21–30 of 70 posts
Are physics engines not yet accurate enough to enable "virtual" pre-training / full training of the networks, lighting conditions, etc? If they are, exclusively using physical robots seems somewhat inefficient.
Gazebo with Mike Sherman's physics engine might be good enough. DARPA paid to get a decent physics engine into Gazebo; the ones from games were never quite right.
Are physics engines not yet accurate enough to enable "virtual" pre-training / full training of the networks, lighting conditions, etc? If they are, exclusively using physical robots seems somewhat inefficient.
That's a very interesting question. My guess is that the physics of grabbing things, especially non-rigid things, is very messy and difficult to simulate. It would be great if someone here were able to give a detailed answer to this question though.
1. The best / most recent attempt at this was for the DARPA robotics challenge and the Gazebo simulator.
This was still very buggy and prone to hilarious / depressing physics.
2. Almost all game physics engines start from rigid body and slap on particles, deformables, etc.
An exciting counter example to this is nVidia Flex which starts with unified particle simulation (much closer to molecular dynamics simulation used for, you know, real work).
3. From the perspective of AI, accurate simulation might not be required.
Intelligence requires complexity and a certain degree of predictability. So as long as you can build a rich and consistent / learnable world then whatever simulation you have could be super useful.
From the perspective of transferring that knowledge into a robot though you need accurate physics.
4. Natural touch sensors are hard to do in rigid body simulators but are super important to naturalistic learning.
There's a ton of information that your sense of touch and body position provide about how the world works, and getting the tens of thousands of soft-contact touch points simulated you need for this kind of sensing is pretty challenging today.
Lots of physics engines do all sorts of things to minimize contact points, or ignore them if there's no motion. You have to work against optimization a lot if you want mechanoreceptors and proprioception.
I always thought this was the only way to build a true AI -- build a 'virtual baby' that has to go through much the same experiences as a human baby. I'm sure this idea has been explored somewhere already - anybody have any pointers?
This is precisely the approach taken at MIT under Prof. Rod Brooks: "Within our group, Marjanovic, Scassellati & Williamson(1996) applied a similar bootstrapping technique to enable the robot* to learn to point to a visual target. " *named Cog, short for "Cognition" http://people.csail.mit.edu/brooks/papers/CMAA-group.pdf If I may paraphase, his model is biologically inspired -- believing hierarchical layers of behav…
The question of course, is, how could we deal with the implications of not just creating a smarter computer, or new life, but an entirely new and unprecedented class of life?
For one thing, if they're so great, why bother keeping us around?
Brett robot folding clothes. https://www.youtube.com/watch?v=Thpjk69h9P8
Earlier quoted context omitted.
Do animals have souls, and do we care?
A cow kicked a lantern and burned down Chicago. A powerful and incensed AI could destroy the foundations of global society before we would even know what's going on.
A powerful and incensed President could order a nuclear strike that could end civilization as we know it. Why the concern over a theoretical intelligence that could theoretically have emotion and theoretically have so much power it could theoretically do the same?
Are physics engines not yet accurate enough to enable "virtual" pre-training / full training of the networks, lighting conditions, etc? If they are, exclusively using physical robots seems somewhat inefficient.
Earlier quoted context omitted.
This is precisely the approach taken at MIT under Prof. Rod Brooks: "Within our group, Marjanovic, Scassellati & Williamson(1996) applied a similar bootstrapping technique to enable the robot* to learn to point to a visual target. " *named Cog, short for "Cognition" http://people.csail.mit.edu/brooks/papers/CMAA-group.pdf If I may paraphase, his model is biologically inspired -- believing hierarchical layers of behav…
I have long believed that we aren't going to get an AI that matches biological intelligence until it has to fend for itself. Nearly every biological function is linked to the fundamental need to survive through scarcity in hostile environments in order to reproduce and pass along genetic material. Without that need, there would not have been such rigorous evolutionary arcs that ultimately brought humans to this earth…
Earlier quoted context omitted.
It is difficult, but doable assuming Coulomb friction. The two main issues are that it is computationally expensive, but also that your mechanical modeling has to closely match that of the actual robot (especially the contact model), otherwise I suspect the training data will be useless in the end. So if you can afford an actual robot, it makes sense to do the training using it.
How computationally expensive ? Are we talking supercomputer time to simulate the few seconds it takes to grab an object ? Advanced robots are expensive too and usually much harder to get access to then computational ressources (ie. AWS).
On a typical desktop computer, that would probably range from real time for the fast/imprecise simulation, to maybe one day for a full-blown simulation.
But again, most roboticists will tell you there is a world between the simulation (even an accurate one) and the actual robot.
Earlier quoted context omitted.
I have long believed that we aren't going to get an AI that matches biological intelligence until it has to fend for itself. Nearly every biological function is linked to the fundamental need to survive through scarcity in hostile environments in order to reproduce and pass along genetic material. Without that need, there would not have been such rigorous evolutionary arcs that ultimately brought humans to this earth…
There are plenty of organisms on the planet that co-exist with more powerful ones and they don't attempt to wipe out the other. There would need to be such fierce competition over natural [or unnatural] resources that only one of the two organisms could exist, and then competition would give rise to a potential outcome of one extinguishing the other. Your question is simply an irrational fear, probably on the order o…