SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
This study addresses the significant accuracy gap between spiking neural networks (SNNs) and artificial neural networks (ANNs) in end-to-end autonomous driving planning, alongside the challenge of maintaining edge energy efficiency. We propose the first fully spike-driven end-to-end autonomous driving planner. Methodologically, we construct a single feedforward inference pipeline that eliminates temporal simulation loops by integrating quantized ANN-to-SNN conversion, Spike Maximum Depth Distribution (Spike-3D-Lift), Spike-QFormer, and deformable spike cross-attention mechanisms. Experimental results on the nuScenes dataset demonstrate that our model achieves an average L2 error of 0.40m, a collision rate of 0.12%, and an energy consumption of only 69.9mJ, while attaining a NAVSIM PDMS score of 86.3. These findings comprehensively surpass existing SNN baselines, validating the potential of SNNs to match dense ANN performance in complex driving tasks.