Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstrate impressive reasoning capabilities, they lack the capacity to predict future geometric evolution, creating a significant disparity between semantic interpretation and physical simulation. To bridge this gap, we propose HERMES++, a unified driving world model that integrates 3D scene understanding and future geometry prediction within a single framework. Our approach addresses the distinct requirements of these tasks through synergistic designs. First, a BEV representation consolidates multi-view spatial information into a structure compatible with LLMs. Second, we introduce LLM-enhanced world queries to facilitate knowledge transfer from the understanding branch. Third, a Current-to-Future Link is designed to bridge the temporal gap, conditioning geometric evolution on semantic context. Finally, to enforce structural integrity, we employ a Joint Geometric Optimization strategy that integrates explicit geometric constraints with implicit latent regularization to align internal representations with geometry-aware priors. Extensive evaluations on multiple benchmarks validate the effectiveness of our method. HERMES++ achieves strong performance, outperforming specialist approaches in both future point cloud prediction and 3D scene understanding tasks. The model and code will be publicly released at https://github.com/H-EmbodVis/HERMESV2.

翻译：驾驶世界模型通过模拟环境动力学，成为自动驾驶的关键技术。然而，现有方法主要聚焦于未来场景生成，往往忽略了全面的3D场景理解。相反，尽管大型语言模型展现出令人印象深刻的推理能力，但它们缺乏预测未来几何演化的能力，导致语义解释与物理仿真之间存在显著差距。为弥合这一鸿沟，我们提出HERMES++，一个统一驾驶世界模型，在单一框架内整合了3D场景理解与未来几何预测。我们的方法通过协同设计应对这些任务的不同需求：首先，采用BEV表示将多视角空间信息整合为与LLM兼容的结构；其次，引入LLM增强的世界查询以促进理解分支的知识迁移；第三，设计从当前到未来的连接以弥合时间间隙，使几何演化条件化于语义上下文；最后，为强化结构完整性，我们采用联合几何优化策略，将显式几何约束与隐式潜在正则化相结合，使内部表征与几何先验对齐。在多个基准上的广泛评估验证了方法的有效性。HERMES++取得了强劲性能，在未来点云预测和3D场景理解任务均优于专家方法。模型与代码将在https://github.com/H-EmbodVis/HERMESV2公开发布。