BonnBot-I: A Precise Weed Management and Crop Monitoring Platform

TL;DR

BonnBot-I tackles the challenge of reducing herbicide usage while preserving crop yield by unifying field monitoring and precision weed management in a single ROS-compatible platform. It introduces a novel movable-weeding-tool arrangement on linear actuators, fuses GNSS and wheel odometry to improve crop localization, and provides a dedicated simulation framework plus a new CN20 corn dataset to evaluate strategies. The approach demonstrates significant improvements in crop-monitoring accuracy (NAE reductions) and explores multiple weeding intervention strategies that balance target coverage with movement efficiency. The work advances practical precision agriculture by enabling plant-level interventions with flexible tooling and validated planning in both simulated and real-field conditions. The findings have direct implications for scalable, environmentally friendly weed management in European arable farming.

Abstract

Cultivation and weeding are two of the primary tasks performed by farmers today. A recent challenge for weeding is the desire to reduce herbicide and pesticide treatments while maintaining crop quality and quantity. In this paper, we introduce BonnBot-I a precise weed management platform which can also performs field monitoring. Driven by crop monitoring approaches that can accurately locate and classify plants (weed and crop) we further improve their performance by fusing the platform available GNSS and wheel odometry. This improves the tracking accuracy of our crop monitoring approach from a normalized average error of 8.3% to 3.5%, evaluated on a new publicly available corn dataset. We also present a novel arrangement of weeding tools mounted on linear actuators evaluated in simulated environments. We replicate weed distributions from a real field, using the results from our monitoring approach, and show the validity of our work-space division techniques which require significantly less movement (a 50% reduction) to achieve similar results. Overall, BonnBot-I is a significant step forward in precise weed management with a novel method of selectively spraying and controlling weeds in an arable field.

Figures (7)

• Figure 1: BonnBot-I Platform, a robotic platform capable of conducting field monitoring and precision weed management in arable field.
• Figure 2: Overview of BonnBot-I with dimensions of key aspects such as height, clearance, camera and tool placement (all numbers in centimeters).
• Figure 3: BonnBot-I ROS simulation with active sensors and actuators (left), An example view of weeding simulation Framework (right) with green markers as plants and red markers representing weeds in each segment. A weeding path is also visualized in blue line for single axis weeding scenario.
• Figure 4: Example image of the CN20 dataset. Left is the original images and right is the same scene with instance-based annotations with unique color for each plant.
• Figure 5: Visualization of Kinematic model of weeding tool work-space (a) the weeds detected in the viewable area of the camera $C_{detect}$ (c); and (b) the gap between two regions.