Economical Cartesian Fruit Harvesting Robot (CarteR)

Faculty Mentor Information

Dr. Duke Bulanon, Northwest Nazarene University

Presentation Date

7-15-2026

Abstract

Agriculture is responsible for twenty percent of Idaho’s GDP; however, labor-intensive tasks like harvesting face labor shortages and strain local farmers. To address the labor shortages, an economical harvesting Cartesian robot (CarteR) was developed to automate the apple picking process. CarteR is comprised of a Cartesian manipulator, a color depth camera, a gripper, and a control system mounted on a mobile platform. A RealSense™ depth camera was used to identify apples, determine their location based on the coordinate frame of the robot, and guide the robot’s gripper to the apples. Results showed that the camera’s depth estimation accuracy decreased at distances greater than sixty centimeters. However, this positioning error can be compensated by the fault-tolerant fin-ray apple grippers. Additionally, the Cartesian manipulator’s positioning accuracy of ±2 mm helps minimize the overall error. Ultimately, the current capabilities of CarteR provide the necessary foundation for a fully autonomous robot at an economical value.

This document is currently not available here.

Share

COinS
 

Economical Cartesian Fruit Harvesting Robot (CarteR)

Agriculture is responsible for twenty percent of Idaho’s GDP; however, labor-intensive tasks like harvesting face labor shortages and strain local farmers. To address the labor shortages, an economical harvesting Cartesian robot (CarteR) was developed to automate the apple picking process. CarteR is comprised of a Cartesian manipulator, a color depth camera, a gripper, and a control system mounted on a mobile platform. A RealSense™ depth camera was used to identify apples, determine their location based on the coordinate frame of the robot, and guide the robot’s gripper to the apples. Results showed that the camera’s depth estimation accuracy decreased at distances greater than sixty centimeters. However, this positioning error can be compensated by the fault-tolerant fin-ray apple grippers. Additionally, the Cartesian manipulator’s positioning accuracy of ±2 mm helps minimize the overall error. Ultimately, the current capabilities of CarteR provide the necessary foundation for a fully autonomous robot at an economical value.