EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these challenges, we propose EvoDriveVLA-a novel collaborative perception-planning distillation framework that integrates self-anchored perceptual constraints and future-informed trajectory optimization. Specifically, self-anchored visual distillation leverages self-anchor teacher to deliver visual anchoring constraints, regularizing student representations via trajectory-guided key-region awareness. In parallel, future-informed trajectory distillation employs a future-aware oracle teacher with coarse-to-fine trajectory refinement and Monte Carlo dropout sampling to synthesize reasoning trajectories that model future evolutions, enabling the student model to internalize the future-aware insights of the teacher. EvoDriveVLA achieves SOTA performance in nuScenes open-loop evaluation and significantly enhances performance in NAVSIM closed-loop evaluation. Our code is available at: https://github.com/hey-cjj/EvoDriveVLA.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingSimilar Papers 제목 키워드 기반
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
End-to-end autonomous driving has achieved remarkable advancements in recent years. Existing methods primarily follow a perception-planning paradigm, where perception and planning are executed sequentially within a fully…
Autonomous DrivingDefer to Plan: Adaptive Multi-Agent Fusion for End-to-End V2X Driving
Vehicle-to-everything-aided autonomous driving (V2X-AD) significantly enhances driving performance through information sharing. However, existing collaborative perception methods only optimize module-level perception cap…
Autonomous DrivingA Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Driving
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for end-to-end autonomous driving by jointly integrating perception, reasoning, and decision making within a unified multimodal framework. However, …
Visual Question AnsweringTrajectory PlanningAutonomous DrivingDecision MakingCloud-Edge-Terminal Collaborative AIGC for Autonomous Driving
In dynamic autonomous driving environment, Artificial Intelligence-Generated Content (AIGC) technology can supplement vehicle perception and decision making by leveraging models' generative and predictive capabilities, a…
Autonomous DrivingDecision MakingManagementMotion Planning+1Uncertainty Quantification of Collaborative Detection for Self-Driving
Sharing information between connected and autonomous vehicles (CAVs) fundamentally improves the performance of collaborative object detection for self-driving. However, CAVs still have uncertainties on object detection d…
Autonomous VehiclesObjectobject-detectionObject Detection+1