Social Robots to Support Rehabilitation Goal Achievement through Personalized Motivational Strategies
Jason Avina, Shivangi Narayan, Osiel Enrique Sales, Milton Esteban Salazar, Perri Cox
Department of Computer Science
Faculty Supervisor: Alyssa Kubota
In this project, we demonstrate a goal achievement framework that aims to support users in achieving their real-world goals across a longitudinal rehabilitation setting. The system uses Retrieval-Augmented Generation (RAG), combined with the ASER (activities, states, events, and their relations) commonsense knowledge graph, and knowledge graph attention network (KGAT)-based reasoning to enable robots to understand everyday contexts and provide meaningful guidance to users. Reinforcement learning allows the robot to adapt its assistance strategies over time based on user interaction and feedback. The goal is to develop cognitively assistive robots capable of providing context-aware and personalized support in real-world environments.