Date of Award

8-2026

Degree Name

MS in Mechanical Engineering

Department/Program

Mechanical Engineering

College

College of Agriculture, Food, and Environmental Sciences

Advisor

Eric Espinoza-Wade

Advisor Department

Mechanical Engineering

Advisor College

College of Engineering

Abstract

This thesis details the development and testing of a computer vision-based real-time pose estimation system for differential drive robots. A single camera with a fisheye lens is used to locate ArUco markers placed at fixed locations and attached to robots. Using the OpenCV library, the Perspective-n-Point (PnP) problem is solved to facilitate the transformation of 2-D robot positions in an image to world-frame coordinates. An analytical solution is presented to estimate robot poses based on a single PnP solution, rather than solving the PnP problem for each pose estimate. Pose information is relayed to individual robots using a multi-microcontroller architecture that leverages the ESP-NOW wireless protocol.

For static objects, the pose estimates from the computer vision (CV) algorithm produced accurate results compared to ground truth values, but when integrated on a moving robot, the CV pose estimates deviated significantly from odometry-based values. This project validates the CV system as a viable source of pose data and verifies the reliability and efficiency of the wireless communication system. Further work should be done to verify and increase the accuracy of pose estimates for moving objects.

Share

COinS