Coregionalised Locomotion Envelopes - A Qualitative Approach
This work addresses the challenge of robust control in rehabilitation robots through transfer learning, but it appears incremental as it builds on existing concepts of statistical strength sharing.
The paper tackles the problem of predicting human poses and generating natural walking sequences by exploiting correlations between body parts, such as hands and legs, using a method called coregionalised locomotion envelopes for multi-dimensional manifold regression.
'Sharing of statistical strength' is a phrase often employed in machine learning and signal processing. In sensor networks, for example, missing signals from certain sensors may be predicted by exploiting their correlation with observed signals acquired from other sensors. For humans, our hands move synchronously with our legs, and we can exploit these implicit correlations for predicting new poses and for generating new natural-looking walking sequences. We can also go much further and exploit this form of transfer learning, to develop new control schemas for robust control of rehabilitation robots. In this short paper we introduce coregionalised locomotion envelopes - a method for multi-dimensional manifold regression, on human locomotion variates. Herein we render a qualitative description of this method.