We present a contact-based phenotyping robot platform that can autonomously 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 detect and 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 challenges and insights obtained from deployment in the field. Our research platform is open-sourced, with additional information available at https://kantor-lab.github.io/cornbot.
@article{arxiv.2311.03697,
title = {Towards Autonomous Crop Monitoring: Inserting Sensors in Cluttered Environments},
author = {Moonyoung Lee and Aaron Berger and Dominic Guri and Kevin Zhang and Lisa Coffee and George Kantor and Oliver Kroemer},
journal= {arXiv preprint arXiv:2311.03697},
year = {2023}
}