Can Robots"Taste"Grapes? Estimating SSC with Simple RGB Sensors

2024-12-29

AI Summary

This study addresses the challenge of high-cost, impractical deployment of hyperspectral sensors for estimating soluble solids content (SSC, °Brix) in seedless grapes during robotic harvesting. We propose a low-cost, non-destructive SSC estimation method leveraging ubiquitous RGB sensors. To overcome uncontrolled illumination in natural field conditions, we first empirically validate—on real-world data—that RGB imagery can achieve human-level measurement accuracy. Our method introduces a dual-path lightweight framework: (1) an efficient histogram-based statistical approach, and (2) a compact CNN tailored for embedded platforms, integrating color-space modeling with cross-seasonal field calibration. Evaluated on two years (2021–2022) of field-collected data, our model achieves an RMSE of ≈0.8 °Brix—comparable to manual refractometer measurements. The algorithm has been successfully deployed on both robotic embedded systems and smartphones, significantly enhancing the feasibility and cost-effectiveness of autonomous grape maturity assessment.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Scene Analysis & Understanding
• Machine Learning: Semi-Supervised Learning

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In table grape cultivation, harvesting depends on accurately assessing fruit quality. While some characteristics, like color, are visible, others, such as Soluble Solid Content (SSC), or sugar content measured in degrees Brix ({deg}Brix), require specific tools. SSC is a key quality factor that correlates with ripeness, but lacks a direct causal relationship with color. Hyperspectral cameras can estimate SSC with high accuracy under controlled laboratory conditions, but their practicality in field environments is limited. This study investigates the potential of simple RGB sensors under uncontrolled lighting to estimate SSC and color, enabling cost-effective, robot-assisted harvesting. Over the 2021 and 2022 summer seasons, we collected grape images with corresponding SSC and color labels to evaluate algorithmic solutions for SSC estimation on embedded devices commonly used in robotics and smartphones. Our results demonstrate that SSC can be estimated from visual appearance with human-like performance. We propose computationally efficient histogram-based methods for resource-constrained robots and deep learning approaches for more complex applications.

Problem

• RGB sensors
• Sugar content estimation
• Robot-assisted grape harvesting

Innovation

• RGB sensors
• Deep learning
• Sugar content estimation