BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
技术动态
来源：arXiv cs.RO发布时间待核实
arXiv:2608.12854v2 Announce Type: replace Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling.