PHOTO: KOOS GROENEWOLD
PHOTO: TAMME VAN DER WAL
PHOTO: LEX SALVERDA
GLOBAL VIEW ▶▶▶
nutrient stress, unfavourable soil conditions, competing weeds, pests or diseases – or it might even have been caused by a malfunc- tioning sowing machine. The most important thing to do with satellite data is to verify in the field what has caused the vegetation stresses which the satellite has revealed. Combining data from different sources, for instance a soil map, a height map, weather data and agro- nomic knowledge, will certainly help farmers to narrow down the list of possibilities.
‘Natural colour’ images (RGB) of the same location taken by two different satellites. Left by Superview at 0.5 m resolution and right by Sentinel-2, four days later, at 10 m resolution. This comparison shows how features appear at different resolutions. Check out the fields on the left side of the farm (bottom left quarter). The farmer clearly harvested some fields between 23 and 27 July.
Maybe use a co-bot until the robot is truly autonomous
BY BRAM VELDHUIZEN T
here are many ag-robots for sale. Does this mean you shouldn’t buy a new tractor any-
more? I don’t think so, robots are not a one- on-one replacement for tractors. Any farmer knows how to use a tractor. A new one, even when it’s a different type, doesn’t take long to get used to. That’s different with robots, even the ones that look like a tractor. With a tractor you go to the field and basically start your operation there. With a robot the op- eration starts in the office, making a plan (or route) along which the robot will operate. You define the field, the GPS guidance line to fol- low, and all the operational settings. This might be the hardest thing to do. Do you know all the machine settings in advance? You usual- ly tweak them during the job, changing set- tings whenever the situation in the field re- quires it. This ability to change is something I haven’t seen with robots yet. All require planning the operation from behind your desk. Luckily most allow for minor changes in the field. But, when it starts to drive, you think you can go home because “the robot is autonomous”,
Checking and re-adjusting the settings is business as usual. Robots are not yet good enough to just push the start button and leave them alone.
right? Then you realise that the robot lacks a system for checking the quality of its work. Hoeing for example looks like a simple opera- tion. If you drive accurately along the crop rows, what could go wrong? Well, quite a lot... What do you, or even a novice operator, do when you see something clogging up the blades? You stop and free up the machine. But robots can’t see this, let alone ‘understand’ what they are seeing. So they will drive on re- gardless, ripping half of your crop out. This doesn’t mean that I think robots are a
waste of time and money. It just means that that you shouldn’t buy one as a direct replace- ment of a tractor. Before investing, you need to consider how you could best use it. I think that for the next few years this doesn’t mean using an autonomous robot, but rather a co- bot, a robot that works in conjunction with a person. For example a tractor driver does a tillage operation and a light robot does the seeding, no longer compacting the loose soil. Or maybe the tillage is done by a robot as well, and the operator checks both jobs.
▶ FUTURE FARMING | 20 November 2020 67
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 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
