higher fruit

The low fruit in robotics is what we see around us now – most automation is either very limited in scope or else occurs in a controlled context, because even the most sophisticated machines are barely capable of operating in a truly uncontrolled environment, populated with with unknowns. The higher fruit remains largely hypothetical, for the moment.

But, at least as importantly, the low-hanging fruit involves fitting robots into what’s is already happening, as by substituting machines for people doing more or less the same work. Conversely, the higher fruit involves taking advantage of robotic technology to transform what's happening, substituting better practices for those that are currently convenient, or at least conventional. But transformation is, by its nature, disruptive.

I’d like to begin by laying out a conceptual, two-dimensional graph of possibilities, expanding upward and to the right from a point of origin. Let’s call the horizontal axis time, with what’s technically possible now near the left edge and what will sooner or later become technically possible arrayed to the right, according to how far in the future it can be expected to come within our reach. The vertical axis is a little trickier. At time zero (the present), you could call the bottom of the graph ‘current practice’ and points higher along the left edge represent increasing departures from current practice, all possible within the constraints of current technology, but which could be expected to involve greater investment and/or to encounter increasing resistance from vested interests, or other forms of economic or social inertia. Let’s label the vertical axis ‘disruptiveness’.

As you move to the right (applications of technology not yet within the state of the art), data points above the horizontal axis represent applications which, even if they were to become possible tomorrow, would still involve varying degrees of disruption of current arrangements. Current arrangements being financial, legal, social, habitual, or any combination of these, but specifically including current practice as what would be most directly disrupted.

Now, for the sake of simplicity, let’s reduce this graph to a four-celled, two-by-two grid (see graphic), with the lower-left cell representing current practice, the lower-right cell representing predictable advances in technology that, once available, can be applied without disrupting current arrangements, the upper-left cell representing transformations that are technically possible now, but which can’t be applied without disruption, and the upper-right cell representing what will become possible at some point in the future, given predictable advances in technology, but which can't be applied without disruption, unless current arrangements change in the meantime.

That upper-right cell is a kind of Pandora’s Box. It contains many wondrous things that, were they imminent, would nevertheless be characterized as impractical, because they somehow run afoul of current arrangements. Nevertheless, this is where you’ll find much of the potential of robotics.

Take the notion of Personal Rapid Transit (PRT) as an example of something overlapping between the upper-left and upper-right cells. PRT is an application of robotics to transportation which has been knocked about for several decades. Technically, it’s not such a great challenge that a determined effort couldn’t get it working acceptably on a large scale in fairly short order, a few years at most, but that determined effort can’t happen, because deploying such a system would require a large investment in new infrastructure and would work to the disadvantage of those who are already invested in some aspect of automobile transportation, including car owners since that infrastructure would inevitably mean taking some space from existing streets and some funding from their maintenance. Instead we get cruise control and automated lane following in otherwise conventional cars running on conventional roadways, and PRT research lives perpetually on the back burner, making slow progress.

To bring this back around to the application of robotics to agriculture, from a certain point of view it's easy to overlook the disruption involved – displacing monoculture, heavy equipment, and petroleum-based fuel, fertilizer, pesticides, and herbicides – as a net gain in itself. But not everyone would agree, certainly not most of the companies whose primary business is marketing such products to farmers. And most farmers would surely be pushed far outside of their comfort zones if the whole vision of replacing conventional agriculture with what is essentially robotic gardening were to be ready today and imposed by fiat tomorrow. Wherever you find yourself on that spectrum, it must be obvious that the application of robotics to plant care in a very detailed manner, on a plant-by-plant basis, if scaled up to a significant percentage of the land area currently under cultivation, holds the potential to be hugely disruptive. Because of this, I’m not particularly surprised to see research of this sort proceeding on a shoestring, privately, or outside of the US.

On the other hand, its potential for disruption is no measure of the intrinsic value of a potential technology, and some technologies are needed, even desperately needed, despite that they are likely to run afoul of current arrangements. I would argue that the application of robotics to making the best practices of horticulture scalable is one of these, perhaps even the poster-child example.

This is the fourth post in a series: Part 1, Part 2, Part3.

aligning research for long-term relevance

“Luck is what happens when preparation meets opportunity.”
— Seneca the Younger

“Change brings opportunity.”
— Nido Qubein

No one wants to spend their life doing something that ceases to matter before they've even reached retirement, yet who can say which enterprises will wither and which will prosper, and for how long. We make our choices and take our chances that fate and fashion will be kind to us.

On the other hand, some things are predictable. One such is the increasing price of petroleum and products derived from it, over a matter of decades, as easily pumped supplies dwindle, as the techniques involved in extracting other supplies become both more expensive and less acceptable, and as calls for a gradually escalating tax on carbon emissions gain traction. Another is that the already high concentration of greenhouse gases in the atmosphere will climb even higher before leveling out, with dramatic consequences for climates worldwide.

Yet another is that given other pressures on agriculture, from climate change and the rising price of fuel and other petroleum derivatives, practices that result in soil erosion and the mineralization of what remains will become even less popular than they are already, perhaps to the point of becoming illegal. In the future, if tillage is to be used at all, contour farming might be required wherever there's enough slope for water to collect in puddles or run off the land rather than percolating into it. But, realistically, routine tillage is a problem no matter how you go about it, ten thousand years of precedent notwithstanding. No-till farming is gaining in popularity – although, at present, frequently depending heavily on herbicides, something else that's becoming increasingly unpopular. There has to be a better way.

So say you're a professor, postdoc, or grad student with an interest in agricultural robotics. To what should you apply your efforts? If you climb onto the bandwagon of the latest fad, whatever it might be, you run the risk that you're work will never be put to practical use. Conversely, if you simply work to automate practices that are currently common, you risk seeing your work devalued as those practices are displaced altogether by some new approach to farming. What to do?

The answer to that will necessarily be largely driven by your technical background and interests, which piece(s) of the complex technological puzzle that is robotics you are comfortable with and/or motivated to work on. Happily, some technologies are broadly applicable, and will be useful no matter what farming system is in use. One such example is UAVs that are large enough to carry an array of sensors and robust enough to deal with vigorous winds; the information they can provide will be valuable no matter what is happening on the ground.

Other technologies are more tied to specific farming practices. This is commonly seen in row cropping, where crops are planted in rows that are far enough apart for the wheels of smaller tractors or self-propelled sprayers to fit between them, with the spraying equipment and implements pulled by those tractors also designed to fit between the rows. But most such equipment is designed for use with narrow rows separated by wider gaps, so just the change from narrow rows (single lines of plants) to wide rows (densely planted swaths, perhaps eight feet wide) renders much of this equipment useless. A more dramatic shift, such as a switch from monoculture to polyculture, especially a polyculture that incorporates perennials, could force us to rethink our entire approach to field work and idle most existing equipment.

That existing equipment represents a huge investment, and therefore its removal from service can be expected to encounter a huge amount of inertial resistance, which is why no change of this magnitude could possibly happen overnight. It will take years, perhaps decades, before new equipment, suited to a new way of doing things, can be designed, factory production ramped up, and existing inventory replaced. Considering that this new way of doing things is likely to parallel or precipitate other changes, for example in the nature of commodity markets, this gradual transformation may be a good thing, as it will provide time to make other adjustments.

What will this new way of doing things look like? First it must be far less destructive of the environment than current methods. There are some objective measures for this, for example: how much soil is blown or washed from the land each year, contributing to the dust load in the atmosphere and the sediment load in streams and estuaries; how much of what remains on the land is organic material (decaying plants and humus); the amount of fertilizer, pesticides, and herbicides that find their way into the atmosphere and into aquifers and rivers; and the loss of biodiversity (plants and animals) caused by the destruction of natural ecosystems to make way for agriculture. Ideally it should be regenerative, gradually healing the destruction already done.

But, at the same time, it must be productive on a scale at least approaching that of conventional modern agriculture, as measured in terms of food value (calories, protein, dietary fiber, vitamins, minerals, etc.) per acre per year. To sacrifice this would be to invite destruction of the last remaining wildernesses to make way for expansion, and/or famine. Some slack in the need for production can be created by a shift away from grain-fed meat and dairy products.

This combination of requirements, that agriculture continue producing food of acceptable quality in adequate amounts, while at least becoming environmentally benign, and without further expansion onto land not already committed to agricultural production, is the minimum acceptable scenario. It is also a formidable challenge, requiring intensive management to make the best possible, gentle use of available land. If that intensive management had to be provided by people, we might need to move upwards of 25% of the population back into agricultural production. Happily, robotics offers an alternative approach, one that doesn't involve forcing people back onto the land.

But, even using intensive methods, how is it possible to accomplish maintaining or increasing productivity without sacrificing environmental concerns? Many believe the answer to this is agroecology, the use of agricultural methods that mimic (and, on the edges, blend into) natural ecosystems, which at the minimum means both polyculture (intermingling of companion plants) and permaculture (the inclusion of perennials). That agroecology should also be free from reliance on routine tillage is not yet so widely appreciated, however one has only to glance at the floor of any mature natural ecosystem to see what nature has to say on the subject. Tillage is best accomplished by worms and other burrowing critters.

Routine tillage excepted, most other gardening techniques can be used, and most (perhaps all) of these can be performed by robotic machinery. Because the qualities that differentiate robotic systems from ordinary mechanical equipment are exactly what the new, intensive approach will call for, and because the scale of agriculture dwarfs most other enterprises, the necessary, if gradual replacement of existing equipment described above represents a tremendous opportunity for roboticists and robotics companies, and a guarantee that work invested to bring it about will remain relevant for a long time to come.

This post is the third in a series. (Part 1, Part 2)

design options, and factors which impinge upon them

This is the second post in a series, which began with what operations should a ‘cultibot’ be able to perform?.

If you've read the masthead for this blog, you'll know that it is about how robotics can assist with the application of horticultural methods on an agricultural scale, so, even though I've been talking about gardening, the real goal is to apply gardening methods (or at least the attentive attitude of a careful gardener) over the entire landscape, ‘from sea to shining sea’, wherever land is managed as opposed to being left entirely wild. That's a tall order, of course, and no single system could conceivably cope with the vast range of conditions implied.

So, to simplify matters somewhat, I'll confine myself to consideration of land primarily engaged in production for market, whether for food, fiber, fuel, or any of the other reasons we put land to productive use, and to systems engaged in the management of land for production.

In this context, it's reasonable to divide plants into two basic categories, crops and weeds. Any such system must be able to differentiate between the two and nurture crop plants while eliminating or at least suppressing the growth of weeds. Differentiating plants is more easily accomplished after they have grown beyond the seedling stage, but controlling weeds that grow from seed is more easily done while they are still seedlings. So one design choice is whether to attempt to differentiate seedlings and eliminate weed seedlings before they've had a chance to root deeply.

Differentiating seedlings can be made considerably easier if you know very precisely where the crop seeds have been planted, so anything appearing more than a very short distance from one of these locations has a high probability of being a weed. Beyond that, a robotic gardener could use visual information (from gross morphology to the vein pattern of the seed leaves) and/or sniffing for volatile compounds. Visual information can be acquired from a considerable distance, relative to the size of the seedling, whereas chemical sniffing requires close approach, and is generally better accomplished by a small device.

Either way, once the decision to take out a seedling has been made, there remains a choice of methods. If the device which detected it is small, light, and locally supported, meaning that its weight rests on nearby soil, then a mechanical extraction of the seedling from the soil (uprooting it) may be the most reasonable approach, the main concern being that that it grasps the correct seedling.

On the other hand, if the device is remotely supported, meaning that it is essentially suspended amid the foliage, mechanical uprooting may still be an option, if it also possesses one or more quick-moving appendages, but the time involved will be a more pressing consideration, as a remotely supported device would necessarily represent a larger investment, so there will be fewer of them and each must handle a larger area. But other options are available to a remotely supported device. It might use a laser which can be retargeted as fast as a mirror can be repositioned, or a miniature turret that fires ice pellets, and if it uses an arm, that arm might slice through the seedling with a thin jet of high pressure water rather than grasping it.

So much for weed seedlings, but they're the easy example. Let's consider weeds, like some grasses and shrubs, that spread by rhizome. A rhizome is a horizontal root, running just below the surface, occasionally sending up stems which appear from above to be independent plants, but which are actually part of a larger, robust organism. If a plot is heavily infested with plants that propagate by rhizome, they cannot be eliminated without also destroying whatever crop was in the ground at the time. The approach that works most reliably is to frequently survey for emerging stems of these plants, pulling them up with as much of the rhizome as comes along fairly easily, and to keep at it until the rhizomes run out of stored energy for putting up new stems and rot in the ground. This is an operation that really can't reasonably be performed by a locally supported device, because it can require significant force to pull up such a stem, much less the attached rhizome. A locally supported device might clip them off at the soil surface, but to be effective, that would need to be repeated even more frequently than the uprooting.

Something a small, locally supported device might do would be to apply very small doses of some specific herbicide, such that it would be absorbed into the rhizome itself before killing the stem, but this begs the question of whether herbicides are to be used at all. (If they are to be used, then direct application of small doses to the weeds to be controlled is the obviously best approach.) Something a remotely supported device could do that a locally supported device really couldn't, would be to use an electromagnetic sensor to trace a signal transmitted from one section of rhizome to locate another spot where it could be exposed and then heated by passing an electrical current through it. Another option would be to inject steam next to the stem, killing the stem and a short segment of rhizome.

If we were to go on to consider other operations, for example harvest and dealing with the coarse plant material left over after harvest, it would quickly become apparent that the larger, remotely supported machines are necessary, whereas the smaller, locally supported devices are probably optional, although the most efficient approach might well be to use both in a complementary fashion, the gardening system mentioned earlier, perhaps even including insect-sized devices that fly among or crawl over the plants themselves.

Strictly speaking, devices suspended from a wheeled platform that always follows the same tracks, a practice which is beginning to gain traction in precision agriculture circles, would qualify as remotely supported for the purpose of this discussion, even though part of the surface of the field is sacrificed to supporting the weight of the machines. Where the wheels of those machines don't run, the soil remains uncompressed. Placing gravel on the tracks they do use would help limit damage. Another option would be to install rails or troughs that double as channels for water transport. Still another option would be to support the platform on legs that only ever placed their weight on particular spots. Any of these options would help avoid the rutting of continuous paths that could lead to erosion.

Other design choices include sensors and the sorts of information gathered and the types of manipulators provided. A garden is a very complex environment, most of which is delicate, and while that delicacy makes the design and control of manipulators more difficult than it would otherwise be, getting adequate information into the machine, and deciding what operations to perform, is by far the greater challenge.

Laser scanners of various sorts could prove very useful in mapping foliage. Imaging radar could help locate stems that are hidden by foliage. Video, particularly if high definition not only in pixel density but in color depth (and ideally in splitting the spectrum more finely than the usual RGB), combined with telescopic optics, could make differentiation of seedlings far easier. Chemical sensing, mentioned above, could be used, for instance, to determine the ripeness of fruit and to detect the presence of some infestations and diseases. Very acute hearing could help with the discovery of insect activity. Infrared video would help with locating warm-blooded animals. Touch would be important in making it possible for manipulators to reach through foliage or pick fruit without damage.

All that said, the most fundamental choice isn't any of the above, but rather what sort of management regime to support. I'll address this issue in the next installment.

what operations should a ‘cultibot’ be able to perform?

The list of necessary operations might seem pretty straightforward. A robotic gardener or gardening system (more than one type of machine, each specializing in a subset of the overall range of operations) would need to be able to accomplish the same basic tasks as a human gardener: seedbed preparation, even if it's only a narrow hole through mulch and/or ground cover; planting, watering, weeding and/or suppressing weed growth; applying nutrients in one form or another; intervening to control animal pests and diseases if they threaten to become a problem; tracking the progressing ripeness of the crop and combining that information with the weather forecast to decide when to begin harvesting; and, of course, the harvest itself. Also, to get the best possible productivity from the land and the greatest benefit from the investment in a robotic gardener or gardening system, that machine or system should be able to start seedlings in a greenhouse and then move them out to the open field, inserting them through mulch and/or ground cover.

Then, too, there are other operations which are either optional or less commonly understood to be necessary: either collecting leftover coarse plant matter (corn stalks, tomato vines, and so forth) for centralized processing (grinding, optionally followed by anaerobic digestion producing methane gas, followed by aerobic composting) or simply grinding it into small bits in the field and leaving it where it falls, for mulch; limited relocation of soil to create and maintain a topology which slows the runoff of excess precipitation, without creating pools that persist hours or days after the latest storm has passed; relocating larger stones found in the soil to create permeable dams across grassed drainage ditches, where they can help slow water movement and help prevent it from cutting through the sod; and dredging muck from the bottom of surge ponds and distributing it over the field, to recover nutrients and prevent them from overloading any permanent ponds, much less passing downstream.

But, if you're going to have robotic machinery doing all of this, there are other operations you might want it to perform, operations which machines that have sensors and processors and well as effectors can relatively easily be made capable of performing. Examples might include: keeping detailed records including when each seed was planted and what the soil temperature and moisture content was at the time, when the sprout emerged from the ground, and how fast it grew; monitoring each plant for early signs of infestation, disease, nutrient deficiency or toxicity, waterlogged soil, and so forth; and targeted pruning to control infestation and disease without drastically reducing leaf area.

In the next installment, I'll begin to address design options and mechanical details relating to making machines capable of performing the basic operations listed above.

In agriculture robots replace job vacancies

Here's the bottom line…

So as new types of machines find their way into the fields, rest assured that they are not, for the most part, displacing workers who would otherwise be in those fields, but rather, in some cases, moving them into more technical work as robot tenders, and in other cases taking over work that fewer and fewer people are willing to do for the money it pays, and that, for those few who are displaced, there will be other farmers nearby anxious to hire them. Meanwhile, a new industry will be germinating.

See the full article on Robohub.org

What's in a name: sustainable agriculture vs. agroecology

Names are important in much the same way that book covers are important; they suggest what lies behind them. But there is an additional way in which names are important, which is their resilience in the face of attempted cooption. Does the chosen name continue to robustly represent what it was originally intended to represent, or does its meaning become diluted by misapplication?

There are quite a few names available for use in referencing the practice of growing food (including herbs and spices), flowers, animal feed, forage, fiber, fuel, lubricants, and chemical feed stocks, all in harmony with nature, most of which take the form of an adjective followed by one of the following nouns: gardening, farming, horticulture, agriculture, viticulture, etc. The set of adjectives in use in this manner includes biodynamic, biodiverse, organic, regenerative, resilient, and sustainable. (To complicate matters further there are also some terms relating to specific practices, like permaculture and polyculture, that are important to any such discussion.)

For many of us, there is a tendency to use adjective-noun combinations from this set almost interchangeably. We understand what we're attempting to invoke better than we understand the nuanced distinctions between them, so it seems to make little difference, except that this results in a profusion of terms for essentially the same thing, and some of these term combinations are more susceptible than others to being used in ways that lack clarity or are even contradictory to what we would mean by them, meaning that there is a danger that others hear us saying something different from what we meant.

“Sustainable agriculture” is, unfortunately, one such term. While it originally meant something like ‘a set of practices which can be continued forever without wearing out the soil or reducing yield’ it has come to mean other things to other people, including something on the order of ‘a set of minor adjustments that allows agribusiness to continue doing essentially what they're doing now for another decade or two without catastrophic collapse’.

Another term which is more difficult to fully comprehend, but less susceptible to misuse is “agroecology” (“agroecological” as an adjective). Properly understood, it implies all of the other adjectives listed above, except some of the more arcane aspects of biodynamics, and adds one important concept, cooperation between human-managed production and the native ecology of the land in use, such that you can't tell where one ends and the other takes over.

Just as there is a confusion of terms with respect to the practice of managing productive land in harmony with nature, so too there are many terms for robots designed to assist in this process, nearly as many terms as there are robots of this class, it would seem. Rather than slog through the list, I'll get straight to the point, which is that, after years of using “cultibot” and “cultibotics”, I've found another pair of expressions that I prefer. “Agroecological robotics” nicely defines the field in a manner that resists dilution, and “agroecobot” works well enough in reference to actual machines. I'll probably continue to also use “cultibot” and “cultibotics”, but understand that I intend them only as shorthand for machines designed to assist in the practice of “agroecology” (which itself implies biodiverse, organic, regenerative, resilient, and sustainable practices), with a view to making that practice scalable to millions of acres.

CMURobotics RI Seminar: Mel Torrie of Autonomous Solutions

As guest speaker for a CMURobotics RI Seminar, titled Lessons Learned Bootstrapping a Robotic Vehicle Company, Mel Torrie of Autonomous Solutions (Petersboro, Utah), describes how he got into robotics in the first place, why he made the jump from academia to a startup, how that startup survived their "near-death experience", what the company has been doing since, and what he's learned along the way. There is a strong agricultural theme, both in his original motivation and in the history and current operation of Autonomous Solutions.