The FIRA industry conference and show series is focused on autonomous field machines which have become of huge interest given labour shortages particularly in high value vegetable and fruit crops. This year’s show was held at the Diagora conference centre near Toulouse, France between 7-9 th December 2021 in a mix of face to face meetings and online presentations from across the world. The hybrid format worked well as live streaming is now fairly robust and there was excellent studio management so that even questioners appeared on screen live. In fact I found the video presentations easier to follow back in my hotel room chromecast to a wide screen TV rather than in the conference rooms where visual quality was sometimes poor and distant text was sometimes unreadable.
I had been hoping for genuine live demonstrations but every company resorted to video which of course is immune from real world problems. The robots move up and down rows on video across flat fields.
The biggest company in terms of sales appears to be Naio whilst the longest development cycle seems to be AgroIntelli’s Robotti which grew out of a Kongskilde project and is now in early sales mode. There was a great demonstration of robust simplicity from Swarmfarm in Australia with 20+ machines in the field. The full list of exhibitors is available on the website.
The basic format of autonomous field robots is of a steel frame with an independently driven and steered wheel at each corner. A mast on the frame gives elevation to cameras and antennas, Sensors are mounted around the frame for collision detection and data recording. Most machines have one or more tool bars and a 3 point linkage to mount third party implements such as hoes, seeders and even harvesting units.
Buses for power (electric and hydraulic) and data distribution are a key element attached to the frames. Machines are sized to standard widths for viticulture or horticultural implements. It was claimed that machine weights were 10% of conventional tractor and implement outfits. The system concept is ideal for no till or minimal till rotations. They do not have the power and weight for traditional ploughing and cultivating and they do not cause soil compaction either except in the tramlines. Given the need to reduce energy use and to sequester carbon in soils the autonomous systems offer huge advantages as well reducing the labour cost.
Most machines used either an off the shelf diesel engine powering hydraulic drive or a hybrid system using a small diesel engine to charge batteries and using electric drives. There was an interesting discussion about electric versus diesel versus hydrogen or fuel cell, The pragmatic solution is to use a modular approach that can be adapted as new power source technologies appear. A radical departure was the demonstration of a wireless charging station for batteries by Wiferion. The robot can drive to a shared station and wirelessly charge up with 93% of the power available from the associated power supply (mains, wind or solar + battery). This removes the need to fill up with diesel or plug in a power supply.
One limitation of the robots is that they cannot move from field to field on public roads under robot control due to the same legislation that controls autonomous cars and trucks. This is not a major issue for large farms within a ring fence with internal paths but something to be addressed to enable machine flexibility and sharing.
The most popular and simple application is spot spraying or weeding with bolt on modules that use image capture of weed species and deploy the chemical or mechanical knockout system according to the image and location of target. The difficulties and potential for developing better and faster systems of image capture was well described by Robovision who are specialists in capturing human expertise in visual tasks into software.
A little further from commercialization were robot harvesters and video was shown of systems picking strawberries, asparagus, and cauliflowers in open field conditions. These machines were in only their first season of operation so this is a space to watch for developments. Mishandling of the crop was held as the potential risk for adoption as any damage reduces shelf life and quality and thus price. Two machines in the USA (Harvest Croo and Advanced Farm) were picking the very delicate crop of strawberries and there a major part of the problem is post picking handling and transport. The Harvest Croo machine used image processing, multiple robot grapples and a liquid transport system to move and pack the fruit.
It was stated several times that mechanised field harvesting can improve product quality by removing human contamination of the crop (no exposure to salmonella or covid from pickers) and also by grading the fruit in the field the costs and difficulty of human labour in the packing house could be significantly reduced. Naturally the heavier loads of harvesting need a transport system that does not cause soil compaction to carry produce off the field.
Various pricing mechanisms for the technology were mentioned from outright purchase, leasing and payment by materials harvested (which could then compete directly with the human cost of harvesting). Some of the systems developed have been by a partnership between producers identifying the problem and the start up tech developers. As there is virtually no long term operating experience repair cycles and fault detection were barely discussed except as a legal risk. Only one farmer mentioned the lack of any checking for the real things that happen such as bearing failures causing misaligned weeding disks etc.
Although high value crops have significant niche markets which are under severe stress due to low labour availability from migration restrictions and a loss of traditional recruitment patterns in the countryside, they do not amount to scales that will massively reduce cost of production. While tractors sell in hundreds of thousands of units per year the take up of specialist autonomous platforms is likely to be in hundreds per year for the next few years until issues such as cost of use, serviceability, dealership response times have been resolved. There will still be a need for the flexible farm tractor for many years to come.