Abstract—A smart city strives to enhance society by offering cleaner and improved amenities, with smart underground infrastructure pivotal to achieving this goal. Monitoring the drainage system is essential to maintaining a clean and healthy environment. Manhole monitoring is inefficient and slow, leading to delays in addressing drainage issues. The suggested system offers a low-cost, low-maintenance alternative, which plots manhole coordinates using Global Positioning System (GPS). Traffic is alerted to impending manholes to avoid them, and information is updated every five minutes. The machine learning algorithm utilized by the system for assessing every state is based on Q-learning. The admin office receives a notification outlining the problem whenever there are sudden changes to the settings. By enhancing manhole maintenance, this strategy will have a significant positive social impact. To guarantee efficacy, a test dataset will be used to test and evaluate the Q-Learning Reinforcement Learning algorithm based on policies and rewards.
 
Keywords—Global Positioning System (GPS), manhole, Q-learning, thinkspeak, twilio, water level, product innovation, process innovation


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).