That's not true. Agricultural robotics and automation are certainly more advanced in America and have improving for a long time. Drones with spectral cameras to examine and map plant health and irrigation levels, and to spot-spray pesticides, automated gps tractors and tools, collaborative augmented reality- nothing new in the US or Europe. It's said a lot, but Japanese robotics is somewhat myopic. IMO mostly it's due to the corporate structures in Japan: huge companies like Honda can pour tons of funding into ASIMO for 4 decades, but their goals are too narrow to make up for broad, investigative research. Plus, culture in Japan is a tangible force, and the awareness of societal problems is so high it actually impedes pure research. They are so focused on their aging population and the automation of labor that the large majority of research is geared towards those problems in one way or another. The US has the same problem- we focus on military use over everything else, but we do it just a little less than Japan.
You typically hear this sentiment (Japan is the best at robotics) wrt humanoid robotics, especially ASIMO[1]. ASIMO is basically just a really smooth suite of soft skills. Facial recognition, voice, HRI, and consumer-friendly hardware. The hard skills underneath are extremely highly optimized but fundamentally weak and outdated by over 20 years. ASIMO runs on the same hardware and algorithms from the 90s except for batteries, computer speed and sensor accuracy. In the US we have been extremely inventive with hardware design- eg all-plastic mass-manufacture BAXTER, or ATLAS, which is largely hydraulic. The newest generations of ATLAS have hydraulic actuators integrated into the frame.
ASIMO and most japanese robots use a variation on ZMP walking methods, which has the characteristic high-knee, ankle-heavy look. It's extremely inefficient and unstable. Russian robots use this too. Other robots in the US, Europe and even in China use much more efficient, flexible methods separated by a couple generations of new algorithms. Take Cassie[2] from OSU's dynamic robotics lab. Pretty clearly far ahead of anything in Japan in stability, speed, power[3] and efficiency, built by grad students from scratch. Compact series elastic actuators with HZD algorithms.
Japanese robots are meant to look perfect. Russian robots are meant to look terrifying. American robots are meant to explore new algorithms or technologies. European robots are mostly meant to build cars.
Then there's the Google debacle. Google bought Boston Dynamics, Schaft, and some other robotic startups in 2013, and they were seldom heard from again. The companies that had customers, such as Bot and Dolly, lost them. For a while, the industry assumed Google had the Next Big Thing in the works, but after a few years, it came out that Google's robotics effort had collapsed. That was a real disappointment.
Boston Dynamics's hydraulic technology is just too heavy and bulky. Big Dog was impressive, but it took $120 million to get it working as the Legged Squad Support System. Then the USMC rejected it as not useful in combat. Atlas version 1 was basically a Big Dog mod. Version 2 is better, but still weighs 150Kg.
What you want in an actuator is a spring with adjustable spring constant, neutral point, and damping factor. Muscles are like that. You can do that pneumatically, and that's been done at CWRU, but a compressed air supply is needed. Series elastic actuators are a research tool for faking muscle-like motion. They're a good way to let a motor with a high gear ratio handle a shock load, but they're inefficient; there's no energy recovery. Humans recover over half the energy in running as elastic storage in muscles. (Cheetahs, around 90%) Ideally, you'd like a direct-drive electric motor, which some SCARA robots have used. They're large-diameter devices, though. Schaft used liquid-cooled electric motors and didn't gear them down too much, which worked well. Their humanoid was a great piece of engineering. Electric linear actuators (real linear, not screw drives) once seemed promising but didn't work out well.
(I used to work on control algorithms for legged robots. A key insight there is that slip control dominates; priorities are traction control, then balance, then goal. Once you get off a flat surface, slip control becomes more important.)
Agreed about the disappointment in Google robotics. So in your opinion what will be the best available technology for robot actuators in 5-10 years?
I've recently become much more interested in robotics and I'm trying to figure out the best way to approach the field. I don't have much hardware experience so at the moment I'm thinking about training neural nets for robot control in simulation. I'm also looking for meetup groups or other ways to connect with like-minded people (in the SV area). Any advice for a dev/ML person looking to get into robotics?
If you can manage to be impressive with computer vision, that'll go a long way. The problems in that space are intense but some are solvable with NN. Recognition and things.
Most of the movement problems don't work that well with NN, afaik. I think they've been applied to avoiding singularities but if you wanted to use a NN to optimize movement, you'd have to simulate all the sets of movement first to train it. Hard ask, and people in robotics tend to be interested in abilities rather than optimization although of course they come hand in hand.
If you have the math background to understand the algorithms you can learn the cutting edge papers and implement those, then work on them. It isn't exactly simple, though.
Agree on all counts. IMO the future is large-diameter motors with between 1:1 to 1:10 reduction and very high power/efficiency(roundtrip) batteries. Many different labs are converging on it, BD is a stark exception.
So direct drive motors with something akin to regenerative braking to recover energy? Could a direct drive motor hooked to a capacitor bank recapture energy efficiently enough to act like a muscle in a walking gait?
Maybe, if you had a place to put a motor that large.
Modern motor realities:
1. Electric motors can be enormously overdriven for short periods when you need huge torque. The limits are heat dissipation and demagnetizing the permanent magnets in permanent magnet motors. With modern rare-earth magnets, the second is no longer a problem. Water cooling can deal with the first problem. If you have temperature sensing, you can safely overload temporarily and wait for cool-down. When you see one of those videos of a Tesla car accelerating in "launch mode", you're seeing this in action.
2. Power semiconductors have become really good. Power control is no longer a limiting factor on motors. For most of the 20th century, variable speed motor control for large motors was hard and took bulky, expensive gear. It was a serious problem with electric cars into the 1990s; burning out power controllers was a problem. That's been fixed. Modern electric cars and locomotives use AC synchronous motors with IGBT or MOSFET devices producing 3-phase power at the desired voltage, frequency, and phase to run the motor optimally. Locomotives synchronize all the wheels with electronics and software. This scales down all the way to hobbyist drone size. Robots get to use all this now off-the-shelf technology to run their motors.
3. Some research robots use "series elastic actuators". These are simply a motor driving a screw drive with a stiff spring attached. The trick is how they're used. When the actuator gets a shock load, as when a foot lands, the stiff spring is compressed. As it compresses, the control system detects this, and frantically spins the motor to unload the spring before the spring bottoms out. This works, but it's the opposite of energy recovery; it takes energy to absorb a load. It's possible to write software which makes such devices behave like a spring with an adjustable spring constant, but there's no energy recovery. Good for research, because these can be assembled from off the shelf parts. Not so good for battery life.
4. Gears are terrible at dealing with shock loads. One of the big advantages of direct drive is that "you cannot break the teeth of a magnetic field", as an early GE locomotive designer put it. The downside of direct drive is that torque increases with motor diameter (more leverage), and big flat motors tend to be inconvenient in robots. But there's been recent progress. See this direct-drive robot arm with small motors.[1] Very nice. No gears. No cables. No pulleys. Good force feedback. Nothing to break if somebody forces the arm. Energy recovery possible. Only 10Kg lift capacity, which is OK for industrial arms but not enough for a legged machine. Progress marches on; there may be an all-electric leg solution in time.
For decades, motors were a dull, boring, mature field. Motors came in standard sizes and speeds, and were interchangeable across vendors. Nobody worked much on new designs. Now, with much more elaborate control systems, people are innovating again. By the time there's a market for humanoid robots, the motors will probably be ready.
WRT 3: There is energy recovery, but it's very small and it's more like impedance matching. They've been used for outright storage (eg DURUS) but the springs are usually just too stiff. It still saves energy since there's a smaller initial current spike, but it doesn't save energy step-to-step. Unless you take really small steps, I guess.
Soft spring systems are not usually considered series elastic actuators. There's a "soft actuator" branch of robotics, Shadow Robotics having been doing that for years. Disney has done some work in that space, because they want machines which are safe around people. As control techniques improve, that concept works better.
There's a useful arrangement where you have two opposed springs powered by separate actuators. If you tighten up both springs, the system stiffens up; if you loosen both, you get better energy recovery but worse position control. This is a reasonable muscle model, and can recovery energy, but is bulky mechanically. Movement without load is cheap; changing the compliance is expensive from an energy standpoint. There's also a pneumatic version of this, where you pressurize an air cylinder from both ends. That works well if the valves are close to the cylinder.
There are mechanical approaches to variable compliance, but they're complex mechanically and usually seem to involve string and pulleys.[1] The trend seems to be towards all-electric systems, rather than clever mechanics.
Yes, exactly like regeneration. However it's a highly multifaceted problem to optimize. Batteries, capacitors, drivers, motors and drivetrains all have very picky efficiency regimes. Grease is very inefficient at low torques or high speeds, since it's shear-thinning and viscous. Motors have to have their voltage, current, field strength, size and a few other aspects all optimized. You run the gamut from metallurgy to fluid dynamics to chemistry to EM fields. It requires tons of high performance custom parts.
That said a few groups have done it. Heavily optimized drivetrains can be ~96% efficient at the right speed and torque. Extremely precise drivers can regen at 98%+. If you charge gently enough batteries can be 98%. 88.5% total efficiency. That's extremely good, enough to reduce power consumption by 8.7 times.
It's better than a human but not quite as good as an insulated spring.
It requires tons of high performance custom parts.
Yes. Which is the big problem with robotics. No volume and high tooling cost. With enough money, something like Big Dog or Atlas can be built, with large numbers of custom moving parts. But the price tag is in 8 figures.
Other than the industrial robot arm people and the vacuum cleaner people, nobody is making money in robotics. (Well, the individuals who were bought out by Google exited OK, but overall, the Google thing was a lose.)
Other than the industrial robot arm people and the vacuum
cleaner people, nobody is making money in robotics.
There are modest amounts of money being made in educational mobile robotics. (Lego, VEX, the FIRST consortium)
FIRST robots are moderately interesting, but cost something like $5K-$10K each. VEX and Lego robots are cheaper, but are basically toys. (I work with VEX) Think erector sets with microcontrollers bolted on.
Your argument sounds vaguely similar to the one that Jonathan Hurst (the founder of OSU's DRL/Agility Robotics) likes to make- he insists that Japanese robots focus on looking good while American robots focus on being practical.
I think this is an oversimplified way of looking things.
ASIMO isn't the only robot that Japan has made. The market for Six Axis Robot Arms, the industrial robots that are used in factories everywhere, is dominated by Yaskawa Motoman and Fanuc, both Japanese companies.
Meanwhile, the robots you cite (e.g. Cassie) are far from actually being practical- sure they're awesome and generate a lot of hyped up headlines, but they won't have much traction on the market for a long time.
It's an extremely hyperbolic way of putting it. Rule of thumb rather than real rule. There are companies that fall on all sides, but in general there's more diversity in American robots than Japanese robots.
Japan was at the forefront of robotics research, and still lead robotic manufacturing. However the cutting edge has moved on.
>Japanese robots are meant to look perfect. Russian robots are meant to look terrifying. American robots are meant to explore new algorithms or technologies. European robots are mostly meant to build cars.
Well that's a somewhat discriminatory way to look at things. A counter-example to some of the stuff you said about Japanese robotics is the work SCHAFT has done[0][1]. SCHAFT was a spin out company of the Tokyo JSK lab that came up with some revolutionary new electrical actuators. They dominated the first DARPA robotics challenge because of this and got bought up by google. There are european robots that explore new algorithms and technologies[2][3].
But if you really want to talk about robots that make cars, Japan leads the world at making them. And this is what matters. Sure, America might have the best biped robot in the world right now, but Japan has the tooling to mass produce it on a large scale.
They dominated the first DARPA robotics challenge because of this and got bought up by Google.
Which screwed them up. That still annoys me. Google bought up most of the leading robotics startups in 2013 and ran them into the ground. I wonder what happened to the people. Did they end up in other parts of Google, probably working on making people click on ads?
Many of them left. Some are still there working on things related to robotics, such as Verb Surgical. I'm sure a few became more traditional software engineers, although I don't know any personally.
You typically hear this sentiment (Japan is the best at robotics) wrt humanoid robotics, especially ASIMO[1]. ASIMO is basically just a really smooth suite of soft skills. Facial recognition, voice, HRI, and consumer-friendly hardware. The hard skills underneath are extremely highly optimized but fundamentally weak and outdated by over 20 years. ASIMO runs on the same hardware and algorithms from the 90s except for batteries, computer speed and sensor accuracy. In the US we have been extremely inventive with hardware design- eg all-plastic mass-manufacture BAXTER, or ATLAS, which is largely hydraulic. The newest generations of ATLAS have hydraulic actuators integrated into the frame.
ASIMO and most japanese robots use a variation on ZMP walking methods, which has the characteristic high-knee, ankle-heavy look. It's extremely inefficient and unstable. Russian robots use this too. Other robots in the US, Europe and even in China use much more efficient, flexible methods separated by a couple generations of new algorithms. Take Cassie[2] from OSU's dynamic robotics lab. Pretty clearly far ahead of anything in Japan in stability, speed, power[3] and efficiency, built by grad students from scratch. Compact series elastic actuators with HZD algorithms.
Japanese robots are meant to look perfect. Russian robots are meant to look terrifying. American robots are meant to explore new algorithms or technologies. European robots are mostly meant to build cars.
[1]: https://www.youtube.com/watch?v=AEJeIUTValE
[2]: https://www.youtube.com/watch?v=Is4JZqhAy-M
[3]: https://www.youtube.com/watch?v=tWVci9qS7Ds