Vinobot and Vinoculer: Two Robotic Platforms for High-Throughput Field Phenotyping

Abstract

In this paper, a new robotic architecture for plant phenotyping is being introduced. The architecture consists of two robotic platforms: an autonomous ground vehicle (Vinobot) and a mobile observation tower (Vinoculer). The ground vehicle collects data from individual plants, while the observation tower oversees an entire field, identifying specific plants for further inspection by the Vinobot. The advantage of this architecture is threefold: first, it allows the system to inspect large areas of a field at any time, during the day and night, while identifying specific regions affected by biotic and/or abiotic stresses; second, it provides high-throughput plant phenotyping in the field by either comprehensive or selective acquisition of accurate and detailed data from groups or individual plants; and third, it eliminates the need for expensive and cumbersome aerial vehicles or similarly expensive and confined field platforms. As the preliminary results from our algorithms for data collection and 3D image processing, as well as the data analysis and comparison with phenotype data collected by hand demonstrate, the proposed architecture is cost effective, reliable, versatile, and extendable.

Sensors for measuring plant phenotyping: A review

“…Navigation lines were generated based on the stem locations. As listed in Table 5, the representative autonomous robot platforms include "Vinobot" [166] , "BoniRob" [167,168] and "Robotanist" [169] . The advantage of the robot platforms is that they are able to collect plant information during the day and night.…”

“…In addition, the size of the robot platforms is small. [163] Color digital camera, Range camera, Laser sensor, Hyperspectral camera, Light curtain, GPS receiver, Rotary encoder Plant height, Plant coverage, Tiller density, Nitrogen University of Arizona [160] Sonar sensor, Multispectral camera, Crop Circle ACS-470, Infrared radiometer, GPS receiver Plant height, Chlorophyll, NDVI, Canopy temperature Kansas State University [161] Laser sensor, Crop Circle ACS-470, GreenSeeker, thermometer, Ultrasonic sensor, GPS receiver Plant height, Canopy termperature, NDVI High Resolution Plant Phenomics Centre [164] Color digital camera, Lidar sensor, GreenSeeker, Hyperspectral camera, Thermometer, Thermography, GPS receiver, Wheel encoder Plant height, NDVI, LA/LAD, Biomass, Canopy temperature LemnaTec [165] Color digital camera, Laser sensor, Hyperspectral camera, Thermography, Fluorescence sensor, CO 2 sensor, radiometer Plant height, NDVI, Nitrogen, Plant coverage, Water stress Blue River Technology [162] Color digital camera, Lidar sensor, Multispectral sensor, Thermography, pyranometer, GPS receiver Plant height, NDVI, Leaf angle, LAI, Canopy temperature [166] Stereo camera, Lidar sensor, GPS receiver, RFID reader, pyranometer, Temperature sensor, Humidity sensor Plant height, LAI BoniRob [167,168] Color digital camera, Range camera, Lidar sensor, Hyperspectral camera, Light curtain, GPS receiver, Rotary encoder Plant height, Plant coverage, Spectral reflection, Biomass, Stem thickness, Spacing in the row Robotanist [169] Color digital camera, Stereo vision, Range camera, Lidar sensor, GPS receiver, Attitude and heading reference system Leaf angle, Plant greenness…”

Design and field evaluation of a ground robot for high-throughput phenotyping of energy sorghum

“…The BoniRob models have many promising features; however, their wide tracks and limited clearance present a serious limitation for sorghum phenotyping. The Vinobot is another phenotyping rover implemented on a Husky A-200 from Clearpath Robotics (2017) (Kitchener, Ontario, Canada), capable of measuring individual plants and utilizes stereo cameras and multiple environmental sensors (Shafiekhani et al 2017).…”

Raspberry Pi Powered Imaging for Plant Phenotyping

“…Here, we document three different methods for using Raspberry Pi computers for plant phenotyping (Figure 1.). These protocols are a valuable resource because while there are many phenotyping papers that outline phenotyping systems in detail (Granier et al, 2006; Iyer-Pascuzzi et al, 2010; Jahnke et al, 2016; Shafiekhani et al, 2017), there are few protocols that provide step-by-step instructions for building them (Bodner et al, 2017; Minervini et al, 2017). We provide examples illustrating automation of photo capture with open source tools (based on Python and standard Linux utilities).…”