Search papers, labs, and topics across Lattice.
This paper investigates learning motility maps for an under-actuated robot interacting with a high-friction environment, comparing four modeling approaches for predicting body velocity from shape change. The study evaluates model performance within the same gait, across gaits, and across speeds, using motion tracking data from a custom-built physical robot. Results demonstrate a trade-off between simpler models that excel with limited data and more complex models that perform better with larger datasets.
Simpler models of robot body-environment interaction surprisingly outperform complex ones when training data is scarce.
Geometric mechanics provides valuable insights into how biological and robotic systems use changes in shape to move by mechanically interacting with their environment. In high-friction environments it provides that the entire interaction is captured by the ``motility map''. Here we compare methods for learning the motility map from motion tracking data of a physical robot created specifically to test these methods by having under-actuated degrees of freedom and a hard to model interaction with its substrate. We compared four modeling approaches in terms of their ability to predict body velocity from shape change within the same gait, across gaits, and across speeds. Our results show a trade-off between simpler methods which are superior on small training datasets, and more sophisticated methods, which are superior when more training data is available.
