A new computer-controlled tractor leaves the driving to the Global Positioning System.

written by Caroline Seydel

illustrated by Erin Herzog

    A farmer sits on his front porch, reading The Economist. His wife is checking her stocks on the Internet. The farmhand is driving to town for chicken feed.

   Who’s plowing the field? The tractor, of course.

   This scenario isn’t as fanciful as it seems. Life on the farm could be changed dramatically by a new kind of tractor – one that plows perfect rows, day or night, all by itself. Using satellite signals for guidance, this new tractor could help ease the monotony of endless plowing.

   Those of us who think corn comes from the grocery store may not appreciate the difficulties farmers face. Driving a tractor isn’t like driving a car. There are no yellow lines. To plow straight, the farmer must use his hood ornament – a gun sight – to line up the tractor with a distant landmark, like a notch in the mountains. By aiming for that notch, he can keep the tractor’s path straight within about a foot.

But he’s also pulling a plow, typically 30 feet wide. It doesn’t matter how straight the tractor drives if the plow jostles off course. The driver must not only stay focused on the distant mountain, but constantly turn and look to make sure the plow (or any other implement he tows) is still in line.

   Poor visibility also makes driving tough. A farmer needs a windless day to spray fertilizer or pesticide. But in areas like California’s Central Valley, a calm day may bring dense fog , making it impossible to visually line up rows.  In the future, an automated tractor could solve these problems. By calculating its current position and the path it needs to follow, a robotic tractor can drive a precise path, perfectly matching rows to one another in the thickest fog or the dark of night.

   In the Global Positioning System (GPS) lab at Stanford University, engineers led by professor Bradford Parkinson have developed an automatic system that uses satellite signals for steering control. Such control, according to the researchers, saves time, increases farm efficiency, and lowers overall costs.


   A GPS receiver relies on a system of 24 satellites Earth. To determine its precise position, it uses a geometric principle called triangulation. The receiver measures its distance from three different satellites, obtaining a unique set of coordinates. Imagine long strings stretching from the receiver to each satellite. The receiver determines the length of each string – the distance to each satellite. Because it knows the positions of the satellites relative to Earth, it can determine the one location on Earth where the ends of all three strings could meet, and that is its location.

   A standard GPS receiver is accurate to within 100 yards. To achieve higher accuracy, the tractor uses a special technique to refine the satellite signals and measure distances more accurately, allowing it to fix its position within one inch. The tractor also needs to know in which direction it’s traveling and how fast. For these measurements, it compares the position of a receiver aboard the tractor with the position of a nearby receiver, called a base station, placed in the field. Comparing the two positions tells the tractor where it is relative to the base station.

   The tractor project evolved out of a system Parkinson’s lab developed for landing planes automatically using GPS. In 1993, when graduate student Mike O’Connor was looking for a project, he and Parkinson thought applying the technology to ground vehicles was an obvious move.  "In manufacturing, anything that’s dull and boring and dangerous is automated," Parkinson says, which naturally brought to mind farm tractors. O’Connor took on the project, and after successfully rigging a golf cart to drive straight lines, he and Parkinson talked John Deere into supplying them with a tractor.

   Bob Mayfield of Deere and Co. says he’s enjoyed working with the Stanford team on the project. "Deere brings the experience of dealing with customers," he says. "We’ve been able to direct them toward the things they need to look out for," such as soil conditions and hillside plowing.  Although Mayfield says that helping Stanford develop a GPS-guided tractor has been worthwhile in "just proving that it was possible", Deere may someday benefit more tangibly from the relationship. If Stanford receives a patent for any of this work, Deere can negotiate exclusive license to that patent. So far, however, no patents have been issued, partly because the basic techniques aren’t new. Triangulation, for instance, has been around for centuries.

   For farmers, the potential benefits of a fully automatic tractor are many. When plowing a field normally, a farmer uses marker arms that stick out from either side of the tractor, marking the edge of the row by dragging a line in the soil. The farmer uses the line to orient himself on the next pass. Each arm costs about $4000, O’Connor says, but the autotractor doesn’t need them.  Consider the increased productivity from day-and-night operation, and farmers could save real money. A tractor with a preplanned path drives faster than a human driver trying to stay on course while monitoring an unwieldy implement. And, unlike a human-driven tractor, the autotractor can retrace its steps flawlessly.

   When plowing beds for row crops, such as corn, the tractor digs beds, where the seeds are planted, and furrows, which are the narrow trenches between the beds. A slight wiggle in the beds results in seeds falling into furrows when the farmer comes back to plant. Seeds that fall on furrows don’t get watered and fertilized efficiently. They don’t grow. For every seed that doesn’t become an ear of corn, the farmer loses money. With an autotractor, the seeds go in the beds every time.

   Early in development, the researchers tested a tractor prototype in a dusty Fresno field. The automated tractor was pitted against an "expert" human driver in a contest of speed and accuracy. The autotractor was accurate to within three or four inches, but the human driver could stay only within six or seven inches, even with good visibility. The average farmer is accurate to within about a foot.

   Most telling, however, were variations in the driver’s speed over time. "It was a revelation," says Parkinson. Several times during the trial, the human driver came to a complete stop. When the researchers asked the driver why he had stopped, they found that dust clouds had become so dense he could not see the front end of the tractor.  "I was astounded," says Parkinson, "because I thought people were exaggerating [about the dust]. They were not exaggerating."

   Parkinson envisions a day when a farmer will electronically monitor a fleet of autotractors. For that to happen, however, the system of GPS receivers and computer processors that makes the autotractor independent must stand up better to the physical challenges of the field.

   The current crop of students in Parkinson’s lab is making the tractor smarter and faster. Graduate student Dave Bevly is adding sensors to fill in if a nearby tree or barn blocks the GPS transmission. Sensors that measure orientation and acceleration allow the tractor to maintain control for 10 to 20 seconds, until the link to the base station is reestablished. So far, his sensors keep the tractor true to about a foot. That’s not accurate enough for plowing row crops, but it’s acceptable for less sensitive tasks. "It’s about as accurate as a human," Bevly says.

   Bevly is also studying how to keep the tractor accurate at heart-pounding speeds of up to 15 miles per hour, up from the current limit of 2 to 6 mph. He’s using mathematical models of the tractor’s physical properties to predict how it will move in a given situation.

Despite all the gadgets, though, the autotractor is just a mindless machine, doing what it’s told. That’s where graduate student Andy Rekow comes in. He’s teaching the tractor how to adapt to its environment.

   To steer the vehicle accurately, the control mechanism must predict how the tractor will react to a command. For instance, a tractor can’t turn on a dime. Turning the wheels 30 degrees may guide the tractor into a gentle U-turn, or it may send the tractor fishtailing out of control, depending on soil conditions, slope, and speed, among other factors.

   Rekow compares the tractor’s task with a human learning to ride a bicycle. The inexperienced rider twists the handlebars hard to the left or right to turn the bike. The rider predicts what the bike will do when he turns the wheel and mentally compares the reaction of the bike to what he expected. If the bike veers off course, he knows to turn the handlebars more gently next time. Similarly, the tractor’s controller must learn how hard to turn the wheels at a given speed to move the tractor a certain way.

   Besides speed, many other factors influence how the vehicle responds to the controller. Rekow has shown that the tractor is up to 25% more accurate if it adapts to variable physical conditions, such as wet soil, rather than simply using the same commands for every situation.

Think of the bicyclist now riding through sand. The wheels won’t behave as they do on pavement. The rider must adjust for different forces acting on the tires. Rekow’s controller must learn to make these adjustments. It compares the actual result of a steering command with the predicted result and issues future commands accordingly. In mud, for instance, the tractor’s front wheels slip more than the controller expects. The controller predicts a certain reaction from the tractor, and one-fifth of a second later, it checks its prediction against the positions of the tractor body, the wheels, and the implement being towed.

   "If they don’t agree," says Rekow, "it knows how to adjust itself so that next time, it will make a better prediction."

    If all this seems a little futuristic, it is. Farmers can’t buy fully automated tractors just yet. But they can move one step closer to hands-off plowing.

   Two companies currently sell GPS equipment that farmers can install into existing tractors. IntegriNautics, of Menlo Park, CA, was founded in 1994 by several Stanford students, including Mike O’Connor. The company had begun by selling the airplane-landing systems, and when O’Connor graduated from Stanford in 1998, he brought the tractor project to the company. The other company, Beeline, is based in Australia and has been selling its tractor kit there since 1997. It will begin marketing to American farmers in fall 2000.

   O’Connor calls the autotractor system "a potentially money-saving step for farmers." Beeline’s John Hill agrees, saying, "It lowers per acre input cost and improves yields. … It will return the value of the investment in six to twelve months."

   Both companies sell a similar kit, consisting of a base station, which stays at the barn, a processor and touch-screen for inside the tractor’s cab, and a set of antennae that bolt to the top of the tractor. Beeline’s kit also features a gyroscope for measuring the tilt of the tractor. The gyroscope allows the controller to compensate for swaying due to the sloshing of fluids in the tractor’s sprayer tank.The processor tucks in beside the driver’s seat, and the touch-screen mounts to the right of the steering wheel. The driver chooses instructions in English or Spanish, then selects his site from a menu set up by the farmer.  Once the tractor has pinpointed its starting position, it prompts the driver to "Begin Autosteer." The driver touches the onscreen button and the tractor takes control, lining up the first row and plowing away. When the tractor reaches the end of a row, he must turn it around manually. Simply by taking the wheel, the driver regains control.  Using an onscreen map, the driver lines up the next row as best he can. When he pushes the autosteer button again, the tractor adjusts itself to the exact starting position of the next row and resumes plowing, perfectly straight. The tractor will continue counting off rows until the driver decides the field is finished and drives back to the barn.

   The autotractor controls only the steering; the human driver controls the throttle. Unlike city driving, there is no cycle of braking and accelerating, only "forward," "reverse," and "stop." The tractor cruises along at a constant speed until the driver decides the day’s work is done.

   Although the tractor is capable of making the U-turn by itself, some situations require a human’s judgment. Suppose a highway runs along the edge of the field. If traffic is heavy, the driver must decide when it is safe to pull out. The tractor doesn’t know any better than to blaze into traffic. "Most customers don’t really want us to do the turns," says engineer Tom Bell of IntegriNautics. "A human being is still the best sensor. If there’s a cow in the way, or a drunk sleeping it off on the side of the field – God forbid we build a driverless system and it kills someone." Perhaps a completely driverless system is pretty fanciful, after all.

   But robotics research in other fields, such as obstacle avoidance, could compensate for the tractor’s weaknesses. Although Stanford is the only place where GPS is being used for automatic control, a robotics team at Carnegie Mellon University in Pittsburgh, for instance, are also working with John Deere to build a better tractor.

   IntegriNautics is loaning their system to willing farmers who try it and provide feedback. Overall, O’Connor says, farmers are enthusiastic. "They’re actually almost bragging to the neighbors about it," he says. "Anything that increases productivity, they like."

   He tells the story of one test farmer who plowed his highway-side field with his marker arms sticking straight up. When the neighbors came over to find out why he wasn’t marking his rows, he showed off his new gadget.

   Another farmer took his autotractor to a neighbor’s almond orchard. Beds for planting trees must be 22 feet apart – not 30 inches, as with smaller crops. At that distance, marker arms are useless. To visibly mark where to plow, each row is flagged by white sandbags – a time-consuming and boring job, costing the farmer about $5 an acre, O’Connor says. To the neighbor’s amazement, the farmer with the autotractor plowed more than 200 acres of almond fields without a single bag.

   Yet farmers are a conservative bunch. They must balance their costs against the crops’ selling price. "If they start running wild experiments on their cost side," says Parkinson, "they’ll go broke."

   Beeline hasn’t set its U.S. price yet, but the IntegriNautics kit retails at just under $50,000. "I don’t think it’s an exorbitant price for what it does," says Albert Lockwood, a potato farmer in Idaho. “The vehicle and implement are a $200,000 machine. If you can get a little more productivity out of it...” he shrugs. “It seems like these high-tech things are necessary to compete.”

But Lockwood has 6,000 acres and 14 tractors. His farm has doubled in size in the past year. Some smaller farmers aren’t sure they can afford the initial capital investment. "There’s not a lot of money to be made in farming," says Jack Chapman, who farms 1,000 acres in Merced, CA. "If you only have 1,000 acres, you’re not going to spend $48,000."

   Other farmers feel the system isn’t truly useful yet. "If it’s foggy, [then] it’s rainy and it’s wet and you’re not going to be in the field that much," says Anthony Stegall, who grows cantaloupe in Mendota, CA. "Let me know when you can run five tractors from a joystick in your office."

   Still, some farmers think the autotractor is a good idea whose time will come. Danny Cotta, of Tipton, CA, is already using a simpler GPS system to map his 300 acres of corn and wheat for more efficient fertilizing. "For every little ripple, you miss-spray and it costs you money, you miss-seed and it costs you money," he says. "If the right [tractor system] comes along, it would be a very valuable commodity."

   "We’re all going to be using it eventually," says Dick Reason of Tonopah, NV. Reason grows alfalfa and hay – not big moneymakers. "It’s only a matter of what you’re growing, if you can afford it. It’s like all those technologies," he says. "They’ll get cheaper in a few years."

   Parkinson predicts that if his team succeeds in making the autotractor "bulletproof," farmers will line up to get in on the action. "I’m being a visionary here," he says, "but I think it’s inevitable. … The economics are there." His eyes twinkle as he tells another story of the expert driver in the dusty Fresno test field. While the research team watched from the sidelines, the driver rode in the autotractor as it plowed several arrow-straight rows. When the tractor swung around to demonstrate a circular pattern, however, it suddenly stopped. The driver got out, crouched behind it for several moments, then hopped back into the cab. The tractor drove on.

   Oh, no, Parkinson recalls thinking. What’s wrong with the tractor? When the driver returned, Parkinson approached him.

   "I want to buy one of these right now," the driver said.

   Dumbstruck, Parkinson explained it was only a prototype, full of delicate computer equipment, and not ready for real farm work. "Why," he asked, "do you want to buy it?"

   "One person, three tractors," the driver said simply. He saw Parkinson’s vision: a single farmer managing a fleet of robotic tractors, rather than paying drivers to plow the fields. He had stopped to get a better look at the perfectly aligned rows.

   Parkinson was astonished. " He never even asked me what the price was."


WRITER Caroline Seydel
B.A., genetic engineering, Cedar Crest College; M.A., biology (genetics), Stanford University
Internship: Popular Science (New York City)
BA, Anthropology, Univ. of Southern California
Homeworkhelp.com, Sunnyvale



Text © 2000 Caroline Seydel
Illustrations © 2000 Erin Herzog