Apostle, M. K., & Basnet, S., & Bassett, L. C. (2022, April), Autonomous Inventory Tracking  Paper presented at ASEE-NE 2022, Wentworth Institute of Technology, Massachusetts. 10.18260/1-2--42156

\bibitem{asee_peer_42156}
  Apostle, M. K., \& Basnet, S., \& Bassett, L. C. (2022, April), \emph{Autonomous Inventory Tracking}
  Paper presented at ASEE-NE 2022, Wentworth Institute of Technology, Massachusetts.
  10.18260/1-2--42156

Maria Katerina Apostle, Saurav Basnet, and Luke Clarke Bassett.  "Autonomous Inventory Tracking".  ASEE-NE 2022, Wentworth Institute of Technology, Massachusetts, 2022, April.  ASEE Conferences, 2022.  https://peer.asee.org/42156 Internet.  23 Apr, 2024

\bibitem{asee_peer_42156}
  Maria Katerina Apostle, Saurav Basnet, and Luke Clarke Bassett.
  "Autonomous Inventory Tracking".
  \emph{ASEE-NE 2022, Wentworth Institute of Technology, Massachusetts, 2022, April}.
  ASEE Conferences, 2022.
  https://peer.asee.org/42156 Internet.  23 Apr, 2024

@INPROCEEDINGS{asee_peer_42156
author = "Maria Katerina Apostle, Saurav Basnet, and Luke Clarke Bassett"
title = "Autonomous Inventory Tracking"
booktitle = "ASEE-NE 2022"
year = "2022"
month = "April"
address = "Wentworth Institute of Technology, Massachusetts"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/42156}
number = {10.18260/1-2--42156}
}

TY  - CPAPER
AB  - Inventory management is a key part of the success of many businesses and organizations. Several methods to track inventory exist, the most common of which being manual tracking using items like hand scanners. However, manual input may be more prone to errors such as not scanning the item or double scanning. Some methods of autonomous tracking currently exist, however these are very large-scale and are expensive to produce and maintain. This project proposes a low-cost alternative for autonomous inventory tracking with a QR code-based inventory management robot utilizing a Raspberry Pi and Arduino. The robot uses a USB camera to detect product QR codes on a shelf while using several QTI sensors to follow a black line along the ground bordered at its edges to indicate the start and end point. On each run, the robot will move forward along the path, reversing when it detects the first border and finally stopping when it detects a second border. Meanwhile, as the robot moves along the path, the camera detects the QR codes along the shelves and records the data in a CSV format for easy exporting into databases and spreadsheet programs such as Excel. In practice, the robot functions in most rooms, even in those with lower lighting. Additionally, the robot can accurately and consistently read codes from a large range of distances, allowing for flexibility in its placement in a warehouse or store. Lastly, its cost-effectiveness allows for implementation in most businesses. Currently, more features are being implemented to improve the bot, including allowing it to read codes on higher shelves, improving camera quality and detection, researching alternatives to further reduce costs, and implementing a portable power solution for the Raspberry Pi.
AU  - Maria Katerina Apostle
AU  - Saurav Basnet
AU  - Luke Clarke Bassett
CY  - Wentworth Institute of Technology, Massachusetts
DA  - 2022/04/22
PB  - ASEE Conferences
TI  - Autonomous Inventory Tracking
UR  - https://peer.asee.org/42156
DO  - 10.18260/1-2--42156
ER  -