Robotic Arm Automation
Tran, Lanhjamin
Tran, Lanhjamin
Citations
Altmetric:
License
License
Abstract
Robotic arms and prosthetics have become an established system in the biomedical field to aid people who have mobility issues. While robotic systems have continued to become increasingly complex, it is still a challenge to create fully automated systems that can accurately capture and translate human motion into robotic arm movement. In this research project, we looked at MediaPipe for pose detection and attaching ArUco codes to the human arm to accurately represent real-time motion in the six main joints on an Elephant MechArm270 Pi robot. Once found that ArUco codes served better for our purposes, we expanded upon the project by adding object-based tracking to smooth out the process and began accounting for optical occlusion. To create a more efficient tracking system, we researched a variety of different options such as inverse and forward kinematics along with Kalman filters to predict movement when there are obstructions between ArUco codes and the camera. Additionally, by creating continued motion using Kalman filters, the video stream used to detect ArUco codes was smoothed out. This general robotic project aims to have active human manipulation to create real-time movement on robotic arms.
Description
Date
1/1/2026
Student Status
Junior (Graduating in 2027)
Journal Title
Journal ISSN
Volume Title
Type of presentation
Poster
Collections
Research Projects
Organizational Units
Journal Issue
Citation
DOI
Advisor(s)
Department
Program/Major
Mechanical Engineering
College/School
College of Engineering and Mathematical Sciences
Organization
Research Category
Engineering