Indoor Navigation System (INS) supports seamless movement of objects within confined spaces in smart environments. In this paper, a novel INS that relies on ESP32-based Received Signal Strength Indication (RSSI) measurements for precise estimation of distance using K-Nearest Neighbour (K-NN) algorithm is proposed. The system architecture includes three ESP32 nodes functioning as clients, and ESP8266 combined with ESP32 acting as a server. To overcome the limitations of Global Positioning System (GPS) within an indoor environment, Machine Learning (ML)-based prediction models are employed to estimate distance between nodes and predict user locations along with the distance between source and destination. This approach not only addresses the challenges posed by GPS in indoor settings, but also shows the potential of ESP32 devices and predictive algorithms for enhancing navigation accuracy and reliability.