English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents high precision control and deep learning-based corn standcounting algorithms for a low-cost, ultra-compact 3D printed and autonomousfield robot for agricultural operations. Currently, plant traits, such asemergence rate, biomass, vigor, and stand counting, are measured manually. Thisis highly labor-intensive and prone to errors. The robot, termed TerraSentia,is designed to automate the measurement of plant traits for efficientphenotyping as an alternative to manual measurements. In this paper, weformulate a Nonlinear Moving Horizon Estimator (NMHE) that identifies keyterrain parameters using onboard robot sensors and a learning-based NonlinearModel Predictive Control (NMPC) that ensures high precision path tracking inthe presence of unknown wheel-terrain interaction. Moreover, we develop amachine vision algorithm designed to enable an ultra-compact ground robot tocount corn stands by driving through the fields autonomously. The algorithmleverages a deep network to detect corn plants in images, and a visual trackingmodel to re-identify detected objects at different time steps. We collecteddata from 53 corn plots in various fields for corn plants around 14 days afteremergence (stage V3 - V4). The robot predictions have agreed well with theground truth with $C_{robot}=1.02 \times C_{human}-0.86$ and a correlationcoefficient $R=0.96$. The mean relative error given by the algorithm is$-3.78\%$, and the standard deviation is $6.76\%$. These results indicate afirst and significant step towards autonomous robot-based real-time phenotypingusing low-cost, ultra-compact ground robots for corn and potentially othercrops.

High precision control and deep learning-based corn stand counting algorithms for agricultural robot