Autonomous Weed Control for Crop Plants

Weed management is critical for agricultural production as well as landscape and environmental management and will play an important role in determining whether future food production meets human requirements. Crop productivity is susceptible to damage from weed competition, with early season weeds a control priority to prevent significant yield loss. Weed control is a significant cost for crop producers, especially on organic farms. Agricultural operations are still largely dependent on hand weeding which is labor-intensive. Labor shortages and rising wages have led to a surge in food production costs. Although the market for herbicides keeps growing in the world, many factors including strict regulations on the use of herbicides, the growing consumer concerns, and the strong interest in organic food, limit the acceptability of herbicides in future applications. The use of herbicides also pollutes the environment, especially the uniform application of herbicides in the field without considering the spatial variability of weed infestation. Weeds are a persistent problem, and the continuing rise in the number of herbicide-resistant biotypes reinforces that weed control technologies must constantly advance to stay ahead of weed evolution and adaptation. As weeds will continue to evolve and persist, we should take this as a challenge to find truly sustainable weed management solutions.

It is of significance to realize dramatic improvements in robotics, machine vision, and weed control automation that may form the leading edge of a technological revolution in broader weed management. While some success has been demonstrated at early growth stages when weed densities are low and crop plants are readily distinguished from weeds, new approaches are needed to remove weeds under moderate to heavy weed levels.

This Research Topic focuses on the recent advances and latest technical developments for autonomous weed control strategies. Technological solutions such as mechatronics, deep learning, and autonomous machines will play an important role.

We welcome submissions of different types of manuscripts including original research papers, reviews, and methods, including but not limited to:
• autonomous weed control applications in organic farming
• weed and crop classification and localization using sensors
• Image segmentation in crop and weed detection
• convolutional neural networks for plant identification
• robot for weed management for row crops
• intelligent spraying for sustainable weed control
• mechanical weed control in smart farming