task. Are we merely struggling to hard code each human activity as we strive for an all purpose android? Is there a chance artificial intelligence & robotics will ever become generalized enough to make interaction interesting?"

Comments

Robotic vs. Human ability

[AugustZephyr]

I suppose this raises another question regarding the increasingly human attributes of robots. Is something that is "handmade" or "handplayed" by a robot any more or less valuable than its human equivalent? For instance: it may be very impressive that a robot can play pomp and circumstance, but once this becomes more commonplace (as strange it may seem now), does it have more/less value than a human being able to reproduce the same sequence of notes?

Re:Robotic vs. Human ability

[DoubleRing]

Well, it isn't exactly the same thing, but MIDI with good synths has been used to "perfectly" play a composition. Especially for instruments with simple timbres like drums and piano, a synth can sound very close to the real thing. Even with these ways to create a "perfect" performance, people still find a human performance impressive. It's kind of like meeting a person who can compute logarithms in their head, or find all the factors of a number without a calculator. Sure, a computer can do it--it may even do it faster, but I don't think that the fact that a machine can do something makes the feat less impressive when accomplished by a human. I'm still impressed when someone can run a marathon, even if a machine could do it just as easily, if not better. I don't see why there is so much concern that robotic performances will cheapen the value of human performances. Besides, if a programmer is able to write a program that is able to take a piece of music and interpret it beautifully, then it is still a human achievement in that a programmer was brilliant enough to decipher not only decipher the subtle psychology of what makes one performance sound emotional and powerful and the another sound mechanical, but also codify an algorithm that would imitate that interpretation. Kind of like designing a conversation bot to beat the Turing test. It's still a human accomplishment. Remember, the machine is us/ing us.

Re:Very cool, but

[juggleme]

I agree, but it could be used to perfectly reproduce a master performance (given that instrument quality, etc. are equal, which may not be the case.) They may not be able to do it themselves, but they might be able to serve as a new sort of player piano.

Re:Very cool, but

[Derek Loev]

Pretty much anytime a robot tries to do something a human can do we're faced with these type of comments. Ever since the first computer started to play chess (even twenty years ago they weren't much match for an average player, but look at them now)...

they should modify it

[RHSC]

to play guitar hero. I'd love to see machine vs program on "Fire and the Flames"

Re:Very cool, but

[Mex]

Oh, I'm pretty sure eventually they'll figure it out. It's all just chemical reactions, man. And there's already enough music theory out there. So the rules are already (sort of) written. There's been experiments with music-making robots since the 50's. Not huge progress yet, but it will happen.

I do believe, eventually, "creativity" will be programmable.

Re:Very cool, but

[FooAtWFU]

On the contrary. I contend that it is possible that, given adequate dexterity, one could construct a robot that would take a preselected song and render the music in a way which evokes the same emotional qualities from the performance that a skilled human could accomplish. In fact, there's an easy way you can do it without the robot: record a skilled human's performance into an MP3 file and play it back. :P Now, physical reproductions are a lot harder, but entirely plausible.

I further suspect that with adequate research into psychology and music, it would indeed be possible to construct a robot to render most arbitrary scores in a manner emotionally appropriate to that song. Aesthetics are measurable, techniques observable. It would be nontrivial, certainly, to achieve this, but it is not too hard to imagine it being done as early as in, oh, the next fifty years or so. After all, it's not that hard to figure out "minor keys, slow tempo, hey, this might be a sad song", and while there are certainly exceptions and outliers, a little data mining on musical scores could go a signifcant way. (Ooh, now there's an idea for an application of approximate nonnegative matrix factorization! mwuahahhaha.)

Composing great works is the hard problem, because most of those can tie into some rather creative Ideas, and it's harder to come up with those than it is to encode music and gestures and such.

Bad performance

[chickamade]

This is seriously even worse than MIDI. A good violinist can make much rounder/sweeter sound. The arranger who arranged that song for violin didn't do a good job either, because the bowing (slur/detache) is horrible: too much detache. I think my computer MIDI would come out better with a better bowing arrangement.

On the other hand it must be hard to program the robot for all the movement that since if it had been easy they would probably have it play Bach instead.

Damn I was hoping for a robot capable be shown a score and sight-read, actually sight-perform it! I'm a composer BTW.

Re:Article asks silly questions...

[timeOday]

Robots offer an advantage over humans when every repeated action needs to be identical.

That's pretty much like surgery. Most medicine isn't about making up stuff on the spot or putting "your own riff" on a procedure, it's about carrying out a specific procedure in a specific way. Of course it's adapted to the specific variations in each body, but that's not necessarily so hard. A lot of it is like airline pilots. What they do is very easy, but we respect them because it's so important.

Re:Very cool, but

[Fael]

"Geez, what will they think of next, music stored in a digital, binary format? Never happen."

If you're implying that the storage and replication of music is comparable in difficulty to its creation or interpretation, then I can only weep at your ignorance. My computer can show me a scanned image of Monet's Water Lilies, but that doesn't make it an artist.

"Music is all about mathematics."

I'm not sure where you got that idea. Perhaps you're not listening to very good music? Music is, and has always been, about the manipulation of emotion and intellect. Naturally, certain structures and patterns emerge, some of which are mathematically definable. To assert that they are ALL mathematically definable is pretty arrogant. "As any Computer Science student can tell you", there are plenty of problems that are easy to formulate, but algorithmically insoluble.

"We're talking about a COMPUTER here. Math is EVERYTHING it does."

That is the problem.

Consider vibrato on a stringed instrument - a crucial aspect of interpretation, yet only one of many. Because there are an infinitely divisible number of positions on the string (as there are of any finite space), there are an infinite number of theoretically possible vibrati from which a performer is free to choose (even within the space of an inch and a half) - for one fraction of a single note. Obviously, no intelligent performer would use a uniform vibrato for an entire piece, or even an entire phrase - in many cases, not even for an entire note. Similarly, within the timescale of the piece - four minutes, seven minutes, an hour - there are an infinitely divisible number of potential events; in this context, let us say opportunities to vary the vibrato. How do you plot this matrix of potential vibrati, infinite in two axes, in a mathematical simulation? A computer can plot a function through this space. A musician can traverse it at will.