A Cognitive Architecture for Socially Assistive Robots
摘要
Recent studies have tried to approach through Socially Assistive Robotics (SAR) the challenge of supporting elderly individuals living alone. In this paper, we introduce a cognitive architecture for SAR, incorporating planned and reactive behaviors. We emphasize the role of generative AI to provide a high-level semantic understanding and reasoning over dynamic environments, allowing more natural and flexible interactions with the user. The architecture has been deployed using the TIAGo mobile robotic manipulator in a simulated kitchen environment.