Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
This addresses the real-time deployment challenge for autonomous driving systems, offering an incremental improvement by integrating navigation priors with existing early-exit methods.
The paper tackles the high inference latency of Vision-Language Models in autonomous driving by proposing Nav-EE, a navigation-guided early-exit framework that reduces latency by up to 63.9% while maintaining comparable accuracy to full inference.
Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-exit reduces latency by terminating inference at intermediate layers, yet its task-dependent nature limits generalization across diverse scenarios. We observe that this limitation aligns with autonomous driving: navigation systems can anticipate upcoming contexts (e.g., intersections, traffic lights), indicating which tasks will be required. We propose Nav-EE, a navigation-guided early-exit framework that precomputes task-specific exit layers offline and dynamically applies them online based on navigation priors. Experiments on CODA, Waymo, and BOSCH show that Nav-EE achieves accuracy comparable to full inference while reducing latency by up to 63.9%. Real-vehicle integration with Autoware Universe further demonstrates reduced inference latency (600ms to 300ms), supporting faster decision-making in complex scenarios. These results suggest that coupling navigation foresight with early-exit offers a viable path toward efficient deployment of large models in autonomous systems. Code and data are available at our anonymous repository: https://anonymous.4open.science/r/Nav-EE-BBC4