Robots are envisaged to cooperate with humans in public spaces, navigating swiftly in dense crowds. Social robot navigation refers to a robot navigation task in human environments associated with multiple objectives including the efficiency of a path, safety, naturalness, as well as social compliance. This problem is inherently interdisciplinary in nature, interconnecting insights from diverse fields including planning, multiagents, human-robot interaction, psychology, and sociology. Recently, several colleagues and I had an opportunity have an in-depth discussion on the core challenges of the social robot navigation, namely, the planning, behavioral, and evaluation challenges. In this talk, I would like to share the discussion, focusing on the lessons learned from the past research work and the key insights for the potential future directions in this field.
Jean Oh is a faculty member at the Robotics Institute at Carnegie Mellon University. She is passionate about creating persistent robots that can co-exist and collaborate with humans in shared environments, learning to improve themselves over time through continuous training, exploration, and interactions. Jean heads Bot Intelligence Group (BIG) research laboratory where the current research areas are focused on social navigation, multimodal planning, and creative AI. Her team has won two Best Paper Awards in Cognitive Robotics at IEEE International Conference on Robotics and Automation (ICRA) for the works on following natural language directions in unknown environments and socially compliant robot navigation in human crowds, in 2015 and 2018, respectively. Jean received her Ph.D. in Language and Information Technologies at Carnegie Mellon University, M.S. in Computer Science at Columbia University, and B.S. in Biotechnology at Yonsei University in South Korea.