Date of Award

2026

Document Type

Open Access Master's Report

Degree Name

Master of Science in Mechatronics (MS)

Administrative Home Department

Department of Applied Computing

Advisor 1

Aleksandr V. Sergeyev

Committee Member 1

Ashraf Saleem

Committee Member 2

Nathir A. Rawashdeh

Committee Member 3

Vinh T. Nguyen

Abstract

Vision-guided robots offer a clear advantage over teach-pendant programming for battery handling, where modern packs hold thousands of cells and teaching each position by hand does not scale. Commercial vision systems address this need, but their calibration, detection, and coordinate-conversion stages are closed to the user, making it hard to incorporate newer learning-based methods. This work presents a modular, custom-built vision-guided system using an Orbbec Gemini 435Le eye-in-hand camera, an NVIDIA Jetson Orin Nano, an Allen-Bradley Micro850 PLC, and a FANUC LR Mate 200iC, communicating over Modbus TCP and EtherNet/IP. A per-hole classification model resolves each known hole into a present, absent, or flipped state. A two-stage calibration—17-point homography plus affine correction—achieves 0.93 mm RMS positioning accuracy across eight runs, comparable to two FANUC iRVision configurations (0.904 mm and 0.756 mm). By keeping every stage from image to robot coordinate accessible, the system aims to establish a calibrated, sub-millimeter foundation for LLM/VLM planners on industrial robots.

Download

Share

COinS