Valerio Modugno

The hybrid motion prior enables seamless transfer of locomotion skills across tasks, eliminating the need for retraining while preserving expert performance.

SGD stabilizes training dynamics while Adam's reorganization of eigenvectors reveals a surprising localization effect, highlighting stark differences in optimizer behavior.

Achieving certifiable robustness in complex control tasks, this novel MPC framework ensures stability through a unique blend of Transformer networks and Riemannian contraction analysis.

A complete hardware-software platform enables statistically grounded comparison of mid-air docking strategies for dual-drone aerial manipulation.