S2M-Trek: From Single to Multi-Sphere Transport via Per-Frame Deep Sets on a Wheel-Legged Robot
The paper introduces Per-Frame Deep Sets (PFDS) to handle transporting multiple identical spheres simultaneously, which is physically equivalent regardless of their slot assignments. PFDS pools observations within each history frame before temporal processing, creating a Gframe-invariant architecture. This invariance allows the model to robustly scale from single-sphere transport to five spheres without needing complex slot permutation training.