In the field of autonomous driving, Vision-Language-Action (VLA) models have made significant advancements. However, existing methods often lack comprehensive world cognition or suffer from fragmented world foresight, confining these models to reactive driving. To address this limitation, we propose WCog-VLA, a novel dual-level World-Cognitive VLA framework that successfully bridges semantic world forecasting with generative world evolution to achieve proactive autonomous driving.
At the semantic level, WCog-VLA unifies world cognition and reasoning by incorporating 3D spatial perception and injecting agent tokens to capture the world dynamics, while concurrently enabling Game-theoretic Chain-of-Thought (Game-CoT) reasoning.
At the generative level, we introduce the Aligned Decoupled Diffusion Transformer (ADDT) as a powerful generative world model that synthesizes physically-plausible joint multi-agent trajectories. Through scene representation alignment, ADDT reduces the number of denoising steps required and thus significantly accelerates inference.
To facilitate strategic reasoning, we further construct a large-scale dataset featuring 85k Game-CoT annotations. Extensive experiments on the NAVSIM benchmark demonstrate that WCog-VLA achieves a State-Of-The-Art (SOTA) PDMS score of 92.9.
Blogger's Review: WCog-VLA breaks through the limitations of traditional VLA models with its dual-level framework, combining deeper world cognition and generative capabilities to strongly support proactive decision-making in autonomous driving. The successful validation of game-theoretic reasoning in complex environments is noteworthy and warrants attention.