The AutoDoc began as a senior design project at Greenville University, with the goal of creating an autonomous robot capable of identifying nutrient deficiencies in crops using spectral imaging. Our team saw a gap in the agricultural technology market—specifically the need for accessible, real-time crop health diagnostics that could reduce labor and resource waste while improving yields.

The first phase of the project focused on developing a functional proof of concept. We built and tested an initial prototype capable of autonomously following a preprogrammed path while scanning soybean plants for early signs of nutrient deficiencies. Using near infrared (NIR) technology and custom data interpretation algorithms, we successfully identified deficiencies—sometimes as early as the first week of growth.

This milestone validated our core hypothesis: that spectroscopy can be a powerful, non-invasive tool for early crop health diagnostics. Along the way, we also built a foundation for future scaling, with modular designs, a clear patentable technology pathway, and strong results that justify further research and investment.

Now that we’ve graduated, our team is continuing AutoDoc as an independent venture, building on our university roots but charting our own path forward. The positive outcomes from Phase 1 have led us to pursue Phase 2: advancing the hardware, increasing autonomy, enhancing data accuracy, and preparing the system for patenting and eventual real-world deployment.