A Personalized Data-Driven Generative Model of Human Repetitive Motion
This work addresses the need for realistic human motion models to improve autonomous avatars and robots in domains like rehabilitation and sports, though it is incremental as it builds on prior research on individual motor signatures.
The authors tackled the problem of generating realistic personalized human motion by proposing a data-driven LSTM model that captures individual motor signatures, showing it accurately reproduces velocity distribution and amplitude envelopes for specific individuals while outperforming existing Kuramoto-like models.
The deployment of autonomous virtual avatars (in extended reality) and robots in human group activities -- such as rehabilitation therapy, sports, and manufacturing -- is expected to increase as these technologies become more pervasive. Designing cognitive architectures and control strategies to drive these agents requires realistic models of human motion. Furthermore, recent research has shown that each person exhibits a unique velocity signature, highlighting how individual motor behaviors are both rich in variability and internally consistent. However, existing models only provide simplified descriptions of human motor behavior, hindering the development of effective cognitive architectures. In this work, we first show that motion amplitude provides a valid and complementary characterization of individual motor signatures. Then, we propose a fully data-driven approach, based on long short-term memory neural networks, to generate original motion that captures the unique features of specific individuals. We validate the architecture using real human data from participants performing spontaneous oscillatory motion. Extensive analyses show that state-of-the-art Kuramoto-like models fail to replicate individual motor signatures, whereas our model accurately reproduces the velocity distribution and amplitude envelopes of the individual it was trained on, while remaining distinct from others.