V2F: Vision-Informed Grasp Force Prediction for Damage-Aware Robotic Handling of Date Fruits

2026-07-22

AI Summary

This study addresses the inherent conflict in jujube harvesting between high detachment forces and low bruise resistance by proposing a Vision-to-Force (V2F) framework, which enables cross-cultivar prediction of safe grasping forces from non-contact visual inputs for the first time. The approach integrates image segmentation, active contour optimization, and geometric feature extraction, and embeds Hertzian contact mechanics into a physics-informed residual neural network to establish an end-to-end mapping from visual data to grasping force. Evaluated on unseen cultivars, the model achieves a prediction accuracy of R² ≈ 0.7. Experimental results demonstrate that post-grasping residual deformation remains below 1 mm with no visible damage, enabling stable and non-destructive automated harvesting.

Abstract

This paper presents a vision-informed grasp force prediction framework for robotic handling of date fruits. Addressing the dual challenge of high detachment forces and low bruise thresholds, we first conduct mechanical characterization on date samples to define a safe grasping envelope and quantify the relationship between fruit geometry and bioyield stress. In this work, we develop a Vision-to-Force (V2F) pipeline that combines computer vision-based segmentation, active-contour refinement, and geometric feature extraction with a physics-informed residual neural network that augments a Hertz contact equation. The resulting model maps non-contact visual descriptors and cultivar metadata to predict a safe grasp force with mean validation performance of $R^2 \approx 0.7$ across unseen cultivar groups, which is a good result given the inherent mechanical variability of biological tissue. Experimental validation using a gripper and load cell indicates that the predicted forces enable stable manipulation of different types of date fruits, with residual deformations below 1 mm and no observable damage. These results show that pre-emptive, vision-driven force estimation% can replace slow and potentially damaging tactile exploration , enabling safer robotic handling of fragile fruits.

Problem

• grasp force prediction
• damage-aware handling
• date fruits
• robotic manipulation
• fragile produce

Innovation

• Vision-to-Force
• grasp force prediction
• damage-aware manipulation
• physics-informed neural network
• Hertz contact model