FLARE: Learning Future-Aware Latent Representations from Vision-Language Models for Autonomous Driving
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911497818472448 |
|---|---|
| author | Xie, Chengen Sima, Chonghao Li, Tianyu Sun, Bin Wu, Junjie Hao, Zhihui Li, Hongyang |
| author_facet | Xie, Chengen Sima, Chonghao Li, Tianyu Sun, Bin Wu, Junjie Hao, Zhihui Li, Hongyang |
| contents | While Vision-Language Models (VLMs) offer rich world knowledge for end-to-end autonomous driving, current approaches heavily rely on labor-intensive language annotations (e.g., VQA) to bridge perception and control. This paradigm suffers from a fundamental mismatch between discrete linguistic tokens and continuous driving trajectories, often leading to suboptimal control policies and inefficient utilization of pre-trained knowledge. To address these challenges, we propose FLARE (Future-aware LAtent REpresentation), a novel framework that activates the visual-semantic capabilities of pre-trained VLMs without requiring language supervision. Instead of aligning with text, we introduce a self-supervised future feature prediction objective. This mechanism compels the model to anticipate scene dynamics and ego-motion directly in the latent space, enabling the learning of robust driving representations from large-scale unlabeled trajectory data. Furthermore, we integrate Group Relative Policy Optimization (GRPO) into the planning process to refine decision-making quality. Extensive experiments on the NAVSIM benchmark demonstrate that FLARE achieves state-of-the-art performance, validating the effectiveness of leveraging VLM knowledge via predictive self-supervision rather than explicit language generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05611 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FLARE: Learning Future-Aware Latent Representations from Vision-Language Models for Autonomous Driving Xie, Chengen Sima, Chonghao Li, Tianyu Sun, Bin Wu, Junjie Hao, Zhihui Li, Hongyang Computer Vision and Pattern Recognition While Vision-Language Models (VLMs) offer rich world knowledge for end-to-end autonomous driving, current approaches heavily rely on labor-intensive language annotations (e.g., VQA) to bridge perception and control. This paradigm suffers from a fundamental mismatch between discrete linguistic tokens and continuous driving trajectories, often leading to suboptimal control policies and inefficient utilization of pre-trained knowledge. To address these challenges, we propose FLARE (Future-aware LAtent REpresentation), a novel framework that activates the visual-semantic capabilities of pre-trained VLMs without requiring language supervision. Instead of aligning with text, we introduce a self-supervised future feature prediction objective. This mechanism compels the model to anticipate scene dynamics and ego-motion directly in the latent space, enabling the learning of robust driving representations from large-scale unlabeled trajectory data. Furthermore, we integrate Group Relative Policy Optimization (GRPO) into the planning process to refine decision-making quality. Extensive experiments on the NAVSIM benchmark demonstrate that FLARE achieves state-of-the-art performance, validating the effectiveness of leveraging VLM knowledge via predictive self-supervision rather than explicit language generation. |
| title | FLARE: Learning Future-Aware Latent Representations from Vision-Language Models for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.05611 |