In this paper, a novel Multimodal Smartphone based IoT framework is proposed that interconnects human user with robotic system in performing SLAM based Human Robot Interactive tasks. Through this system, humans are added in the loop to build and update the SLAM map where they send commands to add and change locations on top of the 2D SLAM map and navigate to locations using the SLAM map when users issue a navigation command. Preliminary experiments conducted in a lab environment showed that the system can build and update SLAM maps, using user voice and text commands. Adding or changing a location in the SLAM map through user speech and text commands took an average time of 9.7 seconds while the robotic system took an average time of 40.96 seconds to complete a navigation task based on user commands using the SLAM map with an average distance error of 10.4 cm.