COMMENT COMMENT
Khasha Ghaffarzadeh research director, IDTechEx
Deep learning for agchems
R
Data and AI will become an indispensable part of the general field of crop protection, of which agrochemical supply will become only a subset, albeit still a major one.
obotics is quietly transforming many as- pects of agriculture, including agrochemi- cals. Intelligent and autonomous robots can enable ultra-precision agriculture,
changing bulk commodity chemical suppliers into speciality chemical companies and requiring many agchems businesses to regard data and artificial intelligence (AI) as a strategic part of their crop protection offerings. Computer vision is already used commercial-
ly. Simple row-following algorithms, for example, enable a tractor-pulled implement to automati- cally adjust its position, relieving the pressure on the driver to maintain an ultra-accurate driving path when weeding to avoid damage to the crops. Now, these implements are also being equipped with full computer systems, allowing them to image small areas, detect the presence of plants and distinguish between crop and weed. The system can then instruct the imple- ment to take a site-specific precision action to, for example, eliminate the weed, and in future even to recognise different crop and weed types. This technology is currently run on a small
scale and only for specific crops. The implements are custom built and ‘ruggedized’ for agriculture. They are not yet fully reliable and easy to oper- ate, and the upfront machine costs are high. Nonetheless, the direction of travel is clear: data will increasingly take on a more strategic role in agriculture. This is because the latest im- age processing techniques, based on deep learn- ing, feed on large datasets to train themselves. Indeed, a time-consuming challenge is assem- bling large-scale sets of tagged data. In the near future, we will see image process-
ing algorithms focused on a particular crop or weed type. In time, these capabilities will expand, allowing the algorithms to be applied to a wider set of circumstances. In parallel, and in tandem, with more accumulated data, algorithms will offer more insight into the status of different plants, laying the foundation of ultra-precision farming on an individual plant basis. Agriculture is a challenging environment
This comment covers topics reported in depth in Agricultural Robots and Drones 2017-2027: Technologies, Markets, Players (http://www.
idtechex.com/agri).
for image processing. Seasons, light and soil conditions change, whilst the plants themselves change shape as they grow. Nonetheless, the ac- curacy threshold is lower than in many other ap- plications such as autonomous general driving. Consequently, algorithms can be commercially rolled out in agriculture far sooner. Agriculture is already a leading adapter of autonomous mobility technology. Here, the
autosteer and autoguide technology, based on outdoor RTK GPS localisation, are already well-established. The technology, however, already moving towards full ‘level-5’ autonomy. The initial versions are likely to retain the cab, enabling the farmer/driver to stay in charge, ready to intervene, during critical tasks such as harvesting. Unmanned cable versions will also emerge when technology reliability is proven and when users begin to define ‘staying in charge’ as remote fleet supervision. The evolution towards full unmanned au-
tonomy has major implications. It may give rise to fleets of small, slow, lightweight agricultural robots or ‘agrobots’. These fleets today have limited autonomous navigational capability and suffer from limited productivity, but this will, however, change as designs/components be- come standardised and the cost of autonomous mobility hardware goes down. Now we can see the silhouette of the agro- bots of the future: small intelligent autonomous mobile robots taking precise action on an individual plant basis. These robots can be con- nected to the cloud to share learning and data, and to receive updates en masse. They can also be modular, enabling the introduction of differ- ent sensor/actuator units as required. Individu- ally, however, they will never be as productive as today’s powerful farm vehicles, but they can be in fleet form if hardware costs are lowered and the fleet size-to-supervisor ratio is increased. So what will all of this mean for the agro- chemicals sector? First, data and AI will become an indispensable part of the general field of crop protection, of which agrochemical supply will be- come only a subset, albeit still a major one. This will mandate a major rethinking of the chemical companies’ business model and skillsets. Sec- ond, non-selective blockbuster agrochemicals – together with engineered herbicide resistant seeds – may lose their total dominance because the robots will apply a custom action for each plant, potentially requiring many specialised selective chemicals. This will not happen overnight. The current
approach is highly productive, particularly over large areas, and off-patent generic chemicals will further drive costs down. The robots are low- lying today, constraining them to short crops. Achieving precision spraying using high robots will be a mechanical and control engineering challenge. But these changes will come, diffusing into general use step by step and plant by plant.
36
09
09 | 2017 17
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
