The project’s motivation is to create a robot capable of navigating in an environment with people, detecting the people within range and interact with them. The importance of such project stems from the fact that robots are present in every aspect of our modern life, specifically servicing. Therefore, using “friendly” robots who can recognize people and induce pleasant sensation could be very useful.
This project is a continuation of a previous one in which some actions were implemented: scanning the environment, navigating in a defined site, as well as avoiding obstacles. Our project’s targets were implementing autonomous navigation at the site, detecting people while on the move and eventually, stopping and greeting the detected person.
The working environment which we used was ROS (Robot Operating System). We implemented functional units called nodes that were responsible for the robot’s movement, people’s detection and for the greeting. To implement the navigation, we used the mapping functionality implemented in the previous project. We then made it possible for the movement to be autonomous in a predetermined patrol route. People detection was implemented using a node that used the LIDAR data and classified clusters of points as possible legs. When it was highly probable that two legs are in fact a human, it classified it as such. Greeting was done using a node that stopped the robot’s movement and presented an animated face along with a subtitle every time the robot detected a person.
Eventually, the robot successfully navigated and greeted people without problems. Having said that, we did encounter some false detections. We tried overcoming them by tweaking parameters in the code. Additionally, we suggested many possible solutions and future work possibilities.
In conclusion, we believe our project acts as a proof of concept for using robots in dynamic environments while navigating autonomously and interacting with people