Slashdot Mirror
Honda Creates Walking Robot
ilyah writes: "The ever-crafty Honda engineers have apparently created a robot that can accurately walk on two legs (i.e. just like humans). Take a look at The Honda Japan site -- a Japanese site that has some pictures and videos worth looking at (hint: videos are under linked marked "04"). It's pretty awesome watching that thing walk around." If I remember correctly, they've been working on this for quite some time - like 15 - 20 years, but this is apparently one of the breakthrough steps, pun intended.
When I was in Japan this summer I heard a lecture from Mitsuo Kawato, who I believe is a member of the research team. The general approach used by Kawato is called feed-forward control, and is based on the physiology of the cerebellum. Kawato argued that feed forward control has signifigant speed advantages over feed back models. Rather than botch the model by trying to explain it (I'm a brain guy, not an engineer) I'll just point you to the references: Trends in Cognitive Sciences 2:338-345 (review) Neural Networks 11:1317-1329 (equations here) Current Opinion in Neurobiology 9:718-727 Nature 403:192-195 (human application) By the way, one of the videos he showed during his lecture had the robot hitting tennis balls!
--everytime you learn something a piece of your brain is replaced by something that someone else said
This was posted a while ago, but with a different site. Try this site: http://www.honda-p3.com/ for english text and movies and such.
Stupid people will be persecuted to the fullest extent allowed by law.
- Greatly improved user-robot interface. Last I saw, the robot required a fairly intricate computer interface and some fairly serious developer guidance to work properly. Now, they seem to have the bulk of it hooked up to a wearable PC and game pad. Additionally, the robot is now completely wireless, which I believe wasn't the case earlier this summer. Quite the improvement over the old method.
- Greatly improved motor control software. This model actually moves in a fluid, almost natural way. The turning is vastly improved (the robot used to be able to only execute spot turns) and they seem to pretty much have the basics of the counter-balancing swing down.
- Improved robot design? It appears that they've tweaked the design of the robot somewhat, most noticably in the robot's backpack, which used to tower over it's shoulders like an astronaut's spacesuit. The current model looks much more "approachable" (for lack of a better way of quantifying it) and seems to have a few other cosmetic changes added (the hands, I believe, were less hand-like in the previous model, for example.) I'm not seeing the tech specs readily available in English, so I'll assume that the prototype is pretty much the same physically as the previous one, save for (quite non-trivial) space optimizations and otherwise more modern components. The fundamental design appears the same.
- Overall Humanness. This robot actually moves in a way that I could call human-like. Yes, there are still the herky-jerks, and the arms don't quite seem to swing right, but the movement flows right. It can walk pretty much in whatever fashion it chooses, can vary it's walking pace and step length, can walk sideways and backwards, can "swing" from a side step into a front step, and does it all with stunning grace for a machine. What's more, it's moving fast now--we're talking a brisk walking pace, no more of this ponderous mechanized trudging. The old videos from this summer were impressive because the robot could successfully walk in a straight like, lean to compensate for tilting floors, and navigate up and down staircases without falling over and with minimal programmer intervention. Today, this thing's strutting around like it owns the place.
This is some serious progress from the good folks at Honda. I'm really excited to see what the next version brings.$ man reality
Obliteracy: Words with explosions
The more interesting thing that I got from the special was the robot that *learned* to walk like an infant does. At power up, it is wobly and nervous. As the instructor helps it maintain its balance and catch it falls, the robot's AI (neural networked?) learns from its mistakes and improves. After a few hours, the bi-pedal contraption is able to walk on its own. That is, until it is turned off and its memory gone.
Now we just need to get these things fighting on BattleBots
The Japanese obviously put a lot of effort into encasing the machinery. Every time MIT shows off a robot it's a bunch of wires and cameras dangling everywhere.
I completely disagree. Diverse research makes for better answers. I agree that the problems of poverty, wildlife, etc are more important than the puzzle of a walking robot. However you never know when research in another field will turn out to be very usefull in another field. Science is full of times where the best use for something isn't what it was designed for. Diverse research leads to a larger body of science for the people in the "important" fields to draw on. So this robot research may seem frivouls(sp) to you but the resulting body of knowledge may have something in it to help with micro surgery techniques.
As x approaches total apathy I couldn't care less.
Having discussed extensively design possibilities with the big walker operator and worked a bit on a Walking robot repairs with him while with SRL (www.srl.org), I can attest that the Honda robot is definately an impressive achievement. Stable walking is difficult enough on tripedal and quadropedal robots, and the hacking done at SRL only succeeded in 2 and 3 legged robots, with not much hill-climbing ability, and only moderate speeds. The feedback circuitry and balancing techniques needed for a biped like the Honda robot is, sadly, not yet within reach of even the sophisticated hackers without a ton of money.
The Honda robot qualifies as an "impressive start"... its 2.0km/h speed of the Honda robot is not impressive for a lightweight tri or quad walker, but it is for a bipedal robot of human size.
The fact that it can climb stairs is especially cool, given the extensive rebalancing done every moment in a step, and the feedback sensors needed to read these motions properly.
Certainly there are lifting robots which can hoist many tons, so the 5.0kg/hand weight limit seems skimpy - but not when considering that this machine can allegedly walk and perform complex arm manipulations while holding this weight. Sadly, its continuous runtime before recharge is only 30 minutes, but I suspect later versions will take advantage of increasing innovation in charge/weight ratios in batteries, and perhaps solar panels for space use (an obvious application of these robots would be EVAs for the ISS or other craft).
Cool, in terms of integration with other systems, is the use of wireless ethernet as the comm standard, rather than some proprietary system. This means this robot could be controlled by base-station systems of arbitrary complexity - including a Beowulf cluster running a complex AI system like Webmind. This means that while technology is not quite there yet to put any advanced computational intelligence inside a biped robot, it can be controlled by advanced systems running at fixed-position stations through LAN technology - a good compromise in terms of merging the state-of-the-art in Robotics with AI to try to build towards a better convergence.
Regarding the robustness, it appears that the 25 minutes of runtime is the primary limitation in terms of continuous operation - there is no data I was able to find on failure rates or the fault tolerance of the sensors or computational systems on-board.
As for hacks vs. new general purpose algorithsm... They obviously do not reveal tremendous amounts of details, but suffice it to say that the engineering done to build 3 successive models of bipedal robots that can walk and climb (stairs, hills) represents fundamental work in robot dynamics engineering which, while parameter tweaked for this robot's operations, is certainly applicable (with some tweaks or modifications, as with all engineering techniques) to other bipedal robot applications.
The wireless lan comm technology, improved user interface (over the previous version), and sensor systems are all also certainly reusable in similar robots (indeed, likely also in multi-legged robots).
However, as it is a commercial product AND I do not read Japanese, I was not able to find any papers on specific algorithms to give a more detailed analysis...
Here are some useful resources I did find:
The official site in English
An article about the robot's walking functions
Images of the robot at UIUC
Biped Robots in General
Robodex Robotics Conference
o/~ we are pissed, we are pissed, we have to resist... o/~ - ec8or
Maybe not. "Ashi mo" (which can also be romanized Asimo) means "Legs too!" in Japanese.
Cheers,
-j.
But, on a more serious note: What happens if Honda gets to the point where they produce a robot capable of digging wells and planting crops in underdeveloped, potentially hazardous countries? What happens if Honda manages to develop a robot that can act as a lab assistant, routinely, tirelessly and accurately performing a wide range of menial yet necessary tasks in a lab environment? Sure, it's too advanced to be able to accurately predict something like this coming along today, but the very essence of science is the pursuit of being able to do and understand things we currently cannot do or understand. Today, this thing is just a prototype that can saunter across a studio floor. Another fifty years, it may be able to run for weeks on end with minimal human intervention, able to do a huge array of tasks that would require fairly heavy human intervention today.
Just as the pioneers of computing could have no way of accurately predicting the impact computers would have on the world fifty years later, the Honda engineers can have no way of knowing what will become of their robot in another 50 years. Rest assured, though, that they, like the computing pioneers, are serious scientists and serious dreamers...
$ man reality
Obliteracy: Words with explosions
Salon.com published a review recently.
Lars
__
Reality or nothing.
By the way, I would like to see those new movies but I can see only mpegs on my linux machine. Does anybody know how I can see quicktime movies on linux?
- Biohazar d
- Honda P3
They're both technically Heavyweights as the P3's a StompBot, however, I think that Biohazard's low center of gravity gives him a definate advantage.Build it, and they will come^Hplain.
I'm not sure if i saw the same video as everybody else, but a while ago when i was looking form information on this cool motorcycle (honda X-WING) that is not available outside of japan, i stumbled across a robot video while plowing through the japanese site. In any case, the cool thing i saw was this guy walking up to the robot, putting his hand on it's forhead and pushing it backwards, and it walked backwards to keep it's balance, and then when he stopped pushing it and it swayed, braced itself, and rearanged iself for better balance. It really moved LIKE A PERSON! It was so cool...
---
Play Six Pack Man. I
KILROY!
Is: "Anything that can be used for sex and anything else, will be used for sex".
I can imagine the fake Visa adds already:
Tube of hydraulic fluid: $15
Honda robot: $9000
Your name becomes a sexual verb: Priceless
But can it flail its arms around and say "Danger! Danger Will Robinson!" That is the true mark of a great robot.
Check out this link for a complete English press release: Honda One-Ups Furby
A question to any robotics experts out there... or heck, any mechanical engineer.
Why is walking so hard? It seems to me that the secret is having a balance sensor similar to the inner ear. If it has movable feet, then you use the balance sensor to keep the robot upright. Once you have that, then it seems like it's just a matter of kicking it forward. As long as it keeps one leg moving forward and keeps the other foot adjusting for balance, you should have natural walking motion.
Clearly it's not this easy, otherwise it would have been done long ago. What's wrong with this solution?
--
Sometimes it's best to just let stupid people be stupid.
But can it chew gum at the same time?
The Moore-Murphy Law: The number of things that will go wrong will double every 2 years.
Answers on a postcard please . . . :)
Any sufficiently advanced technology is indistinguishable from a rigged demo
--Andy Finkel (J. Klass?)
Put some breasts on this thing, teach it a few new tricks, and we will have a winner!
Interesting that they choose to name by drawing tribute to Isaac Asimov.
- passion
*agree* on the flamebait poster. I wouldn't have the first idea about biology stuff like cancer research, but I can do the software just fine. So I'll spend my life doing software, thanks all the same. And who says it's not valuable? In 20 years time, when they give you your prosthetic legs to replace the ones you lost in a road accident, be glad they were doing this research!
But as for the "what happens when..?" question above, the answer is: we adapt. The implication is that we need to consider how it's going to affect us b4 we develop it. But we can't, and shouldn't, let that hold up developments which will improve the lives of everyone. The lobby groups were out in force when the car was invented - they reckoned it would spell the end of horses and everyone involved in that. And it did... but that doesn't mean we should have reconsidered allowing cars to be developed.
And BTW, the original cars were merely expensive, unreliable and slow toys. It took a couple of decades from the first working example b4 they were as fast as a horse, and another couple of decades b4 they were as affordable as a horse. And it took several years of work to get that first example working. Compare and contrast to the first human-size walking robot, which took several years to get working, and is still a slow, expensive toy...
Grab.
The fact that it can climb stairs is especially cool, given the extensive rebalancing done every moment in a step, and the feedback sensors needed to read these motions properly.
:)
Well...
You're right, the ability to climb stairs with a bipedal robot is impressive, but when you find out they programmed it specifically for those steps it becomes a little bit less impressive.
The Honda engineers, in fact, admitted that if the steps were changed by only an inch in width the robot wouldn't be able to handle them. Instead of sensing it's environment there, it's just reverting to a subroutine for those steps. The thing that stinks is that they pull it off without anyone knowing. I might go so far as to say that it reeks.
But ya, the fact that they're walking on two legs in the first place is pretty cool. Now if only it didn't walk like a stick was up it's butt.
____
I do research in this field; Honda's robot demo dates back to July, I believe. If you're interested, you can also check out MIT's project, or NASA's project.
In general, these humanoid robots are NOT meant for physical research: building legs, as cool as it is, is not a new thing. Instead, these are research PLATFORMS, designed to test new theories in artificial cognition. The thinking, quite simply, is thus: if we want a robot to act like a human, it has to perceive the world (and interact with it) as a human does. Therefore, you equip it with sensors akin to ours (eyes, ears, touch), program the drivers and such (so that the robot knows it CAN see, CAN hear, CAN touch), and then you teach the hell out of it. Fun stuff!
This is not Honda's first robot project - they have been working on them for almost two decades, and have spent hundreds of millions of dollars in R&D. Earlier versions include the P2 (1996), and the P3 (1997). As an idea of their progress, here are Honda's specifications for the P2 and P3.
They're impressive beasts, but one has to wonder why they've spent nearly a billion dollars on this. For improving mass production techniques? Possibly, but there are surely better ways. As transport of the future? Hardly.
Free Anne Tomlinson!!
In an article off yahoo it appears that Sony too has a walking bot.
As x approaches total apathy I couldn't care less.
They gave it a humaniod torso because the PR value of Yet Another Tethered Insect is marginal.
The real hoax, I think, is that this is a mechanical engineering achievement, not a leap forward in robotics -- notice how smooth the stage was? Adjust the angle of the stairs or put a bump in the floor and watch the thing fall on its ass.
That's not real robotics if it can't handle the real world.
[troll? Anyway.]
No, that was an earlier version: the P3. This is just the latest in a line of Honda robots starting with the P2. The Slashdot article you refer to is concerned with the P3.
It's not terribly clear, probably because it's in Japan, but they are different things.
Free Anne Tomlinson!!