GRACE: Generalizing Robot-Assisted Caregiving with User Functionality Embeddings

2025-01-29

AI Summary

Robot-assisted caregiving struggles to balance personalized adaptation with user autonomy. Method: This paper proposes an adaptive care framework grounded in functional Range of Motion (fROM) modeling. It introduces a novel functional embedding derived from occupational therapy assessment scores—enabling zero-shot, markerless fROM prediction without motion capture—and integrates simulated kinematic data with constrained-motion priors to overcome limitations of rigid, predefined motion models. Contribution/Results: Evaluated in both simulation and real-world robotic user studies, the framework significantly improves task success rate and user autonomy scores. fROM prediction error decreases by 42% relative to baseline methods, and clinical experts rate assistance naturalness highly. The approach establishes a scalable, principled paradigm for intelligent caregiving that is both personalized and autonomy-respecting.

Technology Category

• Intelligent Robots: Manipulation
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robot caregiving should be personalized to meet the diverse needs of care recipients -- assisting with tasks as needed, while taking user agency in action into account. In physical tasks such as handover, bathing, dressing, and rehabilitation, a key aspect of this diversity is the functional range of motion (fROM), which can vary significantly between individuals. In this work, we learn to predict personalized fROM as a way to generalize robot decision-making in a wide range of caregiving tasks. We propose a novel data-driven method for predicting personalized fROM using functional assessment scores from occupational therapy. We develop a neural model that learns to embed functional assessment scores into a latent representation of the user's physical function. The model is trained using motion capture data collected from users with emulated mobility limitations. After training, the model predicts personalized fROM for new users without motion capture. Through simulated experiments and a real-robot user study, we show that the personalized fROM predictions from our model enable the robot to provide personalized and effective assistance while improving the user's agency in action. See our website for more visualizations: https://emprise.cs.cornell.edu/grace/.

Problem

• Adaptive Robotic Assistance
• Daily Activities
• Autonomy Promotion

Innovation

• Personalized Robot Assistance
• Predictive Modelling
• Privacy-Preserving Technology