Design, Integration, and Evaluation of a Dual-Arm Robotic System for High Throughput Tissue Sampling from Potato Tubers

TL;DR

This paper introduces a cost-effective, machine-vision-guided dual-arm robotic system for high-throughput tissue sampling from potato tubers, significantly reducing manual labor and increasing efficiency.

Contribution

The study presents an integrated robotic system with dual arms and vision guidance for automated tissue sampling, demonstrating high success rates and low costs compared to manual methods.

Findings

Average positional error of 1.84 mm

Sampling success rate of 81.5%

Average cycle time of 10.4 seconds

Abstract

Manual tissue extraction from potato tubers for molecular pathogen detection is highly laborious. This study presents a machine-vision-guided, dual-arm coordinated inline robotic system integrating tuber grasping and tissue sampling mechanisms. Tubers are transported on a conveyor that halts when a YOLOv11-based vision system detects a tuber within the workspace of a one-prismatic-degree-of-freedom (P-DoF) robotic arm. This arm, equipped with a gripping end-effector, secures and positions the tuber for sampling. The second arm, a 3-P-DoF Cartesian manipulator with a biopsy punch-based end-effector, then performs tissue extraction guided by a YOLOv10-based vision system that identifies the sampling sites on the tuber such as eyes or stolon scars. The sampling involves four stages: insertion of the punch into the tuber, punch rotation for tissue detachment, biopsy punch retraction, and deposition of the tissue core onto a collection site. The system achieved an average positional error of 1.84 mm along the tuber surface and a depth deviation of 1.79 mm from a 7.00 mm target. The success rate for core extraction and deposition was 81.5%, with an average sampling cycle of 10.4 seconds. The total cost of the system components was under $1,900, demonstrating the system's potential as a cost-effective alternative to labor-intensive manual tissue sampling. Future work will focus on optimizing for multi-site sampling from a single tuber and validation in commercial settings.