Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning
For autonomous driving researchers, this work improves token-based world modeling and planning by bridging the gap between reconstruction and decision-useful representations.
The authors propose a discrete tokenizer for autonomous driving that aligns with DINO features and incorporates geometric cues (depth, pose) to improve representation quality. It achieves better reconstruction fidelity and competitive planning performance on NAVSIM.
Discrete visual tokens should provide a compact representation for both token-based world modeling and planning in autonomous driving. However, most tokenizers are inherited from image generation and are optimized mainly for pixel reconstruction, which may leave a gap between what is easy to generate and what is useful to decode for driving decisions. We present a representation-guided and geometry-enhanced tokenizer that learns discrete tokens under joint supervision. The tokenizer aligns its discrete bottleneck with a frozen DINO feature space through feature decoding, while preserving appearance via RGB reconstruction with perceptual and adversarial losses. To inject geometric state-related cues, we add adjacent-frame depth and relative-pose supervision during training and stabilize joint objectives with multi-codebook quantization. We evaluate the same learned tokens with a lightweight planning readout and a GPT-style next-token world model. Experiments on NAVSIM show improved reconstruction fidelity and representation consistency, competitive planning performance under a fixed decoder, and better generative quality under matched settings.