Tractor makers play it tactically For as long as the market remains inaccessible, the tractor manufacturers will keep to them- selves, and work on roboticising their tractors in piecemeal fashion. Only Fendt once present- ed a small field robot, but the product’s status is unclear. Perhaps it serves as a warning to field robot manufacturers? Tractor manufac- turers are playing a power game: remember that, with RTK-GPS ex-works, the ability to au- tomatically turn on the headland, and technol- ogy that enables the tool to act on the tractor, state-of-the-art tractors are already not far from autonomous.
The Dutch company Precision Makers already demonstrated in the past that it is indeed pos- sible to completely roboticise a tractor; the technology exists. Full-liner companies have the capital, the dealer network, and soon also compact (electric) tractors that they will be able to roboticise. No universal field robot will be able to compete with them. Bear in mind that they not only have the tools in-house, they also have both the platform and the opportunities to invest in deep learning software. The starting shot has been fired: last year, John Deere bought Blue River Technology, a start-up specialising in weed identification
“Tractor manufacturers will soon seize on it”
Tijmen Bakker obtained his PhD on field ro- bots ten years ago, and has developed and built one himself. He takes stock of past and future developments. Expectations for field robots were high around 2002. “I interviewed many people back then for my doctoral research. When it came to weed removal, many people felt that field robots would become common- place within 10 years.” During that time, he also developed a working robot himself (see photo). He expected the last few technical problems to be resolvable within a reasona- ble period of time, but it proved more diffi-
cult. After completing his doctoral research, Bakker started his own business focusing on robotics for road construction. Developments appear to have been fairly stagnant during the last 10 years. Bakker qual- ifies that observation: “Not in practice. Field robots are never used on a large scale, but the technology has seen a great deal of develop- ment, particularly in relation to deep learning. I expect to see rapid progress over the next few years.” This fairly new form of artificial in- telligence could perhaps remedy the earlier is- sues. Bakker points out two major problems: one being safety, and the other the fact that
using AI in combination with a robot. The robot is now nowhere to be seen, but the website now features photos of the smart spraying technology behind a John Deere trac- tor, and therein lies the key factor. To cultivate more effectively, it is not strictly robots that we need, but rather smart tools. Whether they will be attached behind an autonomous tractor or an autonomous robot in the future is of no particular interest. It is all about the tool of the future. Robot manufacturers that fail to work on the basis of that practice and that realisa- tion merely form part of fleeting hype, not a long-term trend towards greater autonomy.
Tijmen Bakker is owner of Tyker Technolo- gies, that focusses on robotising in the build- ing industry. He got his PhD in 2008 at Wage- ningen University in the area of field robots.
The DLG-Feldtage in 2010. At the time everybody expected field robots to be common good by now. However, hardly anything happened in the fields. Arable farms seldom use one.
there is no driver’s insight regarding assess- ment of the output produced by the tool. The tractor driver is aware of many things simulta- neously that are difficult to define for a robot.” The nature of the market isn’t helping. “Ro- bot manufacturers are small businesses. They do not have the means to alter the playing field. But if tractor manufacturers know that field robots will become a success, and the underlying technology is fully developed, they will seize on it immediately. What’s more, if tools soon become intelligent and the safety issue is resolved thanks to deep learning, it will make little difference wheth- er the tools are attached behind a robot plat- form or an autonomous tractor. However, in specific markets, such as weed identification and hoeing technology, I think that special- ised manufacturers could enjoy success.”
▶ FUTURE FARMING | 27 August 2019 35
PHOTO: HENK RISWICK
PHOTO: HENK RISWICK
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
