Autonomous Navigation of a Mobile Robot

Thumbnail Image
Date
2020-05
Authors
Boor, Paige
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Research Projects
Organizational Units
Organizational Unit
Mechanical Engineering
The Department of Mechanical Engineering at Iowa State University is where innovation thrives and the impossible is made possible. This is where your passion for problem-solving and hands-on learning can make a real difference in our world. Whether you’re helping improve the environment, creating safer automobiles, or advancing medical technologies, and athletic performance, the Department of Mechanical Engineering gives you the tools and talent to blaze your own trail to an amazing career.
Journal Issue
Is Version Of
Versions
Series
Abstract
This project focuses on indoor robot navigation and the initial development of software for a mobile robot, a TurtleBot, to detect objects. The motivation is to use the findings to connect verbal instructions to exact objects in an environment. First, an environment was developed virtually using Gazebo. The virtual environment mirrored a real-world environment that could later be used for testing of navigation. Features were added to the environment such as doors, windows, furniture and colored walls for the robot to see. Second, a general framework model for object detection, Mask RCNN, was installed and validated on ROS, the robotic operating system, for a mobile robot. Mask RCNN segments objects at an instance, applies a mask, and predicts the class. The capability of the model on this type of robot was tested with different settings, such as lighting and camera quality. It is found that lighting and angles of objects affects the results. Overall, the model is able to be implemented within ROS, so the TurtleBot is able to detect objects it sees.
Comments
Description
Keywords
Citation
DOI
Source
Subject Categories
Copyright