MomaGraph: 体感任务规划中的状态感知统一场景图
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
AI总结：
MomaGraph通过统一场景图与强化学习模型，实现家庭环境中体感任务规划的高效任务规划与场景理解。
摘要：
家庭中的移动机械臂必须同时导航和操作。这需要一种紧凑且语义丰富的场景表示，能够捕捉物体的位置、功能以及可操作的部分。场景图是自然的选择，但以往的工作往往将空间和功能关系分开，将场景视为静态快照，不考虑物体状态或时间更新，并忽略了完成当前任务最相关的信息。为了解决这些限制，我们引入了MomaGraph，一种为具身智能体设计的统一场景表示，整合了空间-功能关系和部分交互元素。然而，推进这种表示需要合适的数据和严格的评估，这在很大程度上缺失了。因此，我们贡献了MomaGraph-Scenes，首个大规模的富含注释、任务驱动的场景图数据集，以及MomaGraph-Bench，一个涵盖六个推理能力的系统评估套件，从高层规划到细粒度场景理解。基于此基础，我们进一步开发了MomaGraph-R1，一个基于MomaGraph-Scenes训练的70亿参数视觉-语言模型。MomaGraph-R1能够预测任务导向的场景图，并在图-规划框架下作为零样本任务规划器。大量实验表明，我们的模型在开源模型中取得了最先进的结果，在基准测试中达到71.6%的准确率（比最佳基线高11.4%），并且能够跨公共基准测试泛化，并有效转移到真实机器人实验中。
英文摘要：
Mobile manipulators in households must both navigate and manipulate. This requires a compact, semantically rich scene representation that captures where objects are, how they function, and which parts are actionable. Scene graphs are a natural choice, yet prior work often separates spatial and functional relations, treats scenes as static snapshots without object states or temporal updates, and overlooks information most relevant for accomplishing the current task. To address these limitations, we introduce MomaGraph, a unified scene representation for embodied agents that integrates spatial-functional relationships and part-level interactive elements. However, advancing such a representation requires both suitable data and rigorous evaluation, which have been largely missing. We thus contribute MomaGraph-Scenes, the first large-scale dataset of richly annotated, task-driven scene graphs in household environments, along with MomaGraph-Bench, a systematic evaluation suite spanning six reasoning capabilities from high-level planning to fine-grained scene understanding. Built upon this foundation, we further develop MomaGraph-R1, a 7B vision-language model trained with reinforcement learning on MomaGraph-Scenes. MomaGraph-R1 predicts task-oriented scene graphs and serves as a zero-shot task planner under a Graph-then-Plan framework. Extensive experiments demonstrate that our model achieves state-of-the-art results among open-source models, reaching 71.6% accuracy on the benchmark (+11.4% over the best baseline), while generalizing across public benchmarks and transferring effectively to real-robot experiments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
