AI and Robotics in Agriculture in Japan [video]
www3.nhk.or.jp
www3.nhk.or.jp
ps: I heard there were tiny leaf cutting quadcopters on the market in Europe.
But at some point I realised this: nature is technology. It's a super-advanced nanotech that is not of our design, and which we can't control... yet.
Our current solutions may seem better, but that's only because they're crude attempts at directly optimizing for narrow set of goals. Planes may be faster than birds, but they don't self-heal, self-fuel, and don't do centimetre-precision maneuvering in a complex environment.
Nowadays I believe that our technology has a lot to learn and steal from nature - e.g. materials, energy-efficiency, self-replication. Better metal will look more and more like flesh.
Note though that even though these robots and algorithms are inspired by biology, in terms of functionality or design they typically only play lip service to the real thing.
At the end we'll only get to understand our own world and own bias. Then we may reconsider the meaning of life and our cultures.
For me, since the dawn of human age, we've been mostly taking baby steps, and only in the last two or three decades we've entered puberty. There's still a lot for us to learn, and nature is a constant reminder of that.\
For me, the fly is not amazing just because it's a fly - it's amazing because it shows how many things we have not learned... yet. It's a constant reminder that we're nowhere near the peak of what's possible, and a constant encouragement to try and scale that peak.
- Ken Wilber's Integral philosophy attempts to bridge "soul and sensibility". It includes a discourse on modernity and how it breaks with tradition, how post-modernity is not the answer. He pulls in work from other philosophers, one idea being that modernity breaks the Great Chain of Being.
- Christopher Alexander, the architect who developed (with collaborators) the idea of pattern languages (which later directly influenced the schools of object-oriented patterns and human-interaction UX design) originally developed the pattern language that ends up incorporating traditional modes of design. That is, by creating a pattern language where it is impossible to create a bad, incoherent design, and is simple enough for end-users to use, you end up with design that is always contextually appropriate and sensitive to local community values while adhering to global principles discovered through modernity.
He then went on to develop the ideas around "centers", and "centers of centers". (With "centers of centers" having a parallel with Wilber's Integral philosophy, or Koestler's work on holoarchy).
This is no longer about the "Western" world or "Western values". China, for example, is going through a transition which struggles with modernity vs. traditional. My favorite example is the discussion by the Chinese elites about the film Kung Fu Panda.
We can learn a lot from nature -- in the sense that we can learn a lot of knowledge. And you are right, we are nowhere near the peak. Maybe I am reading into your words too much, but it feels like there is a lot of enthusiasm you have for technology. That resonates with me.
However, I agree with the other guy -- it is hubris. How I get there has to do with wisdom not being normative. We might be able to gain a lot of knowledge, but we have not been gaining much wisdom.
There are other frames I can get into -- for example, Eisler's "Chalce and Blade", Mander's "In the Absence of the Sacred", Mazis's "Trickster, Magician, and Grieving Man". I think we very much have an arrogance which comes with technology, in our attitudes around it and what we want to do with it, and the many consequences around how we use and abuse technology.
For me, a fly is not just amazing because it shows how much knowledge we have yet to learn about a fly. To use the language of mystics: there is wisdom in _being_ the fly, one that is non-obvious.
But the thing is, the more I know about the universe, the less I want to "know". Or at least the less I want to turn into application, business and all that; which in this is case is often hubris, ignorance (selling things hidden behind marketing talk and shiney package), for the purpose of being the best, owning a market, "advancing" the world (when most people need more basic things but alas).
The latter part assumes a "consciousness as first principle" rather than as an emergent property of matter -- that is, why would consciousness configure itself and experience in this particular way ?
Also, thanks to this I just learned that "biopunk" is a thing.
Thanks for mentioning Diamond Age, I'll add that to the queue too.
There is a brief summary of the history of Schafmeister's approaches (and why he thinks direct copying of protein-based mechanisms from nature will not work) in this talk: https://www.youtube.com/watch?v=8X69_42Mj-g
I actually asked him why he thinks "direct copying of protein-based mechanisms from nature will not work". He had a pretty smart answer for that, which I unfortunately don't remember anymore :(.
Here's the video from last year's ELS.
At the beginning of it he actually explains some of the reasoning - i.e. proteins are cool and powerful, but a) too hard to design, and b) too fragile.
There are bacteria that survive in space for a period. Earth could easily have been seeded by outerspace bacteria with DNA. Carbon, Hydrogen, Oxygen are not rare elements in the Milkyway. If the ingredients are plenty, why isn't there intelligent life booming in the galaxy.
Plausible reason: after a certain amount of intelligence, the species becomes unstable and self destructs.
They have been doing it because they saw labour shortages in the future because of declining population they are solving a local problem. So far Japan has been the economic model many people show about what can go wrong. But the way I see it when the robot revolution comes well actually the robot revolution is already here when the ai revolution comes countries with declining and aging population will be a lot more stable than countries with young and growing population with little means to support or earn a living.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
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.
[0]: https://www.youtube.com/watch?v=C3JCd7ooILo [1]: https://www.youtube.com/watch?v=fwoFjzLZ5rQ [2]: http://roboy.org/ [3]: http://www.rsl.ethz.ch/robots-media/anymal.html
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?
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.
Japan was at the forefront of robotics research, and still lead robotic manufacturing. However the cutting edge has moved on.
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.)
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.
[1] http://www.kollmorgen.com/hi-in/service-and-support/knowledg...
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.
[1] http://mime.oregonstate.edu/research/drl/publications/_docum...
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.
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.
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.
Press video for the 2016 VEX World Championships. Thousands of people. https://www.youtube.com/watch?v=0Y1YiGZv_F4
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?
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.
This is what I'm working on: http://www.kokonaut.com
Agrobot. Strawberry harvester. Nice vision system, too slow and too fragile.[2]
DeepField Robotics. Bosch automatic weeding robot.[3] Well-built, but too expensive.
Mechanical engineering for dirty environments is hard. But there's a lot of good machinery working in dirty environments and getting the job done.
Computer vision, at last, works, which makes intelligent agricultural implements possible. But the computer vision component isn't a big part of the system; it's basically a smartphone-sized piece of electronics. Most of the problems come from the moving parts.
[1] https://www.youtube.com/watch?v=mS0coCmXiYU [2] https://www.youtube.com/watch?v=RKT351pQHfI [3] https://www.deepfield-robotics.com/index-en.html
The govt and pop at large want to keep Japan Japanese. It's not a new religion. They've been that way since before cmdr Perry. I can respect that.
I live in India. My country has 300M people living in acute poverty - less than $1/day.
These are the people who would likely benefit most from immigrating to a developed country with better healthcare and opportunities.
Yet:
1. These people would be liabilities in a developed nation since they have no transferable skills apart from manual labor. Most can't even read or write.
2. In 99% of cases, these people wouldn't even know anything about immigration, refugee status, etc.
Open immigration essentially helps people who already have the knowledge and means to immigrate. These are not the poorest and most in-need.
The Indian immigrants moving to America or Europe can have perfectly okay lives in India. I don't begrudge them for moving, but for western people to assume a philanthropic stance for taking them in is wrong. You aren't helping the poorest; you're helping the "doing okay" segment of the population.
Yet, legal roadblocks make mechanization unfeasible in India (laws against owning farm land beyond a certain level, making mechanized farming effectively unfeasible).
These roadblocks are mostly because of political reasons. Politicians know that if they were to make mechanized farming possible, they'd see massive unemployment and hence, massive loss of votes.
So the same thing is going to happen to any other technological advancement that affects this massive vote bank: it will be stopped at a political level.
Silicon Valley ambitions tend to fail hard when confronted with the reality of acute poverty and the kind of political situations it engenders.
The people I'm talking about are from states where 40% of the population lives below poverty line and the literacy rate is still at 60%.
Or do you just not care for those 300 millions of citizen?
In Tokyo these days, you can go to a culture festival and not have to see police stationed every block with assault rifles and flak jackets.
They're watching and learning from us, that's for sure.
Honest question.
In fact, even if UKIP did win outright, I doubt there are enough qualified instructors to train a significant number of police with firearms in just a few months. I think there are only about 1000 officers in the UK with firearms training at the moment.