EvoDriveVLA: Evolving Autonomous Driving VLA Models via Collaborative Perception-Planning Distillation
Jiajun Cao1,2†,
Xiaoan Zhang1,2†,
Xiaobao Wei1†,
Liyuqiu Huang1,2,
Wang Zijian2,
Hanzhen Zhang2,
Zhengyu Jia2,
Wei Mao2,
Xianming Liu2,
Shuchang Zhou2,
Yang Wang2*,
Shanghang Zhang1*,
1Peking University,
2XPENG
† Equal contribution
* Corresponding authors
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 oracle-guided 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, oracle-guided trajectory distillation employs a future-aware oracle-teacher with coarse-to-fine trajectory refinement and Monte Carlo dropout sampling to produce high-quality trajectory candidates, thereby selecting the optimal trajectory to guide the student’s prediction.
If you find EvoDriveVLA is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry:
Our work is primarily based on the following codebases:
Impromptu-VLA,
FSDrive and,
OmniDrive.
