Open Problems in Robotics • Hacker News Board

Re: Open Problems in Robotics

#181

Post by pilingual » Wed, Aug 19, 2020, 9:08 PM UTC

lisper wrote: post #144

> Guys like Rodney Brooks seemed to accept this and built various robots that would learn how to walk using primitive hardware and feedback oriented ideas rather than programmed ideas. There was even a name for this; “Nouvelle AI.” No idea what happened to those ideas; I suppose they were too hard to make progress on, though the early results were impressive looking. The problem was that subsumption didn't scale, but…

This paper seems to pre-date behavior trees. Any comment on how TLA relates? (I skimmed but will give a closer look when I have more time.)

I was curious what Brooks now thinks about subsumption and found this from a few months ago:

The approach to controlling robots, the subsumption architecture that it proposed led directly to the Roomba, a robot vacuum cleaner, which with over 30 million sold is the most produced robot ever.¹

Like many, I got a Roomba not long after the pandemic began. I was disappointed by its poor sensorimotor system. Within a few days its IR cover was scuffed up and it was covered in scratches from getting stuck under an office chair. Brooks doesn't say that 30mm Roombas incorporate subsumption, and no doubt after a decade or two of programmers I wonder about the nature of the codebase. The Roomba's behavior is entirely unpredictable, as sometimes it will bump into something full speed and sometimes it will slow down as it approaches. There are a number of other issues too long to mention including the charging contacts and recently it started roaming around with its charger still attached for no apparent reason.

¹ https://rodneybrooks.com/peer-review/

Re: Open Problems in Robotics

#182

Post by rcv » Wed, Aug 19, 2020, 9:23 PM UTC

tgflynn wrote: post #154

Animats wrote: post #66

- 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…

I don't really understand why depth estimation using binocular vision is still a problem. I worked on this a bit a number of years ago and I thought I had scene matching working pretty well. The problem is I was trying to make it work without actually having two cameras (ie. on a smartphone where binocular cameras were not available at the time and for the most part still aren't). I was hoping to use the acceleromete…

Stereo vision isn't exactly "solved," but there are a ton of very good solutions out there both open source and commercial. The "Semi-Global Block Matching" algorithm implementation in the OpenCV library[1] is very good even though the algorithm is over 10 years old at this point. I've played around with the new Intel RealSense[2] units recently as well, which are stereo cameras with onboard processing and a nice IR pattern projector. Pretty cheap, and for the most part they "just work."

[1] https://docs.opencv.org/4.4.0/d2/d85/classcv_1_1StereoSGBM.h... [2] https://www.intelrealsense.com/stereo-depth

Re: Open Problems in Robotics

#183

Post by tsimionescu » Wed, Aug 19, 2020, 9:24 PM UTC

mhb wrote: post #123

imtringued wrote: post #34

Earlier quoted context omitted.

Humans have a mental model of humans, they can predict what another human is going to do with reasonable accuracy. Robots are wholly artificial so there is no existing mental model we can apply to them to understand why and how they act.

You have no mental model of the crazy person who drives his car into oncoming traffic.

Sure, and that's why we try not to let people with altered states of consciousness or with unpredictable rationality (children) drive.

Re: Open Problems in Robotics

#184

Post by lisper » Wed, Aug 19, 2020, 9:44 PM UTC

pilingual wrote: post #181

lisper wrote: post #144

> Guys like Rodney Brooks seemed to accept this and built various robots that would learn how to walk using primitive hardware and feedback oriented ideas rather than programmed ideas. There was even a name for this; “Nouvelle AI.” No idea what happened to those ideas; I suppose they were too hard to make progress on, though the early results were impressive looking. The problem was that subsumption didn't scale, but…

This paper seems to pre-date behavior trees. Any comment on how TLA relates? (I skimmed but will give a closer look when I have more time.) I was curious what Brooks now thinks about subsumption and found this from a few months ago: The approach to controlling robots, the subsumption architecture that it proposed led directly to the Roomba, a robot vacuum cleaner, which with over 30 million sold is the most produced…

> This paper seems to pre-date behavior trees.

Indeed. By a good 20 years :-)

> Any comment on how TLA relates?

I've been out of the field for a long time so BTs are new to me. All I know about them is from skimming the wikipedia article. But they look to me like a more formal implementation of the TLA sequencing layer.

Re: Open Problems in Robotics

#185

Post by oytis » Wed, Aug 19, 2020, 9:54 PM UTC

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, that's what research is about: to solve the said problems more reliably, faster and in the end at lower cost.

Re: Open Problems in Robotics

#186

Post by contingencies » Wed, Aug 19, 2020, 10:46 PM UTC

Symmetry wrote: post #145

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…

There are happy middle grounds which are neither the rote repetition of industrial production nor the impossibly unstructured environments a theoretical butler robot would have to work in. I work piece picking and, with a succession of unknown objects to pick up and place, the problem is both interesting and achievable.

Almost all picking is done with pneumatic suction because it's highly reliable, powerful, relatively safe and easily adaptable. Furthermore, the standard silicone nozzles on the market permit varying amounts of safety margin due to squishiness. You can solve for almost every real world picking problem without more custom hardware than perhaps a mounting plate and scale instantly to mass-produced parallelism. This is why the industry has standardized on this approach... it's practical, cheap, fast and quickly adaptable.

The other 1% of items is a problem only in the case that the thing to be picked is either particularly complicated and irregular in shape, or has some delicate physical property. The annoying case, which seems to be what you are working on, is large numbers of unknown items.

If you start with recognition that no system will work with arbitrary items (the 'best case' generalized picking system will still be necessarily limited by maximum size of the object it can pick, the reach of the picking/placing motion, the weight it can support, and its accuracy/repeatability), this is a difficult field to justify research in, as while an algorithm aiming at generalizing solutions in this space can probably find a way to use the standard pneumatic approach against, say, the largest exposed flat surface of an unseen item after collecting a point cloud or grasping using opposite surfaces or enclose convex faces with an alternate gripping mechanism, these are never going to increase the generality to an absolute extent. Sadly, with this increased complexity comes diminishing returns, increased cost (sensors, actuators, computation, latency, etc.) and counter-intuitively (unless a major paradigm shift is obtained) also therefore a diminishing market.

Logically, then, the process governing new item ingress for whatever operations you are automating may likely be a better place to spend time than chasing after a non-existent magic algorithm / gripper design to solve for arbitrary cases. For example: "Mandate square boxes" elegantly solves the problem, as per international shipping. You don't actually need enclosed boxes - stackable trays work fine too.

About the only case where random item picking makes sense outside of garbage sorting is very large scale general warehousing for hugely dissimilar items, the sort of problem only Amazon has. For almost anyone else, sacrificing storage space efficiency with boxes or segmenting in to multiple specialised systems are likely better tradeoffs.

Re: Open Problems in Robotics

#187

Post by cpgxiii » Wed, Aug 19, 2020, 11:59 PM UTC

fxtentacle wrote: post #114

cpgxiii wrote: post #53

Earlier quoted context omitted.

If you have a vision system that "just works" and produces high-quality pointclouds in an actual kitchen environment, with reflective appliances, silverware, shiny countertops, shiny ceramic dishware, and glasses, we would absolutely use it. We have in-house research work on both learned monocular depth (so-so for robotics tasks) and learned stereo disparity (much more promising), so progress here isn't impossible, b…

It "just works" for our use case. We put in 4K @ 60fps and receive 960x540 @ 20fps of stereo correspondence pairs. So every matched pixel is averaged over 3 frames in time and 4 pixels in every direction in space, meaning 9x9 convolution kernels. In other words, we make the video super clean by area sampling in space and time. The specific part about our system that makes it usable for me is that for pixels that cann…

Yes, in general if you can capture multiple views you can make up for many dropouts and artifacts. The more you can move, the more likely that you'll get a complete reconstruction. Single-view artifacts are more of a problem when reaching into confined areas or during visual servoing where you don't necessarily have the freedom to move around to get a better view.

The results for the Sintel benchmark do look interesting. Do you have a report or some sort of overview of your approach? It would be nice to see a similar benchmark on real recorded scenes, especially if that provided a way to compare learned matching algorithms with available sensor hardware.

I think there's reasonable promise in learned stereo matching, especially if we include more information than just visible spectra. Human eyes are so much more than two RGB imagers, so we shouldn't limit our robots to that either. Monocular depth, I agree, seems to be mostly a memorization problem. In cases where you can effectively memorize everything, it will work quite well and the savings in hardware complexity (and physical sensor size) will be well worth the training complexity. I actually think it has much more promise as a backup depth perception method on cars, since objects in a driving context are mostly consistent in size. I have doubts about how useful it will be in manipulation tasks where you may encounter similar objects at a range of sizes.

I'm part of a research group at TRI working on home manipulation tasks although I have something of a hobby interest in outdoor robotics as well - in general I'd say the depth sensors for outdoor tasks are often better, but much more expensive and out of reach for hobbyist users.

Re: Open Problems in Robotics

#188

Post by throw149102 » Thu, Aug 20, 2020, 12:25 AM UTC

redis_mlc wrote: post #71

burntoutfire wrote: post #12

Earlier quoted context omitted.

What about "practical error bounds", i.e. testing the system through millions/billions of miles driven?

> testing the system through millions/billions of miles driven? Makes sense doesn't it? Well, actually no. The Google cars drive the same route every day in Mountain View with no deviation, so those millions of miles are really the same 10 miles over and over. Even seen 3 in a row behind each other. Fools the regulators, and apparently you, though.

Deaths are often measured in deaths per 100,000,000 miles driven, with a current measurement of 1.18 deaths per 100 million miles[1]. If a car is driving 60 mph 24/7, it takes 190 years for it to drive 100,000,000 miles. Let's assume that, in a decade, 1% of cars are on autopilot. There are 37,000 deaths per year in the USA due to car accidents[1]. Therefore, in order for Tesla/Google/GM to claim that it is equivalent to normal cars, it has to drive 370 * (100 million/1.18) ~= 31,300,000,000 miles, with only 370 accidents. If $COMPANY really had, say, 400 accidents, then it would have to make up the additional miles. In specific, it would have to make up 30 * (100 million/1.18) ~= 2,500,000,000. That means a fleet of (190 * 25) = 4,750 cars driving 24/7 for an entire year. That's not impossible for $COMPANY to do, but it is starting to become unreasonable. What's more likely is that $COMPANY just straight up lies about its incidence rate to regulators. But that's hard to do, considering it's going to be public if someone gets hit by a car.

I don't think its possible to fool the regulators, but even if it was possible there are dramatic consequences for lying. Volkswagon tricked regulators into thinking their car didn't emit as much as it really did in 2007-2015, and ended up having to pay 33.3 billion dollars in fines and returns[2]. Volkswagon stock went from a high of around 27 to 12. 5 years later, it's only recovered to around 16. The massive lawsuit that would be formed if Tesla's (or other automated car maker) car was found to be unsafe would likely be even larger. Furthermore, it would crush the self-driving car business semi-permanently. VW at least still gets to make environmentally safe cars, Tesla and Waymo's main value proposition is dead in the water.

Basically, even though there are incentives to lie and cheat, I think the incentives to try to make something that is safe is far, far greater. And while I'm sure there are Google cars driving the same route every day, I'm sure there are also tests being done in all sorts of conditions all over the planet. I think that practically, socially, and politically speaking, we can use billions of miles driven. The stakes are way too high to lie.

[1] https://en.wikipedia.org/wiki/List_of_self-driving_car_fatal... [2] https://en.wikipedia.org/wiki/Volkswagen_emissions_scandal

Re: Open Problems in Robotics

#189

Post by Nasrudith » Thu, Aug 20, 2020, 12:39 AM UTC

deepGem wrote: post #77

Animats wrote: post #66

- 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…

"The real problem: solve any of these problems, make very little money" - Just curious why have you come to this conclusion ? Object manipulation has potential products in dishwashing and vegetable chopping - sufficiently large markets, potential billion $ outcomes for a startup which takes the early mover lead. Two robotic hands that can work in co-ordination just as human hands do. Extremely difficult to solve, but…

I would have thought the money wouldn't be there for a different reason - human hands suck compared to tools which is why we created them in the first place. It is a bit of a silly trope to have industrial work done by humanoid robots with hand tools.

The ability to manipulate destandardized sizes would be useful but precision manufacturing ate most of the lunch long ago which reduces it to more of a "last mile" task.

Re: Open Problems in Robotics

#190

Post by rajansaini » Thu, Aug 20, 2020, 1:00 AM UTC

stillsut wrote: post #167

The pile of problems in Robotics reminds me of the challenges faced by computer vision before modern methods were developed. To generalize the issue: humans learn and perform vision and navigational tasks "below" the level of language. To use a vivid example, you can use language to teach a child how to hold a pencil and write, how to recognize digits, and how to do two digit addition. But there's some cognitive abil…

That's a very interesting perspective. There have been many articles complaining about the "hype" behind ML, but I too wonder if DNNs could assist with controls, especially when it comes to reacting to sensor data. After all, it's just matrix math.