Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving

arXiv:2604.12208v1 Announce Type: cross Abstract: Global navigation information and local scene understanding are two crucial components of autonomous driving systems. However, our experimental results indicate that many end-to-end autonomous driving systems tend to over-rely on local scene understanding while failing to utilize global navigation information. These systems exhibit weak correlation between their planning capabilities and navigation input, and struggle to perform navigation-following in complex scenarios. To overcome this limitation, we propose the Sequential Navigation Guidance (SNG) framework, an efficient representation of global navigation information based on real-world navigation patterns. The SNG encompasses both navigation paths for constraining long-term trajectories and turn-by-turn (TBT) information for real-time decision-making logic. We constructed the SNG-QA dataset, a visual question answering (VQA) dataset based on SNG that aligns global and local planning. Additionally, we introduce an efficient model SNG-VLA that fuses local planning with global planning. The SNG-VLA achieves state-of-the-art performance through precise navigation information modeling without requiring auxiliary loss functions from perception tasks. Project page: SNG-VLA

Related

• HyperLiDAR: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing
• Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention
• Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
• Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models

Source: arXiv cs.AI | 2026-04-15