发表机构
UMich; UCLA; NVIDIA; JHU; USC; Stanford（密歇根大学; 加州大学洛杉矶分校; 英伟达; 约翰霍普金斯大学; 南加州大学; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对自动驾驶中推理接地性与行动结果脱节的问题，提出以物理实体为接地单元的GroundAct框架，通过参考标记与交互修正实现接地规划，在开闭环测试中表现优异。
AI 中文摘要
驾驶模型日益将推理锚定于因果关系、空间结构、感知证据和预测的未来状态。这些进展使推理更贴近驾驶场景，但留下一个根本问题悬而未决：当模型最终输出一个动作时，接地性应意味着什么？正确接地的推理本身并不能确保理想的驾驶结果。我们提出GroundAct，它源于一个简单的前提：驾驶通过物理实体及其交互展开。因此，实体成为接地的基本单元；一个轻量级参考标记使每个选定实体的连续状态可通过符号推理寻址；并且只有被引用实体与不断演进的提议的交互才能修正计划。其结果是从推理所锚定的内容到计划所执行的内容的显式路径，我们称之为接地规划。为评估其实用价值，我们在开环和闭环设置中评估了GroundAct。GroundAct在正常、分布外和安全关键场景中展现出强大的开环规划能力，闭环结果进一步将该证据扩展到仿真驾驶中。
英文摘要
Driving models increasingly ground reasoning in causal relations, spatial structure, perceptual evidence, and predicted futures. These advances make reasoning more faithful to the driving scene, but leave a fundamental question unresolved: what should groundedness mean when the model ultimately outputs an action? Correctly grounded reasoning does not, by itself, ensure desirable driving outcomes. We introduce GroundAct, which starts from a simple premise: driving unfolds through physical entities and their interactions. Entities therefore become the unit of grounding; a lightweight reference token keeps each selected entity's continuous state addressable through symbolic reasoning; and only the referenced entities' interactions with the evolving proposal correct the plan. The result is an explicit path from what reasoning grounds to what the plan does, which we call grounded planning. To assess its practical value, we evaluate GroundAct in both open- and closed-loop settings. GroundAct shows strong open-loop planning across normal, out-of-distribution, and safety-critical scenarios, with closed-loop results extending this evidence to driving in simulation.
Comments20 pages; Project website: https://groundact.github.io/
