Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Open Problems in Robotics

scottlocklin.wordpress.com

Post reply on HN
Print view View original

61–70 of 232 posts

Re: Open Problems in Robotics

#61

Post by bad_alloc »

contingencies wrote: post #52

Robotics founder here. Popular conceptions of "robots" are unrealistically general. In industry, we do not build robots, we build automation systems. Given the choice, would you prefer an automation system with some environmental assumptions, high speed and perfect repeatability (ie. entire industrial automation world), or no environmental assumptions, crushingly high cost, slow speed and poor reliability (eg. walkin…

Well, most elements on this list would allow us to move beyond needing so many assumptions. Lots of cost could be saved if I didn't need to perfectly measure all my owrkoffsets or didn't have to spend lots of time on designing my workspace to avoid singularities. Also it would allow us to move from relatively narrow-purpose machines ("move this end effector to this position within +/-0.01mm") to much more general jobs, hence opening more to automation.

Re: Open Problems in Robotics

#62

Post by cpgxiii »

fxtentacle wrote: post #45
cpgxiii wrote: post #32

Earlier quoted context omitted.

It's generally understood that motion planning for nontrivial problems is very non-convex, and it's basically impossible to predict if a given initial condition can be optimized to the global optima. Even simple convex 3D geometry in the environment projects to very complex non-convex geometry in the configuration space of the robot (the space you're performing optimization in).

While that is true, the critical question is whether it will be locally smooth once you get close enough to your goal. Long-distance planning is generally bad, even for humans. Short-distance planning tends to work well with A-star

The problem is that "distance" here is not necessarily in any intuitive or useful space, and knowing if you are close to the goal may be as hard as finding the full solution. You can be quite "close" to a solution in, say, Euclidean distance over joint angles, while constraints like joint limits and collisions mean that the actual solution path will be quite long.

Re: Open Problems in Robotics

#63

Post by alwahi »

fxtentacle wrote: post #24
alwahi wrote: post #19

Earlier quoted context omitted.

sorry for sidetracking your answer but what actually does convex mean in the context of optimization. I remember looking at a book called convex optimization. Your statement that > Motion planning is very much non-convex, suggests to me that you are very much talking about the same thing. I understand convexity as in a shape. Why is convex good and concave bad in terms of optimization? I don't want you to dumb down t…

Think of numerical optimization (e.g. gradient decent) as if you're letting a marble run down a hill. Only for some hill shapes can you be sure that the marble will reach the bottom. For other shapes, it'll get stuck on a small flat or in a small hole. Those would be called zero gradient or local minima failures. If your hill has a convex shape, then the marble will always roll up the bottom eventually.

this was so apt and it makes so much sense. a bulb just went on in my head. thanks so much for your simple and precise explanation.

Re: Open Problems in Robotics

#64

Post by mikro2nd »

mvn9 wrote: post #40
tuatoru wrote: post #33

Earlier quoted context omitted.

> Why not let them stay in that state for days until you need to ho[o]ver? Risk of personal injury. (The Lego-on-the-stairs scenario.) Also, some people just like a calm visual field at home.

All very reasonable arguments. What I don't understand is cleaning up in the evening. There is no visual field to perceive if you are asleep.

Perhaps you've not yet reached an age where you frequently need to get up to pee in the night (sometimes several times) and keep the lights off to avoid disturbing a sleeping partner... ;)

Re: Open Problems in Robotics

#65

Post by froj »

MaximumYComb wrote: post #51
cpgxiii wrote: post #6

In the area of Motion Planning (my own area of research), the most that can be said is that practical solutions exist for a tiny subset of cases, workable methods exist for a larger subset, expensive methods exist for a still larger subset, and everthing else might as well be impossible. - If you've got a low-dimensional problem, say 2D or 3D, without uncertainty (or at least bounded enough to pad obstacles and ignor…

Is obtaining optimal solutions a requirement in motion planning for robotics?

In control when you say optimal it usually just means that you solve your problem by defining a cost function which you try to minimize within constraints. For example in motion planning your cost could be distance traveled + time spent + energy used. This cost function would be written as a function of the system state (position, velocity, etc.) and control input (e.g. throttle). The control input that limits the cost function is what you're looking for.

Optimal shouldn't be equated to the absolute best way, because it's always a question of definition.

Re: Open Problems in Robotics

#66

Post by Animats »

- Motion planning: already discussed.

- Multiaxis singularities: much less of a problem than it used to be. We don't need closed-form solutions any more; we have enough CPU power at the robot to deal with this. You need some additional constraint, like "minimize jerk" when you have too many degrees of freedom.

- Simultaneous Location and Mapping. SLAM for short: Getting much better. Things which explore and return a map are fairly common now. LIDAR helps. So does having a heading gyro with a low drift rate. Available commercially on vacuum cleaners.

- Lost Robot Problem: hard, but in practical situations, markers of some kind, visual or RF, help.

- Object manipulation and haptic feedback: Look up the DARPA manipulation challenge. Getting a key into a lock is still a hard problem. It's embarrassing how bad this is. Part of the problem is that force-sensing wrists are still far too expensive for no good reason. I once built one out of a 6DOF mouse, which is just a spring-loaded thing with optical sensors. Something I was fooling around with before TechShop went down. I have a little robot arm with an end wrench and a force sensing wrist. The idea was to get it to put the wrench around the bolt head by feel. Nice problem because a 6DOF force sensor gives you all the info you can get while holding an end wrench.

- Depth estimation: LIDAR helps. The second Kinect was a boon to robotics. Low-cost 3D LIDAR units are still rare. Amusingly, depth from movement progressed because of the desire to make 3D movies from 2D movies. (Are there still 3D movies being made?)

- Position estimation of moving objects: the military spends a lot of time on this, but doesn't publish much. Behind the staring sensor of a modern all-aspect air to air missile is - something that solves that problem.

- Affordance discovery: Very little progress.

The real problem: solve any of these problems, make very little money. If you're qualified to work on any of these problems, you can go to Google, Apple, etc. and make a lot of money solving easier problems.

Re: Open Problems in Robotics

#67

Post by person_of_color »

paulpauper wrote: post #56

>Multiaxis singularities -this one blew my mind. Imagine you have a robot arm bolted to the ground. You want to teach the stupid thing to paint a car or something. There are actual singularities possible in the equations of motion; and it is more or less an underconstrained problem. I guess there are workarounds for this at this point, but they all have different tradeoffs. It’s as open a problem as motion planning o…

I thought quaternions work around gimbal lock?

Re: Open Problems in Robotics

#68

Post by rimliu »

fxtentacle wrote: post #38

Motion planning is also an Open Problem for Humans! Let's say we are standing on a high hill and I point to another hill and say: "Walk over there". Do you expect any human to find a reasonably good path by themselves? I would personally try to use a map. How do military robots solve this? They use satellite images. And in general, this article seems very pessimistic to me. My home-built computer vision pipeline can…

Alas, your problem #1 is not really about memorization, it is about understanding. Take a human to the house they have never been before and tell them: "make me some tea". Now try that with any robot you want.

It is you being optimistic, not the article being optimistic.

Re: Open Problems in Robotics

#69

Post by visarga »

> We all know emergent systems are super important in all manner of phenomena, but we have no mathematics or models to deal with them. So we end up with useless horse shit like GPT-3.

Says the author who confesses his lack of domain knowledge in the intro.

So much entitlement. Why didn't he invent something better?

Re: Open Problems in Robotics

#70

Post by jononor »

paulpauper wrote: post #56

>Multiaxis singularities -this one blew my mind. Imagine you have a robot arm bolted to the ground. You want to teach the stupid thing to paint a car or something. There are actual singularities possible in the equations of motion; and it is more or less an underconstrained problem. I guess there are workarounds for this at this point, but they all have different tradeoffs. It’s as open a problem as motion planning o…

The workarounds are designed to solve particular cases. A robot arm in manufacturing is stationary, has a controlled environment, and often a fixed task (or at least task type). The task is know in advance, and humans are involved in developing the solution for each particular task. In an open environment one cannot rely on those things. When the task is not known up-front. Or the new tasks come too quickly for a human to be involved in solving it. Or with influence from other actors, some possibly uncooperative or adversarial.

A lot of 6 axis robots actually work in 3D+3D. That is, they position their arm/tooling first into a work pose, then perform their actually work in a 3D space referenced from that point/orientation. Then poses are chosen such that the space it works in is singularity free. And moving between poses there are then explicit solutions (chosen by human) for dealing with singularities.

Post reply on HN