Alaina Burge

Document Type

Honors Thesis


The Vertically Enabled Cargo Transfer Robot (VECTR) was designed to carry heavy loads along staircases, a potentially hazardous task for humans. The main VECTR project focused on the mechanics of the robot, with little investigation into autonomy. This extended project explored computer vision as a means of making future versions of VECTR more autonomous. The vision module focused on identifying the presence of humans, since this ability is especially valuable for safe navigation. The module was created using Python and OpenCV. The program used the Histogram of Oriented Gradients (HOG) algorithm, with the You Only Look Once (YOLO) algorithm being a potential future upgrade. The completed module performed well in identifying the presence of humans but experienced some false identification trends and a somewhat slow frame processing rate. The overall performance of the module was promising, and further expansion of the program for eventual integration onto VECTR was recommended.

Publication Date






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.