NRI: FND: Mutually Aware Social Navigation

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

This project seeks to provide robots with the social intelligence to be aware of the mutual dependency between their movements and the movements of humans around them. To this end, the work will focus on (1) improving the way robots reason about spatial behavior, and (2) developing navigation methods that lead to understandable and appropriate motion patterns in social environments. This project will build upon prior work in robot perception and social behavior in crowds and groups. This work will impact the future use of robots in many application domains, especially for those where people untrained in robotics are present (e.g., delivery robots, guide robots, etc.). Almost all robots that move near people will need to behave appropriately, so it is necessary to discover socially intelligent navigation techniques, thereby increasing human acceptance and market success. The team will also continue established and successful efforts in fostering diversity, integrating education with research, disseminating new knowledge to the general public, industry stakeholders, and other researchers. Prior work has identified the importance of human-aware navigation, and has developed methods to incorporate the social norms that govern human physical space into aspects of robot path planning. Building on this foundational work, the team will address three main social intelligence tasks: (1) enabling robots to reason jointly about nearby human spatial behavior and their own, (2) enabling robots to communicate their intentions as they navigate so that their motion is understandable by nearby humans, and (3) giving robots the ability to decide when it is acceptable to violate pre-established social conventions. Research in these areas is incomplete since most efforts do not include awareness or reasoning about mutual dependency. This makes it difficult for a robot to reason intelligently on how to alter crowd motions in a socially appropriate manner. Methods discovered by the team will also support the case where multiple robots must mix with multiple humans.