# Investigating Sensors and Methods in Grasp State Classification in Agricultural Manipulation

arXiv: https://arxiv.org/abs/2508.11588 · HTML: https://mlsanity.com/paper/2508.11588/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 43 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 5 of 5)

- [Slip Detection with Combined Tactile and Visual Information](https://mlsanity.com/paper/1802.10153/) (2018)
- [Soft-Bubble grippers for robust and perceptive manipulation](https://mlsanity.com/paper/2004.03691/) (2020)
- [Action Conditioned Tactile Prediction: case study on slip prediction](https://mlsanity.com/paper/2205.09430/) (2022)
- [Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy](https://mlsanity.com/paper/2303.00935/) (2023)
- [Learned Slip-Detection-Severity Framework using Tactile Deformation Field Feedback for Robotic Manipulation](https://mlsanity.com/paper/2411.07442/) (2024)

## Built on by (most cited first, 1 of 1)

- [An analysis of sensor selection for fruit picking with suction-based grippers](https://mlsanity.com/paper/2604.24906/) (2026)

## Abstract (arXiv)

Effective and efficient agricultural manipulation and harvesting depend on accurately understanding the current state of the grasp. The agricultural environment presents unique challenges due to its complexity, clutter, and occlusion. Additionally, fruit is physically attached to the plant, requiring precise separation during harvesting. Selecting appropriate sensors and modeling techniques is critical for obtaining reliable feedback and correctly identifying grasp states. This work investigates a set of key sensors, namely inertial measurement units (IMUs), infrared (IR) reflectance, tension, tactile sensors, and RGB cameras, integrated into a compliant gripper to classify grasp states. We evaluate the individual contribution of each sensor and compare the performance of two widely used classification models: Random Forest and Long Short-Term Memory (LSTM) networks. Our results demonstrate that a Random Forest classifier, trained in a controlled lab environment and tested on real cherry tomato plants, achieved 100% accuracy in identifying slip, grasp failure, and successful picks, marking a substantial improvement over baseline performance. Furthermore, we identify a minimal viable sensor combination, namely IMU and tension sensors that effectively classifies grasp states. This classifier enables the planning of corrective actions based on real-time feedback, thereby enhancing the efficiency and reliability of fruit harvesting operations.