Search papers, labs, and topics across Lattice.
This paper introduces WCog-VLA, a dual-level World-Cognitive Vision-Language-Action model designed to enhance proactive decision-making in autonomous driving. By integrating comprehensive world cognition with generative world evolution, the model employs 3D spatial perception and Game-theoretic Chain-of-Thought reasoning to predict and navigate complex environments. Experimental results on the NAVSIM benchmark reveal that WCog-VLA achieves a State-Of-The-Art PDMS score of 92.9, marking a significant advancement in autonomous driving capabilities.
WCog-VLA achieves a groundbreaking 92.9 PDMS score by merging world cognition with generative modeling, setting a new benchmark for proactive autonomous driving.
Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving. However, existing methods either lack comprehensive world cognition or suffer from fragmented world foresight, inherently 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.
