news    views    talk    learn    |    about    contribute     republish     archives     calls/events

Tag : horticultural robotics

Robohub is an online platform that brings together leading communicators in robotics research, start-ups, business, and education from around the world.
by   -   January 21, 2013


Powered by sunlight alone, and working at 500 meters per hour, VITIROVER can cover about a hectare per hundred hours of operation. If your vineyard is larger than that you’ll want more than one. VITIROVER cuts grass and weeds to within 2-to-3 cm of vine bases, without damaging the vines.

See on

by   -   December 23, 2012

On using robots to make gardening scalable to millions of acres…

You might wonder why I want to turn land management over to robots. Is it because I’m such a geek that I think everything goes better with robots? No, not really. Sure, I think the technology is cool, but I’m not eager to factor human beings altogether out of any activity, not even those that are dull, dirty, and/or dangerous.

I am, however, eager to see the benefits of replacing methods designed to spread a human operator’s time as thinly as possible with methods which reintroduce attention to detail to plant cultivation. Granted, that attention would, for the most part, be provided by robotic sensors, processors, and algorithms, but that has an upside as well as a downside.

by   -   December 10, 2011

Historically, at least since the mechanization of agriculture began in earnest, there have been two primary measures of agricultural productivity, the amount that could be grown on a given acreage and the percentage of the population required to feed all of us. The former, measured in bushels or tons per acre, has generally been increasing and the latter, measured in man-hours per bushel or ton, decreasing for at least the last hundred years, albeit more so for some crops than for others. (A consequence of the decreasing need for labor to produce many staples has been the migration of the children of farmers to cities, where they helped keep the cost of labor low in other enterprises.)


Corn (maize) is a good example of a crop for which these conventional measures of productivity tell a story of brilliant progress, with the result that corn is cheap enough to use not only as livestock feed, to be converted into meat and dairy products, but as the feedstock for production of ethanol for fuel, competing with fuels refined from petroleum pumped from the ground, rather remarkable considering that corn kernels represent only a small fraction of the biomass of a corn plant and that fermentation and distillation aren’t particularly efficient processes.


Crops that fair less well by these measures include many vegetables and most fruits, which have been becoming gradually more expensive, especially as compared with grains that are easily handled mechanically, but even compared with meat and dairy products from grain-fed livestock. One major consequence of this has been that people generally consume more grains, meat, and dairy products, and less fruit and vegetables than they once did, before the mechanization juggernaut got started and while vegetable gardens were still common.


So, by an altogether different measure, how healthy the average diet is, mechanization has been a disaster, so far. I say “so far” because the essential problem is that, so far, mechanization has favored crops consisting of hard, dry seeds, that are easily handled in bulk, making other crops needed for a balanced diet relatively less affordable. In happier economic times this would matter less, as people would simply pay the premium for a healthier diet, but the times being what they are people are scrimping however they can, including with the food they consume.


There are other ways of measuring productivity: energy use*, soil gain or loss*, water use and contamination*, and the degree to which a given practice denies space to native flora and habitat to native fauna. By any of these measures, conventional mechanization comes out looking at least shortsighted if not dimwitted. *(per unit produced)


So is the answer to turn back the clock on agricultural technology, to replace the plow with the hoe and the drill with the planting stick? I’m not prepared to make that argument – although I’ve no doubt others would – aside from noting that gardens are a better use of many urban spaces than are lawns, and there is no further need for rural communities to supply cities with cheap labor, since those cities are already well supplied, and many rural areas suffer from depopulation.


Instead, my position is that we need to take mechanization to the next level, replacing dumb machines suited only to bulk operations with smart machines capable of performing well-informed, detailed manipulations, for example controlling weeds by selectively pulling them from the ground or pest caterpillars by picking them from plants (unless they’ve already been parasitized, as by wasps) rather than by applying poisons.


Given machinery with an adequate array of sensors and a sufficiently broad range of optional actions, applying best practices becomes a matter of mating these with processing power connected to an expert system, and of programming.


It gets better, because the same system that works the land can be used to improve the expert system through experimentation and, in routine operation, by accumulation of data to which statistical methods can be applied, and can also be used to improve the crops themselves, as for instance by leaving the best formed, most insect resistant cabbages to go to seed.


The bottom line is that this approach can make available the mechanical equivalent of an attentive expert gardener, at a cost, given predictable economies of scale, that would make possible the wholesale replacement of conventional, traction-based machinery and methods with more adaptable machinery bringing a whole new repertoire of methods to bear, one far better suited to the production of the fruits and vegetables that have been becoming unaffordable under the current regime.


As for the other measures of productivity mentioned above, such machinery, since it wouldn’t need to turn soil in bulk and could operate long hours without continuous supervision, would consume energy at a relatively low rate, suitable for supply from solar panels or via the grid from renewable sources. It could operate through continuous ground cover, all but eliminating soil loss, and with minimal use or complete non-use of herbicides and pesticides, reducing soil and water contamination. Ground cover, mulch, and the humus accumulating from decaying roots can also reduce the need for irrigation, and the ability to create local varieties through seed selection based on the health of maturing plants can further reduce it, as well as helping to adapt more quickly to climate change. Making room for native species, something that can only be accomplished in conventional practice by leaving land completely undisturbed, becomes a matter of programming the system to leave certain species alone, wherever it finds them, even to the extent of tolerating some crop loss to native fauna, and to leave anything it can’t identify alone until it can be identified.


Such machinery might not be able to compete with conventional practice in the production of corn and other bulk commodities, at least to start with, but it also wouldn’t consume prodigious amounts of petroleum-based fuels. Moreover, development and rapid deployment of such machinery would drive the growth of a new, potentially domestic industry, one that would also work to the benefit of materials recycling efforts, more efficient transportation, and on and on.


The R-word I haven’t yet mentioned is robotics. While such machines probably aren’t what most people first think of when robots are mentioned, their creation and production falls squarely within the discipline of robotics, composed as they would necessarily be from robotic technologies.


Reposted from Lacy Ice + Heat, via Cultibotics.

by   -   January 4, 2009

For the time being, it probably doesn’t make good economic sense to dedicate sophisticated machinery to managing a patch of ground that’s unprotected from the elements, when it might just as well be working inside a greenhouse, where it actually can operate 24/365, and where it won’t need the structural strength to stand up to gale force winds.


On the other hand, greenhouses are most useful when combined with regular gardens and used seasonally to start plants earlier than they could be started in the open, or when the shade from other plants would impede sprouting or development. Even a relatively frail machine, better adapted to spending its time indoors, might venture out in calm weather, long enough to set out plants it had started in trays and peat pots, provided it was sufficiently mobile.


This scenario, a machine that does the tedious work of planting seeds and tending plants in a greenhouse, moving them out to open ground when conditions allow, is what might be termed a natural starting point for the development of such machines, a more limited, more surmountable engineering problem than a machine intended to perform all aspects of land management. A machine applied this way need not be able to perform absolutely every horticultural operation to be useful, nor would it need to be able to deal with a completely uncontrolled environment.


It’s very likely that there are other such natural starting points for the development of cultibots. Collectively, these natural starting points represent a threshold of minimal investment before a return on that investment can be forthcoming. Once that threshold has been crossed, at any point, incremental improvements should be adequate to insure that machines which can handle the whole job are eventually produced, and the return on that initial investment could be very sweet indeed.


There’s another, equally important threshold to consider, the automation of the production of these machines. So long as they are hand-crafted prototypes, they have no chance of competing economically with hand labor, or, as is more likely, with the transportation of produce from milder climates. Mass production will get them into the game.


Self-reconfiguring factories that not only build such machines but which can also replicate, by building the equipment for new factories and the machines to assemble them, will drive down the cost to the point where the logic behind it all becomes inexorable, but by that point we’re no longer talking only about machines for land management, and there had best be very solid safeguards in place. The point of mentioning this scenario in the context of cultibotics at all is that land management may be the one application of robotics where the size of the potential market could justify the investment to cross this threshold. Once crossed, of course, the technology would be generally applicable.


Reposted from Cultibotics.

by   -   November 22, 2008

This a subject for research and development, of course, but it’s my ‘job’ to make this vision as accessible as I can, to both anticipate what that R&D might produce and describe it in plain language.


First, these machines will necessarily have sensory components. Digital cameras and microphones are practically a given, but they may also have infrared imaging, radar and/or laser scanning, chemical sensors to provide something akin to a sense of smell, pressure/stress sensors for a sense of touch, probes for soil moisture, temperature, pH, O2 content, and nutrient availability, weather instruments, and some means of locating themselves very precisely relative to the boundaries of a field or other stationary reference. Compared to most machines, they will have available a rich collection of information about their environments, rich compared even with what human senses provide.


Next, they will have significant computer processing power, sufficient to take the data streams from all of these sensory devices, find patterns in them, compare them with each other and with historical data (including the exact position of every seed and when it was planted), create and update a real time 3-dimensional model of their immediate surroundings, locate items of interest within that model, choose a course of action, and send the detailed instructions to the machine’s moving parts, closely monitoring their progress.


Finally, they will have various moving parts, likely including high resolution or specialized sensory components that can be sent in for a closer look. Those moving parts might include a range of grips, from fine tweezers to something strong enough to uproot small trees, mechanical snips, lasers with enough power to fry a meristem, high-pressure water jets capable of slicing through the stem of a plant, fingers to move other plant material out of the way, a vacuum for sampling air at ground level or removing insects, sprinklers and sprayers, trowels of various sizes, and, of course, the soil probes mentioned earlier. Such tools might be combined into sets incorporated into units which could be plugged onto the ends of articulated arms and quickly switched out.


That’s a basic outline, but we need to return to the data processing hardware and the code it runs to fill out the picture, since it can make the difference between an expensive toy and a productive machine that more than pays for itself. A major task the processor must perform is resource scheduling, and to do that effectively it must sort actions into those that can be performed without moving anything massive (slow) and without switching out tool units, those which require either movement or a tool switch but must nevertheless be accomplished before moving on, those which can be left until a future pass over the same area but not indefinitely, and those which can be left undone unless it becomes convenient to do them. Efficient scheduling also means mapping the movement of even the smallest parts so they proceed smoothly from one thing to the next, without having to retrace their paths more than is unavoidable.


An important point to be taken away from the previous paragraph is that scrimping on computing hardware and software is likely to prove counterproductive, by reducing the overall capacity of the machine disproportionately. We should expect the computing components to represent a substantial fraction of the overall cost of the machine, and we shouldn’t be surprised if they also consume a substantial fraction of its energy budget. Better to invest an extra 10-20% to make a given physical machine capable of performing the work of two, and to invest 1 or 2 kilowatt-hours to save ten.


Something which should be apparent from this mental exercise as a whole is that what’s being proposed is largely a simple extrapolation of technologies which already exist. There are already mechanical arms and mechanical grips; there are already sensors and various means of controlling machine operation. What’s mainly missing is the software which would turn data streams into a 3D model in a horticultural context, choose what to do, schedule resources, and map out the details. That’s a lot left to be done, requiring a significant investment for a long term payoff, but it’s a fairly straightforward problem, and divisible into more manageable chunks. Let’s get to it!


Reposted from Cultibotics.

by   -   November 18, 2008

What would it look like? How would it be powered, and how would it transmit power to the parts that need it? What actions would it be capable of performing?


There’s no single, right answer to these questions. Rather there’s a wide range of potential answers, some of which will likely prove more workable than others. Let’s look at some of the possibilities.


What would it look like? Almost anything, from a snake-like device slithering along the surface, to what appears to be little more than a single wheel rolling about, to a platform supported by long, spider-like legs, to a beam supported at each end by wheeled trucks. It may turn out that the best arrangement is a mixture of larger and smaller machines, with the larger ones designed to never put their weight on soil being cultivated.


How would it be powered, and how would it transmit power to the parts that need it? They could get their power directly from the grid, from engine-driven generators, from wind generators, from photovoltaic panels, from concentrating solar collectors, or simply from batteries or other energy storage. Any such machine will need at least a small amount of electricity, to power the electronics. Mechanical power could also be electrical, but needn’t be. It might be provided via compressed air. Delicate, articulated parts might be moved via fine cables or wires, much as our own fingers are moved by tendons linking to muscles in our forearms.


What actions would it be capable of performing? Planting seeds, of course, beyond that the possibilities are nearly endless, but even the placement of seeds can be accomplished in many ways.


In conventional agriculture, seeds are typically inserted into the soil in rows, through an opening created by a disk (a rotary knife), and covered over by a roller. This is an efficient method of planting a large area to the same crop, or even to a mixture of crops with seeds of approximately the same size, if you don’t mind running the planting device and the tractor pulling it over the same soil surface through which the seeds will have to sprout and in which the sprouts will have to grow. Most such planting devices require the soil first be prepared into a seedbed, meaning that plant debris from previous crops must either be turned under, with a plow, or broken down by a combination of tillage, decay, and weathering, to form a relatively uniform surface, easily broken into small particles. A few such planting devices are capable of placing seeds through rough plant debris, rendering the preparation of a seedbed unnecessary, but they’re still mainly used to sow a single crop to a large area.


A robotic gardener would also need to be able to place seeds not only through plant debris but between standing plants. It would do so one at a time, perhaps very rapidly, like a sewing machine, but still one at a time, and far more precisely than any bulk planter, positioning them in the most advantageous microenvironments available. Even when planting in bulk, the use of rows would be optional, and in many cases a honeycomb-like pattern might prove preferable.


Weeding might be accomplished by identifying weed seedlings and removing them while still in the sprout stage. Undesirable plants that propagate by root spreading could be controlled by injecting steam below the surface, wherever they appeared. Insects, like aphids, could be controlled by removing infested leaves. Diseases could be controlled by removing infected plants. Nutrient deficiencies could be identified early and treated quickly. If plant debris needed to be reduced to mulch it could be clipped off at ground level and shredded, without disturbing the soil.


In each case the action taken would be local and specific, rather than applied to an entire field, and generally would not involve moving large amounts of soil around, a practice which wastes both energy and soil fertility.


But the essential requirement, without which this whole scenario would be futile and meaningless, is that the machines must operate autonomously, puttering through their days without constant human supervision. They must have both the ability and the latitude to choose what to do next for themselves. Considering they must also operate in uncontrolled environments, this is the greatest challenge.


Reposted from Cultibotics.

by   -   January 13, 2008

A very long time ago, 1981 to be precise, I intended to pursue a masters degree in agronomy, with a focus on how well various agricultural systems supported balanced nutrition for those dependent upon them. I didn’t even last through the first semester, assembling the prerequisites, but that was the goal I was aiming at.


Fast forward to 2008.


Take your standard recommendations as to what constitutes a balanced diet; work up a meal plan for a week, and from that a shopping list; go to any supermarket and price out your shopping list. You’ll find that some items, basically those that can be grown and harvested without the use of hand cultivation, are relatively inexpensive, and others, those requiring manual labor for at least one step in the process of getting the crop to market, are relatively more expensive. It’s all too tempting to just go for the less expensive items and leave out the more expensive items, maybe using vitamin supplements to make up for what’s missing, maybe not.


This is a hidden cost of current agricultural practice, that it makes a nutrition-poor survival diet relatively inexpensive, while a really balanced diet is unaffordable to many.


Intensive cultivation using robotic land management could do a lot to make currently expensive produce, and therefore a balanced diet, more affordable.


Reposted from Cultibotics.

by   -   September 14, 2007

I’ve been thinking about this – the application of robotics to horticulture on a scale large enough to replace (some significant portion of) conventional agriculture – for a very long time, and I’m prone to glossing over points that may not seem at all obvious to others.


For example, if these robots that I’ve been talking about aren’t engaged in tillage, what are they doing? That remains an open question, since there are undoubtedly useful techniques I haven’t yet thought of, but, for an idea of what might be possible, consider what gardeners can accomplish with their own two hands and short-handled tools. That’s the scale of manipulation I have in mind, working with individual plants and the spaces into which they’re to be inserted.


Would such robots have human-like hands? [Probably] only in the vaguest sense; they’re likely to have manipulators with opposable, finger-like appendages. Would they stir the soil like a gardener does with a trowel? Maybe. Would they use something like snips to do pruning? Probably, although there might be a better approach to pruning than mechanical snips, like a high velocity water jet (such as are used to cut steel in some industrial settings).


It isn’t necessary, nor even desirable, to exactly replicate the set of techniques used by a gardener. Such machines would need a repertoire of techniques sufficient to manage a garden, but while some of their techniques might seem quite familiar, others might be quite beyond the capability of a human gardener.


For example, if a machine were able to identify a weed seedling early enough, it need only destroy the seedling’s meristem to interrupt the growth of a weed. This requires very little energy, and might be accomplished by a precisely targeted, high velocity water droplet [or flechette-shaped bit of ice, or even a pulsed laser]. Using this method, a machine might deal with several weed seedlings per second, limited only by the speed with which it could identify them and reorient the nozzle [or mirror], all without any disruption to surrounding plants.


More tenacious weeds that sprout from roots could be pulled out, except that they sometimes break off just below the soil surface, and their roots may pass below plants you’d rather not disturb. An option would be steam injection, through a tube inserted next to the stem. Another option would be coring, removing a cylinder of soil around the stem to a depth of a few inches. Yet another option would be to use electrical current to heat the weed. These are all techniques that a gardener might use, but, except for grabbing ahold of the base of the stem and pulling the plant out, they aren’t common.


Compared with weeding, seed planting would be relatively simple. On the other hand, transplanting seedlings started elsewhere would be more challenging, although mechanical systems for this purpose probably already exist and could be used as a model [and the use of compressed peat or compost pots, which are left in place to enrich the soil, would simplify the process].


Dealing with mid-season issues, like insects and nematodes, microbial infections, plant nutrient deficiencies, and so forth, is hugely complicated, and will require considerable development effort. But small-scale machines have an advantage in that they can deal very specifically with the effected leaf, plant, or location, and also in that, because they would revisit each location frequently, they should be able to catch problems early.


Harvest is also somewhat complicated, since each crop type presents its own set of challenges. What works for wheat doesn’t work so well for maize. What works for tomatoes won’t be sufficient for pumpkins. [Specialized] hardware attachments may be needed in some cases.


This vision isn’t a fantasy, but there’s a lot of work to be done.


Reposted from Cultibotics.

by   -   August 17, 2006

This blog is about a vision of a future in which the tending of productive land has been turned over to autonomously operating machines that approach this task much like a master gardener would, one plant or one small patch at a time.


Potential advantages include reduction or elimination of the need for petroleum-based fuels, fertilizer, and pesticides, an increase in the variety and value per acre of crops produced, a huge improvement in the sustainability of agriculture, and a revitalization of rural society through a more interesting, varied environment and the creation of technical jobs (maintenance, etc.). Detailed, automated land management could also help rescue endangered plant species from the brink of extinction.


I’ll be gradually filling out this vision and substantiating each of the points above, while at the same time mentioning any related developments I might learn about and accumulating a list of related efforts (academic, commercial, etc.).


Reposted from Cultibotics.

Editor's Picks