Fast User Adaptation for Human Motion Prediction in Physical Human-Robot Interaction
This work addresses the challenge of user variability in human motion prediction for physical human-robot interaction, representing an incremental improvement through specialized meta-learning.
The paper tackles the problem of predicting human movements in physical human-robot interaction by addressing behavioral differences across users, proposing a meta-learning framework that enables fast adaptation to unseen users using small amounts of individual data, resulting in outperformance over existing baselines on a dataset with 20 users.
Accurate prediction of human movements is required to enhance the efficiency of physical human-robot interaction. Behavioral differences across various users are crucial factors that limit the prediction of human motion. Although recent neural network-based modeling methods have improved their prediction accuracy, most did not consider an effective adaptations to different users, thereby employing the same model parameters for all users. To deal with this insufficiently addressed challenge, we introduce a meta-learning framework to facilitate the rapid adaptation of the model to unseen users. In this study, we propose a model structure and a meta-learning algorithm specialized to enable fast user adaptation in predicting human movements in cooperative situations with robots. The proposed prediction model comprises shared and adaptive parameters, each addressing the user's general and individual movements. Using only a small amount of data from an individual user, the adaptive parameters are adjusted to enable user-specific prediction through a two-step process: initialization via a separate network and adaptation via a few gradient steps. Regarding the motion dataset that has 20 users collaborating with a robotic device, the proposed method outperforms existing meta-learning and non-meta-learning baselines in predicting the movements of unseen users.