Swarm farming has lately been a topic of discussion among manufacturers, innovators, and consumers alike. The question often discussed within stakeholder communities is whether or not swarm robots will be the future of farming.
Swarm farming is the concept of utilizing multiple smaller robotic platforms to autonomously conduct farming operations as a substitute to large manned agricultural equipment. Now, rural agricultural communities have large sections of farmlands and large equipment, which can rapidly cover acres for planting, nutrition, pesticide, and harvesting operations (sometimes involving multiple operations for nutrition and pest control). During a growing season, limited days suitable to work are available to timely complete the specific operation without penalty on yield and profitability.
Key drivers for the motivation in swarm farming include decreasing number of people engaged in agriculture, sustainable crop production methods for environmental sustainability, potential negative effects from soil compaction when using larger ag equipment, increasing size of farming operations, and rising average age of U.S. farmers.
When it comes to substituting current large equipment with swarm farming, one of the key qualifiers is going to be comparative system productivity and accuracy. There are probably dozens of different types of robotic platforms which have been designed in Europe and the U.S. Some examples include Robotti by Agrointelli, Tertil by Franklin robotics, OZ and DINO by Naio technologies, TerraSentia by Earthsense, AVO and ARA robots by Ecorobotix, DOT by Raven Autonomy, SwarmFarm Robotics, and BoniRob by Deepfield Robotics. Platform sizes vary from small robots to do scout activities, medium sized for operations like weeding, and some large enough to conduct multi-row operations like spraying and seeding.
Most of the robotics platforms currently in sight are standalone with a future vision to operate as swarms. The majority of these robotic platforms are light enough to just conduct non-soil engaging activities, whereas only a few can do soil engaging activities. As such, these platforms are currently shown to operate on crops with low canopy heights (vegetable and fruits), with few exceptions like vineyards.
However, there are very few options for row crop operations requiring operation on substantially large acreage, greater draft, and weight transfer. Another interesting facet is that not all of these robotic platforms have been designed with full considerations on implementations or application systems to be utilized in the real-world. Today's producers use a lot of technology, automation, automatic machine data, and not to mention, the human intelligence sitting inside the machine. One question we need to ask ourselves as stakeholders in the industry is, Are we ready to provide a practical switch?
Currently, there are a handful of swarm farming concepts which are being explored. Robotic platforms, like ones from Swarmfarms, DOT, Naio, Guss and others, are examples of how swarm robots could become reality. Personally, I feel the biggest hurdle we need to cross is the ability of such robotic platforms to operate as a fleet or implement swarm farming on large acres in a representative manner.
Swarm farming definitely has some foreseeable advantage, if this swarm fleet becomes fully autonomous in operation over larger fields. Personally, I see two biggest advantages. One, a fully integrated system can reduce operational time spent by farm owners on and off the machines and continuous optimization using machine learning, Two, the automatic decision-based applications using artificial intelligence, data assimilation, and aggregated data availability for analytics are strong assets. Swarm has the ability to operate on its own, detect and communicate faults, automatic reloading of operational boundaries if one platform is down, and many more.
The big dream is that platforms within swarm farming will have capability to operate nearly 24/7, but the question is, how far are we from that reality?
By: Dr. Ajay Sharda, Associate Professor, Precision Ag/Machine Systems Engineer, Kansas State University
Dr. Ajay Sharda in the Biological and Agricultural Engineering department at Kansas State University has a USDA-NIFA funded project under the National Science Foundation’s National Robotics Initiative Program. This is one of the many projects within what he calls the FARMS (Fusing Automation and Robotics for Ag. Machine Systems) Lab at K-State. The project aims for designing a robotic platform, along with an application system, which can not only provide an alternative but add substantial intelligence in terms of artificial intelligence to conduct knowledge based real-time application.
