LATIDIA · Robótica

SDPAD: una tubería totalmente impulsada por picos para la conducción autónoma de extremo a extremo

arXiv: 2610.11583v1Tipo de anuncio: nuevo Resumen: La conducción autónoma de extremo a extremo exige planificadores de trayectoria que sean lo suficientemente precisos y baratos para la implementación en el borde. Red neuronal artificial de última generación (AN

La noticia

arXiv:2610.11583v1 Announce Type: new Abstract: End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (ANN) planners meet the accuracy requirement at the cost of heavy dense computation, while spiking neural networks (SNNs)---though promising orders-of-magnitude energy savings through sparse, event-driven arithmetic---still lag far behind in planning accuracy. We present \textbf{SDPAD}, a fully spike-driven end-to-end planning pipeline that closes this gap. SDPAD converts a pre-trained ANN perception stack into integer-spike form via quantized ANN2SNN conversion, lifts multi-view images into the bird's-eye-view (BEV) space with a spike-driven-max (SDM) depth distribution (Spike-3D-Lift), and plans through the Spike-QFormer, a spiking query transformer in