Human-Robot Interaction(HRI) focuses on the communication and interaction between humans and robots. It is a rapidly evolving concept driven by advanced robotics and Artificial Intelligence. Social Robots are designed to interact and socially communicate with humans in a socially acceptable and meaningful manner. Emotional connections and social behavior drive them. When interacting in a social environment, robots must consider human safety and comfort. Social Robots should be able to identify humans as social entities rather than obstacles. This project examines the behavior of Mobile Robots in unknown environments where Mobile Robots respect the space and boundary of humans. The social behavior of Mobile Robots is studied. Human detection is done using a Machine learning algorithm(ML) called Semantic segmentation. The 3D position of detected humans at different points and angles away from the camera is calculated and this information is used to control the navigation of robots around humans and other objects. A Dataset is recorded and a comparison with ground truth is made to prove the efficiency of this system. The obtained 3D coordinates can be used later for the navigation module like costmaps where higher cost can be given to the area representing humans. Considering humans as a social entity rather than an obstacle will increase the acceptance of a mobile robot in human interactive environments.