Proactive Robot Assistance via Spatio-Temporal Object Modeling
This work addresses proactive robot assistance for household tasks, representing an incremental advance in domain-specific robotics.
The paper tackles the problem of enabling robots to anticipate and assist with human needs by predicting object movements in daily routines, achieving an 11.1% increase in correct location predictions and an 11.5% reduction in wrong predictions compared to a baseline.
Proactive robot assistance enables a robot to anticipate and provide for a user's needs without being explicitly asked. We formulate proactive assistance as the problem of the robot anticipating temporal patterns of object movements associated with everyday user routines, and proactively assisting the user by placing objects to adapt the environment to their needs. We introduce a generative graph neural network to learn a unified spatio-temporal predictive model of object dynamics from temporal sequences of object arrangements. We additionally contribute the Household Object Movements from Everyday Routines (HOMER) dataset, which tracks household objects associated with human activities of daily living across 50+ days for five simulated households. Our model outperforms the leading baseline in predicting object movement, correctly predicting locations for 11.1% more objects and wrongly predicting locations for 11.5% fewer objects used by the human user.