Mechanical Interaction Sensing for Robotic Kiwifruit Handling with an Optoelectronic Soft Suction Cup

Romina Adhami; Ebrahim Shahabi; Alessio Mondini; Samuel M. Youssef; Cosimo Della Santina; Gualtiero Volpe; Barbara Mazzolai

cs.RONov 6, 2026

Mechanical Interaction Sensing for Robotic Kiwifruit Handling with an Optoelectronic Soft Suction Cup

Authors: Romina Adhami, Ebrahim Shahabi, Alessio Mondini, Samuel M. Youssef, Cosimo Della Santina, Gualtiero Volpe, Barbara Mazzolai

Organizations: Bioinspired Soft Robotics Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy · Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands · DIBRIS, University of Genoa, Genoa, Italy

Abstract

Robotic handling of delicate fruit benefits from compliant contact and quantitative sensing of the mechanical interaction at the end-effector. This study investigates an optoelectronic soft suction cup with a kiwifruit-specific bicomponent design for estimating interaction forces during contact with real fruit. During known-contact intervals, the optical signals accurately estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in the optical response. Leave-one-collection-day-out validation remains strong (R-squared = 0.955 +/- 0.031), supporting robustness across acquisition sessions. As an exploratory secondary analysis, binary Soft/Firm classification from compression-test reference labels achieves moderate balanced accuracy (approximately 0.705) under grouped held-out-fruit validation, while finer three-class grading shows limited performance.

Figures & tables

Fig. 1: Sensorized soft suction-cup design. (a) Optoelectronic sensing principle illustrating the LED–phototransistor arrangement and deformation-dependent changes in optical paths under compression and elongation. (b) Final cup construction integrating a PCB with three LED–phototransistor pairs, translucent Ecoflex 00-50 for light transmission, and white reflective Ecoflex 00-50 around the PCB, within a Dragon Skin 10 structural body and a softer Ecoflex 00-10 fruit-contacting rim (base diameter: $23\,\mathrm{mm}$ ).

Fig. 2: Geometry and material screening of Small, Medium, and Large suction cups made from E30, E50, and DS10 on three reference surfaces: soft flat E50, rigid flat PLA, and rigid curved PLA. Bars indicate mean peak attachment force; error bars show sample standard deviation across repeated pull-off trials within each recording (

n=3

–

7

Fig. 3: Peak attachment force on kiwifruit for four Large suction-cup configurations: monolithic E30, E50, and DS10, and bicomponent DS10+E10. Bars indicate mean values; error bars show sample standard deviation across seven repeated pull-off trials within each recording (

n=7

per configuration).

Fig. 4: Representative suction-based grasping sequence of the selected sensorized suction cup on a whole kiwifruit. (a) Approach to the fruit surface. (b) Suction-cup contact with the kiwifruit and suction activation. (c) Lifting of the fruit under suction.

Fig. 5: Robotic experimental setup for interaction-force data collection. The UR5e manipulator applies vertical loading through the sensorized soft suction-cup end-effector, while an axial load cell beneath the support plate provides reference force measurements. Optical sensor signals and load-cell measurements are acquired through the respective interfaces and recorded on a host PC. A reference object was used for setup and positioning before being replaced by a kiwifruit for experimental data collection.

Quantity	Value
Fruits	70
Trials	1509
Nominal force setpoints (N)	1.0–3.5
Contact $\|F\|$ range analysed (N)	0.20–4.81
Collection-day batches	4
Repetitions per fruit (median/mean)	16.5 / 21.6

TABLE I: Analyzed cohort for force estimation

Fig. 6: Representative kiwifruit interaction showing the three optoelectronic sensor responses (S1–S3) together with the measured load-cell force during contact.

Fig. 7: Optical response versus interaction force on real kiwifruit. (a) Mean optical response $S_{\mathrm{mean}}$ versus measured force during loading for several fruits. (b) Force-estimation accuracy on held-out fruits when using individual channels, the mean response, or the joint three-channel input.

Fig. 8: Force estimation on held-out kiwifruit. (a) Predicted versus measured load-cell force using seed-0 grouped out-of-fold predictions ( $n=102{,}640$ contact samples). (b) Per-fruit MAE across 70 held-out fruits (sorted); median MAE $=0.134\,\mathrm{N}$ . (c) MAE by measured force magnitude: low $[0.2,1.0)\,\mathrm{N}$ , medium $[1.0,2.5)\,\mathrm{N}$ , and high $[2.5,10)\,\mathrm{N}$ .

Validation	Model	$R^{2}$	MAE (N)
Grouped OOF	Isotonic	$0.925\pm 0.005$	$0.236$
Grouped OOF	Ridge	$0.959\pm 0.007$	$0.161$
Grouped OOF	Shallow MLP	$0.968\pm 0.005$	$0.138$
Grouped OOF	Progress-only	$0.212$	$0.776$
LODO	Shallow MLP	$0.955\pm 0.031$	$0.171\pm 0.061$

TABLE II: Primary force-estimation metrics.

Fig. 9: Robustness of force estimation. (a) MAE during loading (including overshoot) and unloading on held-out fruits ( $R^{2}$ annotated). (b) Leave-one-collection-day-out MAE across four collection days ( $R^{2}$ annotated).

Vision-Based Tactile Sensing

Vision-based tactile sensing uses cameras to read contact-induced changes in soft sensor surfaces, giving robots detailed information about touch.

See all 70 papers

V2F: Vision-Informed Grasp Force Prediction for Damage-Aware Robotic Handling of Date Fruits
Jul 22, 2026Shahd Shami, Obadah Wali, Eric Feron +1Robotic Grasping Robotic Manipulation
Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Saudi Arabia
An analysis of sensor selection for fruit picking with suction-based grippers
Apr 27, 2026Eva Krueger, Marcus Rosette, Joseph R. DavidsonRobotic Grasping Tactile Sensing
Collaborative Robotics and Intelligent Systems (CoRIS) Institute, Oregon State University, Corvallis OR 97331, USA
FruitTouch: A Perceptive Gripper for Gentle and Scalable Fruit Harvesting
Feb 22, 2026Ruohan Zhang, Mohammad Amin Mirzaee, Wenzhen YuanRobotic Grasping Robotic Hand Design
University of Illinois at Urbana-Champaign, Champaign, IL, USA

Jul 22, 2026J/K move · Enter open · S save

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

Shahd Shami, Obadah Wali, Eric Feron, Shinkyu Park

Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Saudi Arabia

Robotic Grasping Robotic Manipulation Agricultural Robotics

Open paper AskPDF arXiv

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.

Abstract

Vision-Based Tactile Sensing

Explore similar work

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

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

FruitTouch: A Perceptive Gripper for Gentle and Scalable Fruit Harvesting