Towards Autonomous Crop Monitoring: Inserting Sensors in Cluttered Environments

Monitoring crop nutrients can aid farmers in optimizing fertilizer use. Many existing robots rely on vision-based phenotyping, however, which can only indirectly estimate nutrient deficiencies once crops have undergone visible color changes. We present a contact-based phenotyping robot platform that can directly insert nitrate sensors into cornstalks to proactively monitor macronutrient levels in crops. This task is challenging because inserting such sensors requires sub-centimeter precision in an environment which contains high levels of clutter, lighting variation, and occlusion. To address these challenges, we develop a robust perception-action pipeline to grasp stalks, and create a custom robot gripper which mechanically aligns the sensor before inserting it into the stalk. Through experimental validation on 48 unique stalks in a cornfield in Iowa, we demonstrate our platform's capability of detecting a stalk with 94% success, grasping a stalk with 90% success, and inserting a sensor with 60% success. In addition to developing an autonomous phenotyping research platform, we share key insights obtained from deployment in the field.

I. Introduction

With advancements in AI and robotics, the agricultural sector is well-positioned to adopt precision agriculture methods that can enhance crop production and minimize environmental footprint [1]. For example, one of the predominant issues faced by farmers is the overuse of fertilizers, which can be alleviated with increased sensing accuracy [2], [3]. Many existing research works focus on automating vision-based crop monitoring and phenotyping [4], [5], [6], [7], [8], [9], specifically for detecting cornstalks [10], [11]. However, visible plant features are a lagging indicator of nutrient deficiencies. Early detection of these deficiencies enables farmers to respond sooner, enhancing harvest yield. Consequently, our research emphasizes contact-based phenotyping. This involves inserting nitrate sensors developed at Iowa State University [12], [13] into cornstalks to monitor nitrogen concentration, allowing agronomists to proactively address crop deficiencies.