Socially-Aware Navigation for Robots in Public Spaces

As robots become increasingly integrated into public spaces such as hospitals, shopping malls, airports, and museums, their ability to navigate intelligently and socially is crucial. Socially-aware navigation (SAN) goes beyond simply moving from one point to another; it involves understanding and respecting human social norms to ensure that robots’ interactions are comfortable and non-intrusive.

A key aspect of SAN is the robot's ability to detect and respond to the context of its environment. In this work, we propose a novel method for context detection that allows robots to accurately interpret their surroundings and adjust their behavior accordingly. By understanding social cues and the dynamics of the environment, robots can navigate in a way that maintains personal space and fosters a sense of safety and comfort for the people around them.

Additionally, we developed an innovative architecture for SAN in which the robot dynamically executes social navigation behaviors based on the detected context. This system enables robots to seamlessly adapt to diverse social settings, ensuring their presence is perceived as natural and non-disruptive. With this enhanced level of social intelligence, robots can integrate more effectively into public environments and contribute more meaningfully to the spaces they inhabit.

Speaker: Roya Salek Shahrezaie, Sonoma State University

Attend in person or online (see weblink for Zoom information)