Hacker News Reader

Comment by pmohun | Hacker News Reader

Fascinating:

"We observed that for precision grasps, such as the Tip Pinch grasp, Dactyl uses the thumb and little finger. Humans tend to use the thumb and either the index or middle finger instead. However, the robot hand’s little finger is more flexible due to an extra degree of freedom, which may explain why Dactyl prefers it. This means that Dactyl can rediscover grasps found in humans, but adapt them to better fit the limitations and abilities of its own body."

The learning of "emergent" behavior, specifically when it creates improvements to natural human motion is one of the main reasons why this type of work is so important. Similar to the way that we imitate design from nature (e.g. wings, suction cups), we can now accelerate development by observing how the bots perform the task in a variety of environments

View on HN

It's a really cool phenomena, it also means we have to make our simulations better. These sorts of RL algorithms are so good at finding "exploits" in the physics engine they are in that help them "cheat" sometimes, compared to what the researcher wanted.

I agree, but FWIW in the linked work they did randomize some of the engine parameters during training to avoid fitting too much to a specific set of assumptions. Certainly though more accurate simulations, as long as they were still fast to compute, would be very useful!

yeah, I think a big reason why they needed to do randomization in the first place is because of inaccuracies in the simulation compared to the real world. And the extra randomization required almost two orders of magnitude more training time!

otoh, maybe finding "exploits" is all we ever do. I don't grip with my thumb and little finger because it hurts the back of my hand, but that isn't a problem for Dactyl.

Sure but we want to find exploits in the physical universe not in the approximation that we call a physics engine.

This is always true, by using the real universe as the simulation environment, the exploits are applicable.

This means that Dactyl can rediscover grasps found in humans, but adapt them to better fit the limitations and abilities of its own body.

Then why not evolve commensurate dexterity with mechanically simpler manipulators than a human hand? I'd bet that a robot with 4 arms with 4 different specialist manipulators and a few specialist tools (like a generalized screw-threading tool) could eventually be more efficient than a human with 2 human arms. You can even see this happening in real life, powered by human brains. The kind of dexterity people can get out of a crude instrument like a backhoe is very impressive.

The simpler device will always have an economic advantage.

The simpler device might or might not have an economic advantage. There are a lot of variables.

A backhoe is actually very complex - the simple device is a stick. A thousand humans with a stick can do as much work in a week as a single human with a backhoe can do in a day. It only takes a few weeks to pay off the more complex backhoe. Of course your humans can use their bare hands for a further reduction in productivity.

A backhoe is less complex than a horizontal drill, and the drill is less versatile overall. However the drill can go under a structure without harming it which can be a big economic win. If you are just doing a shallow pipe through an open field they are fairly competitive in price though.

The simple device has an economic advantage when the task is not repeated often enough to pay off the costs of the more complex machine (this includes maintenance costs which can be more than the initial investment)

A backhoe is actually very complex

But it's quite a bit less complex than a scaled up anatomic analogue human arm. It's just complex enough to be a general-purpose excavation and construction tool. My point is that the evolved complexity of a human hand is too complex for the general purpose manipulation task. Evolution isn't perfect. It just did a very good job given it had a bunch of fish bones to work with.

Please note I said "simpler" device, not "simplest possible" device. US artillery in WWII had commensurate functionality to German artillery, but did it with nearly half of the number of moving parts. US tanks were individually less capable than their German counterparts, but were more efficient to manufacture and easier to repair. That is what is meant by the economic advantage of the "simpler." Not using a trebuchet instead of a cannon.

> My point is that the evolved complexity of a human hand is too complex for the general purpose manipulation task.

Maybe if you're constraining 'general purpose manipulation' to mean 'rearranging blocks'. That complexity (and especially the extra brain power to run it) costs energy. If it wasn't useful, we wouldn't have it.

Maybe if you're constraining 'general purpose manipulation' to mean 'rearranging blocks'.

I'm thinking more along the lines of "can build a PC" or "repair a machine." I don't think we'll need to lap flint spearheads in 2018 and beyond. I don't think we need to have repair bots play the fiddle so much on the surface of Mars. I do think that the manipulation tasks useful to a 21st century civilization are "within the grasp" of simpler manipulators than the human hand. The human hand is freakishly complex. If we can get 80% of the functionality for 25% the cost, that will be a win. (For the most difficult 20%, there are still humans.)

That complexity (and especially the extra brain power to run it) costs energy. If it wasn't useful, we wouldn't have it.

Of course it's useful! No one disputes that! It doesn't matter. You're fallacious in supposing that 1) all of the complexity and capability is absolutely essential in current and future contexts and 2) that evolution had bought it with maximal possible efficiency. What we understand about evolution tells us that the 1st isn't necessarily true, and that the 2nd is probably not!

Yes, there will be a place for human hands. But some huge fraction of the current uses of human hands will probably be replaced by very capable but much simpler manipulators -- simply due to economics!

Interestingly on a related note I just watched a documentary called "The Workers Cup" about laborers building the venues for the Qatar world cup and there were many shots of the laborers manually shoveling rocks and gravel in places where you would typically see a machine doing it here in North America. Apparently, for them, it's cheaper to use cheap labor to hand dig rocks and dirt than to use a machine to do it.

Yes, if you can treat workers like machines (i.e. no “human rights”) they are actually more efficient per calorie/dollar than a rotary engine for many tasks.

This is why slavery didn’t just die upon invention of the engine.

Citation provided (for the first claim):

Qatar 2022 https://www.amnesty.org/en/latest/campaigns/2016/03/qatar-wo...

Russia 2018 https://www.hrw.org/news/2018/06/06/russia-world-cup-labor-a...

Brazil 2014 https://www.aljazeera.com/humanrights/2014/07/world-cup-work...

(a bit of a threadjack so I'll stop here)

> The simpler device will always have an economic advantage.

The recent history of technology suggests otherwise. General-purpose devices displace simpler single-purpose devices. Consider all the specialized, but relatively simple, circuits displaced by the desktop computer.

Relevant 1 minute video: https://vimeo.com/107569286

General-purpose devices displace simpler single-purpose devices.

Yes, but simpler general-purpose devices displace more complex general-purpose devices, so long as they're also suitable to the tasks. A robot with a couple of graspers, a picker, a suction manipulator, plus some graspable special-purpose tools could be as versatile as a humanoid robot with anatomically inspired human-like hands, but be several times simpler and several times more reliable.

Reply on news.ycombinator.com