"MARKERLESS MOTION CAPTURE FOR DUAL-HANDED TELEPORTATION OF INDUSTRIAL " by Michael F. Vallaro

Date of Award

2024

Degree Type

Thesis

Degree Name

Master of Science in Systems Engineering

Department

Mechanical, Industrial and Systems Engineering

First Advisor

Manbir Sodhi

Abstract

The advancement of teleoperation systems has predominantly focused on single-robot or humanoid systems, leaving a gap in efficient control methods for dual-robot setups. Existing solutions lack the ability to integrate synchronized operations of two robots with intuitive and precise human inputs. This limitation limits the execution of tasks requiring simultaneous coordination, multitasking, and safety measures, particularly in environments that demand precision, such as hazardous material handling, industrial assembly, and automation workflows. To address this issue, a dual-robot teleoperation system is proposed, enabling a single operator to control two Niryo Ned 2 robotic arms using hand motion tracking via Leap Motion controllers. This work is supported by literature in Chapters 2, 3, and 4.

The proposed system enables a human operator to simultaneously control two Ned 2 robotic arms using a Leap Motion Controller, which continuously streams motion capture data from both hands to the computer. As well this system provides a Graphical User Interface (GUI) to assist the user in teleportation and interfacing with the robots. This setup is designed to allow the operator to perform assembly or disassembly tasks remotely, ensuring safety by maintaining a distance. Furthermore, these tasks are recorded, as trajectories which are stored for later use in the same task is required, automating these tasks.

Despite current limitations such as repeatability and the absence of collision control, this system demonstrates significant potential for improving task accuracy and reducing operator effort. Future advancements in sensor integration, machine learning, and computer vision are proposed to improve autonomy, precision, and usability. This work contributes to the field of human-robot collaboration by offering a solution for dual-arm robotic teleoperation, with implications for industrial, educational, and research applications.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.