Research Analyzer
← Back ICRA 2026

Detection of Jamming and Low Harvesting Height in Automated Cabbage Harvesting

Masaki Asano, Takanori Fukao

PDF

AI summary

Key figure (auto-extracted from paper)
A vision-LiDAR fusion framework achieves 97.0% control accuracy by reliably detecting cabbage jamming and low harvesting height to prevent harvester blockages.
Automated harvesting Cabbage jamming detection LiDAR point cloud LSTM motion classification Vision-LiDAR fusion Agricultural robotics

Problem

Automated cabbage harvesters relying on side-mounted cameras frequently fail due to outer leaf occlusion, leading to harvesting height errors and cabbage jamming.

Approach

The system combines overhead camera tracking with an LSTM network for jamming detection and LiDAR point cloud trajectory analysis to identify low harvesting height, triggering automatic height adjustments.

Key results

  • 95.3% accuracy in jamming detection
  • 95% accuracy in low harvesting height detection
  • Real-time operation at 10 Hz in field tests
  • 97.0% overall control accuracy preventing severe blockages

Why it matters

Enables more reliable and robust automated cabbage harvesting, addressing critical agricultural labor shortages by reducing machine failures in the field.

Abstract

Agricultural labor shortages have increased the demand for automation in farming. In cabbage harvesting, au- tomated harvesters rely on a side-mounted camera for detection to control harvesting height, but occlusion from outer leaves can cause errors and lead to failures. This paper presents a robust detection and control framework that integrates YOLO- based cabbage detection, trajectory tracking, LSTM-based motion classification, and LiDAR point cloud analysis. The system functions as a fail-safe while also providing redundancy, enabling recovery when side-mounted camera detection fails, and addresses two critical failure modes: cabbage jamming during extraction and low harvesting height. Temporal mo- tion features are classified by an LSTM, while LiDAR-based trajectory analysis of the cabbage head point cloud centroid identifies low harvesting height. When both jamming and low harvesting height are detected, the system issues a raising command to the harvester. Experiments on real-world data demonstrated 95.3% accuracy in jamming detection and 95% in low harvesting height detection. Field experiments confirmed real-time operation at 10 Hz and effective prevention of severe blockages, achieving an overall control accuracy of 97.0%. These results demonstrate the feasibility of the proposed method for robust automated cabbage harvesting.

Index terms

Robotics and Automation in Agriculture and Forestry Agricultural Automation Field Robots

Related papers