High precision control and deep learning-based corn stand counting algorithms for agricultural robot
- PDF / 2,304,723 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 204 Views
High precision control and deep learning-based corn stand counting algorithms for agricultural robot Zhongzhong Zhang1 · Erkan Kayacan2
· Benjamin Thompson1 · Girish Chowdhary1
Received: 1 December 2018 / Accepted: 9 June 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This paper presents high precision control and deep learning-based corn stand counting algorithms for a low-cost, ultracompact 3D printed and autonomous field robot for agricultural operations. Currently, plant traits, such as emergence rate, biomass, vigor, and stand counting, are measured manually. This is highly labor-intensive and prone to errors. The robot, termed TerraSentia, is designed to automate the measurement of plant traits for efficient phenotyping as an alternative to manual measurements. In this paper, we formulate a Nonlinear Moving Horizon Estimator that identifies key terrain parameters using onboard robot sensors and a learning-based Nonlinear Model Predictive Control that ensures high precision path tracking in the presence of unknown wheel-terrain interaction. Moreover, we develop a machine vision algorithm designed to enable an ultra-compact ground robot to count corn stands by driving through the fields autonomously. The algorithm leverages a deep network to detect corn plants in images, and a visual tracking model to re-identify detected objects at different time steps. We collected data from 53 corn plots in various fields for corn plants around 14 days after emergence (stage V3 - V4). The robot predictions have agreed well with the ground truth with Cr obot = 1.02 × C human − 0.86 and a correlation coefficient R = 0.96. The mean relative error given by the algorithm is −3.78%, and the standard deviation is 6.76%. These results indicate a first and significant step towards autonomous robot-based real-time phenotyping using low-cost, ultra-compact ground robots for corn and potentially other crops. Keywords Machine learning · Deep learning · High precision control · Corn stand counting · Field robot · Agricultural robotics
1 Introduction Phenotypic traits are measured manually by field technicians in the field to determine physical differences between plant genotype and the influence of environmental conditions. Frequent and accurate measurement of these phenotypic traits This is one of the several papers published in Autonomous Robots comprising the Special Issue on Robotics: Science and Systems.
B
Erkan Kayacan [email protected] Zhongzhong Zhang [email protected] Girish Chowdhary [email protected]
1
Department of Agricultural and Biological Engineering, University of Illinois at Urbana-Champaign, Champaign, IL, USA
2
School of Mechanical and Mining Engineering, University of Queensland, Brisbane, QLD, Australia
can be utilized to breed improved crops that have more nutritional value, yield, and resilience to weather anomalies. However, manual phenotyping is expensive due to its laborintensive nature, and prone to human measurement errors. This has led to the so-called p
Data Loading...
