Versatile Photonic Encoding Platform with Selectable Back Ends for Automotive Edge Processing

Abstract

The increasing diversity and computational demands of automotive edge functions require hardware architectures that support heterogeneous processing while limiting implementation complexity and system overhead. We investigate a system-level approach in which a common, fixed photonic front end provides a shared physical transformation for multiple processing functions, while application adaptation is handled by lightweight peripheral processing. We propose the Versatile Photonic Encoding Platform (VPEP), implemented using a fabricated silicon-photonic chip with 32 phase-modulated inputs, a passive fixed encoding core, and 17 on-chip photodetector outputs. Without reconfiguring the photonic core, the same chip is evaluated across four representative functions relevant to automotive edge systems: classification and regression for machine learning, analog-to-digital conversion for mixed-signal processing, and photonic information encoding and recovery for communication-related processing. Compared with linear baselines without photonic encoding, VPEP improves the mean macro-F1 score on 12 of 13 classification datasets and the mean coefficient of determination on 9 of 12 regression benchmarks. For analog-to-digital conversion, the best configuration achieves an in-sample normalized root-mean-square error of approximately 0.75% of full scale. For information encoding and recovery, a lightweight nonlinear decoder reconstructs four-character (32-bit) inputs from 17-channel encoded outputs with approximately 94% character accuracy for a 26-symbol set. These results demonstrate the feasibility of cross-application processing with a single fixed silicon-photonic encoding core and suggest a system-level design approach, complementary to reconfigurable photonic architectures, that combines common photonic hardware with lightweight application-specific processing for future automotive edge systems.

arXiv comment21 pages, 10 figures, 3 tables, 4 supplementary tables