Researchers at Chonnam National University in South Korea have developed an artificial intelligence mapping method that combines drone imagery with ground-based LiDAR data to improve how agricultural robots locate themselves and navigate commercial orchards.
The work targets a familiar problem in agricultural automation. Orchard canopies can interfere with satellite positioning, while repeated rows and similar-looking trees give autonomous navigation systems relatively few distinctive landmarks. As a robot travels farther, small positioning errors can compound, reducing the accuracy needed for operations such as spraying, crop monitoring, transport and harvesting.
Led by Kyeong-Hwan Lee of the university’s Department of Convergence Biosystems Engineering, the research was published June 1, 2026, in Artificial Intelligence in Agriculture after appearing online in March.
The views and opinions expressed are those of the author’s and do not necessarily reflect the official policy or position of C3.