I-Corps: Translation Potential of a Robot-enabled Enhancement of Resource-use Efficiency in Row-crop Agriculture

This I-Corps project is focused on the development of small robots suited to navigate commercial row-crops in-season and autonomously, enabling them to produce higher yields with fewer resources. In an era of narrowing profit margins and labor shortages, robotic equipment offers the potential to improve agricultural production. Autonomous nursery robots enable management strategies that are not possible with conventional equipment.

For example, nitrogen fertilizer can be applied periodically across a plant's lifecycle, reducing stress, enhancing yield, and minimizing material loss through leaching and volatilization. Other applications include foliar feeding, weeding for reduced herbicide use, and field-variable nutrient assessment. These robots also collect data that farmers can use to refine strategies, transforming intuition into data-backed insight.

This capability reduces waste, aligns farming with sustainability goals, and meets market and regulatory demands. Additionally, these lightweight robots reduce anthropogenic soil compaction, a common consequence of traditional heavy machinery, promoting healthier soil.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of novel, tactile-based perception and navigation systems designed to allow small off-road robots to operate in messy, stalky row-crop environments like under-the-canopy of a cornfield.

This tactile navigation system supplements traditional visual methods, providing redundancy against sensor occlusion and feature extraction difficulties in the presence of weeds and leaves. Nearby stalks and obstacles can be detected and localized in the robot's periphery using tactile sensing, allowing for autonomous navigation even when visual data is unavailable.

Robots equipped with this system can autonomously navigate through production cornfields entirely blind, detecting and positioning plants with accuracy. In-season management strategies can be unlocked with a robust navigation system. Early trials demonstrate that yield can be improved by ~10%, using ~20% less fertilizer when the robot spoon-feeds fertilizer to corn slowly over time, providing a clear indication of the economic potential of the technology.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.