PHOTO: AIFARMS
FARM OF THE FUTURE ▶▶▶ Making AI affordable BY MATT MCINTOSH I
n September 2020, Future Farming report- ed that the Center for Digital Agriculture at the University of Illinois launched the Artificial Intelligence for Future Agricultur-
al Resilience, Management, and Sustainability (AIFARMS) Institute. The ultimate goal is to de- velop a prototype autonomous farm where low-cost AI-driven systems enable breeders and farmers to achieve significant improve- ments in profitability while reducing their en- vironmental impact. This involves finding the best ways of using AI to promote more effec- tive autonomous farming and livestock man- agement, better environmental resilience, as well as soil health management and improve- ment. Think of aspects such as welfare-pro- moting herd management or labour-saving technologies, soil health and nutrient flow monitoring. The other part of the AIFARMS approach focuses on solving “foundational AI goals.” According to Vikram Adve, the institute’s director and professor in the Univer- sity of Illinois Computer Science Department, this term refers to AI development problems that are common to all applications of the technology.
Speech or facial recognition is one example. This could be used to help identify and moni- tor individual animals within large herds. But gathering enough data to recognise human faces, let alone the more difficult animal vis- age, is very difficult. Facial recognition re- quires a colossal amount of data for the learn- ing program to process. “The larger the data set the better, but acquiring those data sets is very expensive,” says Adve. “We are exploring how can we make machine learning more accurate with limited data.”
Two-way communication Another foundational barrier relates to how humans interact with AI systems. Adve says good two-way communication is essential. But AI algorithms are not always easy to inter- pret and they struggle to understand human communication. “How do you make algo- rithms interpretable for humans, not just a
For some American researchers, affordability and smaller-scale practical applications are at the heart of AI innovation. The University of Illinois is developing this kind of autonomous farm technology.
black box with an answer at the end? Also, it would be far better if AI could handle casual speech or text.” A robot in the field should be able to both ‘see’ and communicate that it saw leaf blight plainly – rather than through a complex interface. Overall, finding solutions to these and other foundational AI problems involves pursuing more financially feasible and user-friendly approaches.
Smaller scale equals costs As more efficient data management and better communication drive down the cost of AI tech- nology, it can increasingly be applied to small- er machines. Adve says such advances would be a boon to smaller farmers. “Our approach is trying to start with small robots that are just the size of a two foot cube,” says Adve. “You could use hundreds of them to do the work of one large harvester, and use them to do a wide variety of jobs like seed breeding or weeding.” Indeed, small robots have already
been acquired and used by AIFARMS research- ers for a variety of tasks, including cover crop seeding, weeding and agronomic work. The goal remains to successfully expand this pool of workable jobs. Harvesting, however, is one area where small robots hit a practicality barri- er. That said, they can in some cases operate between rows and under the crop canopy. This opens up a range of potential jobs, although Adve highlights the value of mechanical weed- ing as herbicide resistance becomes more fre- quent and more severe. This small-scale focus is what sets AIFARMS apart from other farm-focused AI initiatives. While Adve believes both are doing good work, using large equipment can make the challenge of high technology costs more difficult. “The robots we are using cost in the range of $ 7,000 to $ 10,000 each and we’re hoping to bring the price down,” he says. “This will increase the number of robots farmers can use.”
Creating small robots can make AI financially viable smaller farmers as well. ▶ FUTURE FARMING | 20 November 2020 63
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
