Robots that can walk are now striding to market

https://www.economist.com/science-and-technology/2020/08/25/robots-that-can-walk-are-now-striding-to-market

by pseudolus • 6 years ago

70 105 6 years ago

sradman• 6 years ago

Boston Dynamic's four-legged Spot [1] and bipedal Atlas [2]. Agility Robotic's Digit [3]. It looks like robotic actuators are about to hit an innovation wave.

[1] https://www.bostondynamics.com/spot

[2] https://www.bostondynamics.com/atlas

[3] https://www.agilityrobotics.com/meet-digit

Robotbeat6• 6 years ago

Quasi-direct-drive actuators (BLDC motors with position Feedback and a modest, 5:1 or 10:1 gear ratio) are what you’re thinking of for Spot and similar. For Atlas, you kind of need the specific force and low speed specific power than hydraulics give you. That’s what Boston Dynamics uses for those larger dynamic robots (Atlas, Big Dog, etc). (Hydraulics are under-rated! They can be electrically pumped, so they need not be super loud.)

forgotmysn• 6 years ago

actuators and slip rings are going to change the game for robotics

k__6• 6 years ago

are they a suitable alternative for wheelchairs?

Because of stairs, etc.

lowdose• 6 years ago

This is an unexpected original application. Do you think people in a wheelchair would like to upgrade to a robot?

k__6• 6 years ago

Don't know.

But maybe it would

1. allow them to stand

2. allow them to use stairs

stubish• 6 years ago

Maybe. Maybe not. But the real question is whether people in 10 years time would prefer a walking mobility scooter or a wheeled mobility scooter. When the Star Wars generation hits this point en-mass in 20-30 years, I predict there will be a huge market for personal AT-AT walkers.

samcheng2• 6 years ago

A previous attempt (dynamically balancing wheelchairs) was the progenitor to the Segway:

https://en.wikipedia.org/wiki/IBOT

jpm_sd• 6 years ago

Looks like they are working on a relaunch (re-relaunch?)

https://mobiusmobility.com/

I think unfortunately the main reason the iBot did not originally succeed is that it was too expensive.

adrianmonk• 6 years ago

Could also be useful for movers.

Right now when it's time to carry that heavy desk, couch, piano, etc. through doorways, halls, up/down stairs, etc., two really strong people do it manually.

Imagine if they showed up with a robot that could do it. In addition to walking, it would need to understand gripping and balancing heavy objects and how to orient and maneuver 3D objects through tight 3D spaces, but I bet those things are understood well enough.

ufmace4• 6 years ago

Having worked as a mover for a while once upon a time, I don't think it would make much difference as it is now. It's very rare for any moving job to require more physical strength than an average adult male has. The challenge is more like understanding how to handle items without damaging them or the building, what order to move things in so that a truck can be packed well. We'll need a lot more real-world intelligence from robots before they can do something like that.

Unusual physical strength, or powered mechanical aids, are mostly only used with unusual items. Ex, most "gunsafes" are more properly Residential Security Containers, and aren't all that heavy (~200lbs) and can be moved around, including up stairs, by two average adults. Real safes weigh more like 600lbs and are much more rare, partly due to the difficulty and expense involved in moving them anywhere remotely tricky. I have heard of powered stair climbers being used to lift such things up a flight of stairs.

samcheng2• 6 years ago

Youtuber Marques Brownlee had a cool video on Spot last week.

https://www.youtube.com/watch?v=s6_azdBnAlU

His takeaway was that the big use cases currently are around LIDAR and mapping, e.g. tracking construction progress, in irregular / uneven terrain.

I'm less convinced that walking robots are useful for some of the use cases described in the Economist article, like moving boxes in a warehouse. After all, warehouses are generally built to facilitate wheeled vehicles (forklifts) already...

clairity5• 6 years ago

yes, it's been common knowledge in biomechanics that wheeled vehicles win on flat surfaces, hands down (ha). legs are good for the 99.9% of earth's land that isn't nearly as predictable. the general utility of accessing that 99.9% is relatively dispersed though (and hard to build a business on).

Robotbeat6• 6 years ago

Simply using big wheels or tracks work for non-flat surfaces, too, and are cheaper & more efficient (especially the wheels).

Legs allow you to climb, ie a ladder, very steep stairs ( more than 45 degrees), a tree, or an extremely steep rough slope (think: mountain).

A tracked vehicle or large-wheeled vehicle can go almost anywhere a legged robot can go with a large efficiency and cost advantage.

However, you can run into space constraints. Bipedal robots are good for navigating human-scale environments while still having a tall and stable robot.

But generally, tracks or big wheels are way cheaper and more efficient and can do the same thing.

renox• 6 years ago

I think that eventually robots will get both wheel and legs: wheel are more efficient where they are usable.

stetrain• 6 years ago

SpaceX uses one for inspecting their testing site before clearing personnel to return after a test.

https://www.tesmanian.com/blogs/tesmanian-blog/sn7-zeus

jariel• 6 years ago

Please make me some AI that can clean my toilet, do my laundry and make me a ham sandwich. This will be the revolution.

ipnon• 6 years ago

This is disparagingly referred to as momtech. Young silicon valley transplants try to replace the role of their parents with technology. They want to avoid cooking and cleaning so they can code all the time. "If only a robot could do my dishes for me!"

It's the epitome of fitting a solution to a problem. Cooking and cleaning are simple tasks that any able bodied person can do themselves. There is no shortage of able bodied people in the world.

tlb2• 6 years ago

A good rule of thumb when dismissing some new technology is to ask, "what previous technologies would I have dismissed for the same reasons?" And if those technologies became successful, try to learn from the mistake.

In this case, clothes washing machines and vacuum cleaners seem to fit your thesis.

k__6• 6 years ago

I think is is a very narrow view on the world.

I'd gladly give up houshold chores if it was cheap and wouldn't require a person coming in my home.

TeMPOraL4• 6 years ago

A peculiar way of looking at things.

House chores and maintenance are two big things that are yet to be tackled by technology. They're quite literally life wasters - things you must do in order to get the things you want to do. Prime candidates for automating away, the opposite of "fitting a solution to a problem".

marcosdumay• 6 years ago

It's the epitome of fitting a solution to a problem.

Wait... Isn't fitting a solution to a problem exactly the right way to do things?

ithkuil• 6 years ago

I'd call it Sudo

jamiek884• 6 years ago

I wonder if sudo make me a sandwich could be a reality in our lifetimes?

hooande• 6 years ago

I'd estimate that this is at least 15-20 years away, shortly before or after we have fleets of autonomous vehicles

beambot• 6 years ago

You want the robot that cleans your toilet to make you a sandwich? Huh.

diamondlovesyou• 6 years ago

Presumably, after it also cleans itself, yeah. Humans do it all the time.

DenisM• 6 years ago

So how about some Mountain-Boting[#]? Riding a BigDog" on the mountain bike trails at crazy-stupid speeds.

[#] Mountain-Boting is now a word

Animats3• 6 years ago

The slow march to cost-effectiveness continues. But no killer app yet.

Much of this is a mechanical design problem. You need to be able to generate large forces from a small package, but not all the time. Hydraulics can do it, but then you need a big pump and power source, like the older Boston Dynamics machines. Until recently, all-electric didn't have the power density. Now it does. Which is why quadrotor drones work.

Small polyphase permanent magnet motors ("brushless DC") have taken over. The controllers to drive them at variable speed are now cheap. No brushes, no arcing, no magnet demagnetization. The remaining limit on motor power is cooling.

It's too bad Schaft Robotics was liquidated. They were doing well on humanoids. Then Google bought them, trashed them, and dumped the remains. They were into small liquid-cooled motors. That's a way to get huge torques when you need them.

Reduction gears are always a problem. If they're big enough not to snap gear teeth on shock loads, they're too heavy. Better materials for toothed belts have helped. Those have more space to absorb a shock load. Researchers like harmonic drives, because they can put a big reduction in a small package, but harmonic drives are especially vulnerable to broken gear teeth on overload.

Direct drive, without gears or belts, would be nice. The advantage of direct drive is, as someone said a century ago in the context of electric locomotives, "You cannot strip the teeth of a magnetic field." Washing machine motors are often direct drive today. The electronics is cheaper and more rugged than a gearbox. It's encouraging seeing that happen in a mass-market product.

There's a lot of engineering like that which needs to be done to get mobile robots down to the price of a non-luxury car.

pharke• 6 years ago

Then Google bought them, trashed them, and dumped the remains.

This seems to be a too oft repeated refrain. Google has become such a mire of intra-office politics that being acquired by them is almost a guaranteed death sentence.

Ygg2• 6 years ago

Google is the new IBM.

tgflynn9• 6 years ago

Do you think there's any chance of direct drive generating enough torque for a roughly human sized robotic arm with human like performance (say to lift a 20 kg load) ?

The last time I looked into this it didn't look like that much torque was available in a small form factor. I found it rather surprising because larger scale industrial robot arms appear to far exceed any biological arm in both strength and speed.

macrolime• 6 years ago

There's at least some with 8kg payload

https://www.halodi.com/ever3

thefounder2• 6 years ago

I don't think a robot needs to lift more than 1kg or even less to be game changer. It just needs to be accurate and smart enough so that it can use different tools(i.e push different buttons) that do the heavy lifting.

jamiek884• 6 years ago

Is it really just our arm that lifts that load though?

Plenty of core muscles involved.

Animats3• 6 years ago

In industrial robot arms, the problem is not having enough power to lift the load. It's making the arm rigid enough that positioning the actuators will put the end at the desired point. Most industrial robot arms are position-controlled, usually rather blindly. Customers want repeatable motion to tight tolerances, like a machine tool. The mechanics are overbuilt and under-loaded to achieve that.

I've seen direct drive SCARA robots with a big pancake direct drive motor on top. Those are used for vertical assembly, for designs where a straight-down move puts the part in place. The arm moves in X and Y, then there's a vertical piston-like actuator that moves in Z, and a rotation axis around Z.

jnxx• 6 years ago

It is also that as soon as you have a rigid robot with that force, speed, and without a steel fence as separation near a human, you have a safety problem.

If a human family member holds something like a baseball bat, or a butcher's knife within arms length of you, you can feel safe around them, and be sure they control their motions.

Contrarily, having an industrial robot with something like a screwdriver at the height of your head and within a meter of distance is just scary.

spullara• 6 years ago

Back in high school I had an idea for strings of electromagnetics and springs acting like muscles when power was applied. Seemed like a cool idea but never really figured out if it was at all plausible. Are any of these systems trying to simulate muscles more directly?

6gvONxR4sf7o• 6 years ago

It's amazing to think that so much of the future we imagined decades ago (flying cars, robots, jetpacks, maybe even leisure space travel) might be here if energy weren't an issue. If there's ever a 10x breakthrough in battery tech (today's performance with 10x the energy density), I'd bet the world would change pretty quickly. Even a 2x breakthrough.

andromeduck2• 6 years ago

You can throw "renewables" in there too. Everyone just assumes battery tech is on some kind of moore's law scaling just like how everyone thought SSDs were going to be 1c per TB by now.

neonate• 6 years ago

https://archive.is/D0rEJ

elihu• 6 years ago

Is it possible to make one of these robots cheaply? It seems like the cost of actuators (which you might need dozens of) and to a lesser extent sensors would make this cost-prohibitive for most uses.

For instance, if you were replacing a human salary, it might make sense to purchase a hundred-thousand-dollar robot, but if you just want something to pull weeds in your yard once in awhile, it might be hard to justify spending more than a couple thousand. If the parts alone cost tens of thousands, then that's a pretty big economic limitation on how the technology gets used.

banmeagaindan23• 6 years ago

I don't believe robots will have human level walking skills in our lifetime. This is something that looked easy for 70 years. Hans Moravec described why it was harder than it looked. It is possible to look impressive by pouring in more brains and money but unless you have a general purpose breakthrough it can not be useful and economical.

AI vs AGI is well understood in cognitive tasks but tasks that require motion would also require a parallel breakthrough.

simonebrunozzi• 6 years ago

I don't believe robots will have human level walking skills in our lifetime.

If "lifetime" can be considered to be the next 50 years, I absolutely disagree with you. I'd even venture to say that we will see robots with human level walking skills within the next 15-20 years, at most.

banmeagaindan23• 6 years ago

I assume you are the famous simone of youtube robot fame. I just speak as outsider looking in. I like robots. It would emancipate society to a new level of existence. I have trouble believing they are real - and have dark ideas about what robots really mean in our society - that they might be a symbol of something like a political belief in a sort of utopia in much the same way the Soviet and Fascist investments in science were not value neutral.

I remember looking at some original robots developed around midcentury in England. They were inexpensive and very bad but did function basic functions.

I look at the Boston Dynamics robots and see these are very expensive robots performing more natural movements.

Let us suppose the BD and similar teams are at the half way point.

To get human level performance at this rate of change means trillions of dollars. This robot would impress us - just as the original English robots and BD robots do. The French Empire invented expensive and difficult to create toys and no robot revolution started. I don't see anything continuous between the idea of a robot and the idea of machine automation - I think that is too much generosity. I know people want to give it because the field is very difficult - but this is not being honest.

The ideal of the robot - people have different ideas about this - but the ideal for me is that there is an economical and effective alternative to human level physical articulation. I'm sure you have more advanced definitions - this is just the basic benchmark. It should be plausible for a robot to sew a thread or squeegee a window with grace.

It is not just human level articulation - it's also generalist application.

General purpose machine articulation looks like a high bar to the point it is difficult to imagine what the world would look like were we to be successful.

banmeagaindan23• 6 years ago

I have mistaken your name - I thought to check but then doubted there were even two Simones involved in all of robotics but that was incorrect!

I recommend you check the work of the other Simone out - it is delightful.

https://www.youtube.com/channel/UC3KEoMzNz8eYnwBC34RaKCQ

Robots that can walk are now striding to market

Related Stories