Jump to Main Content
RFID and Drones: The Next Generation of Plant Inventory
- Quino Jannette, Maja Joe Mari, Robbins James, Fernandez R.Thomas, Owen James S. Jr., Chappell Matthew
- AgriEngineering 2021 v.3 no. pp. 168-181
- automation, botanical composition, data collection, inventories, labor, radio frequency identification, unmanned aerial vehicles
- Collection of plant inventory (i.e., count, grade, plant size, yield) data is time-consuming, can be inaccurate, and costly. There has been improvements to the involved processes; however, they still rely heavily on manual labor. In response to increasing labor costs and shortages, there is an increased need for adoption of more automated technologies by the nursery industry. Growers, small and large, are beginning to adopt technologies (e.g., plant spacing robots) that automate or augment certain operations, but greater strides must be taken to integrate next generation technologies into these challenging unstructured agricultural environments. The main objective of this work is to demonstrate merging specific ground and aerial-based technologies (Radio Frequency Identification [RFID], and small Unmanned Aircraft System [sUAS]) into a holistic systems approach to address the specific need of moving toward automated on-demand plant inventory. This preliminary work focuses on evaluating different RFID tags with respect to their distance and orientation to the RFID reader. Fourteen different RFID tags, five distances (1.5 m, 3.0 m, 4.5 m, 6.0 m, and 7.6 m), and four tag orientations [the front of the tag (UP), back of the tag (DN), tag at sideways-left (SL), and tag at sideways-right (SR)] were assessed. Results showed that the tag upward orientation resulted in the highest scanning rate for both the laboratory and field experiments. Two orientations (UP and SR) had significant effect on the scan rate of tags. The distance between the reader and the tags at 1.5 meter and 6.0 m did not significantly affect the scanning efficiency of the RFID system in horizontally fixed (p-value > 0.05) position regardless of tags. Different tag designs also produced different scan rates. Overall, since most of the tags were scanned at least once (except for Tag 6F), it is a very promising technology for using in nursery inventory data acquisition. Although these experiments are focused on inventory in plant nurseries, results for this work has potential for inventory management in other agricultural sectors.