An analysis of sensor selection for fruit picking with suction-based grippers

2026-04-27

AI Summary

This study addresses the challenge of reliably determining fruit harvesting status during robotic picking, a key factor contributing to inefficiency and crop damage. The authors propose a multimodal perception approach based on a soft suction gripper that dynamically selects the optimal sensor combination at different picking stages to enable predictive detection of successful harvests and slippage events. By evaluating sensor effectiveness phase-by-phase, they identify a minimal sensor set capable of high-accuracy state classification and integrate Random Forest and Multilayer Perceptron models for fused decision-making. Real-world orchard experiments demonstrate that the system achieves over 90% prediction accuracy, with Random Forest enabling real-time inference in just 0.09 seconds, thereby significantly enhancing both reliability and efficiency in robotic fruit harvesting.

Abstract

Robotic fruit harvesting often fails to reliably detect whether a fruit has been successfully picked, limiting efficiency and increasing crop damage. This problem is difficult due to compliant fruit and grippers, variable stem attachment, and occlusions in orchard environments. Prior work has explored vision-based perception and multi-sensor learning approaches for pick state estimation. However, minimal sensor sets and phase-dependent sensing strategies for accurate pick and slip detection remain largely unexplored. In this work, we design and evaluate a multimodal sensing suite integrated into a compliant suction-based apple gripper. Our approach is unique because it identifies which sensors are most informative at different phases of the pick, enabling predictive detection of failures before they occur. The contributions of this paper are a phase-dependent evaluation of multimodal sensors and the identification of minimal sensor sets for reliable pick state classification. Experiments in a real apple orchard show that Random Forest and Multilayer Perceptron classifiers detect successful picks and impending failures with over 90% accuracy, and Random Forest predicts pick/slip events within 0.09 s of human-annotated ground truth.

Problem

• fruit harvesting
• pick detection
• suction-based gripper
• sensor selection
• slip detection

Innovation

• phase-dependent sensing
• minimal sensor set
• suction-based gripper
• pick state estimation
• multimodal sensing