LATIDIA · Robótica

Pod-RoPE: Codificación de posición rotatoria sobre distribuciones de observación física para IA incorporada

arXiv:2610.33745v2 Tipo de anuncio: reemplazar Resumen: La percepción incorporada requiere representaciones posicionales que capturen tanto la geometría física como la extensión espacial y temporal de las observaciones. Presentamos POD-RoPE (

La noticia

arXiv:2610.33745v2 Announce Type: replace Abstract: Embodied perception requires positional representations that capture both physical geometry and the spatial and temporal extent of observations. We introduce POD-RoPE (Physical Observation Distribution RoPE), which represents token observation footprints as distributions over camera centers, viewing directions, and sampling times. Under independent sampling, expected rotations encode relative relationships between distributions; when each distribution collapses to a single address, the construction recovers pointwise RoPE. The same rotation statistics support Q/K matching and coherence-dependent V/O transformations, allowing observation geometry to guide both information selection and content aggregation. Per-token pre-aggregation avoids increasing sequence length or processing pairs of observation nodes. We evaluate POD-RoPE across four robot policy architectures,