Socially-Aware Navigation: A Non-linear Multi-Objective Optimization\n Approach

Abstract

Mobile robots are increasingly populating homes, hospitals, shopping malls,\nfactory floors, and other human environments. Human society has social norms\nthat people mutually accept; obeying these norms is an essential signal that\nsomeone is participating socially with respect to the rest of the population.\nFor robots to be socially compatible with humans, it is crucial for robots to\nobey these social norms. In prior work, we demonstrated a Socially-Aware\nNavigation (SAN) planner, based on Pareto Concavity Elimination Transformation\n(PaCcET), in a hallway scenario, optimizing two objectives so that the robot\ndoes not invade the personal space of people. This paper extends our PaCcET\nbased SAN planner to multiple scenarios with more than two objectives. We\nmodified the Robot Operating System's (ROS) navigation stack to include PaCcET\nin the local planning task. We show that our approach can accommodate multiple\nHuman-Robot Interaction (HRI) scenarios. Using the proposed approach, we\nachieved successful HRI in multiple scenarios like hallway interactions, an art\ngallery, waiting in a queue, and interacting with a group. We implemented our\nmethod on a simulated PR2 robot in a 2D simulator (Stage) and a pioneer-3DX\nmobile robot in the real-world to validate all the scenarios. A comprehensive\nset of experiments shows that our approach can handle multiple interaction\nscenarios on both holonomic and non-holonomic robots; hence, it can be a viable\noption for a Unified Socially-Aware Navigation (USAN).\n