No abstract

No abstract

No abstract

This paper presents high precision control and deep learning-based corn stand counting algorithms for a lowcost, ultra-compact 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 (NMHE) that identifies key terrain parameters using onboard robot sensors and a learning-based Nonlinear Model Predictive Control (NMPC) 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 C robot = 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

Traditionally, wear-resistant components are manufactured by cladding hard facing material on the base metal. This production process is typically complicated, expensive, and time-consuming. This study proposes a method of fabricating components with high wear resistance requirements utilizing cold metal transfer based wire and arc additive manufacturing with hard facing welding wire as the consumable material. Thin-walled and block components were manufactured by depositing a combination of a low alloy steel, ER80S-G, and a hard facing material, MF6–55GP. Microstructure characterization and mechanical properties (hardness, tensile and Block-on-Ring wear test) were performed. The results revealed that the ER80S-G/MF6–55GP bimetal components were able to be fused with no detectable defects near the border. As the deposited height was increased, the residual stress also increased; this internal residual stress combined with the external tensile load lead to a very low tensile strength of 447.79 ± 24.32 MPa of the ER80S-G/MF6-55GP/ER80S-G sandwich structure. The microstructures, constituent phases, and hardness distributions differ greatly among the layers due to their different thermal histories. The wear weight loss varies as the load condition changes for both the MF6-55G and Cr12MoV steels. Compared to Cr12MoV, MF6-55GP weld metal exhibits better wear resistance at higher loads in dry sliding wear tests.