Robotic harvesting in dense crop canopies requires effective interventions that depend not only on geometry, but also on explicit, direction-conditioned relations identifying which organs obstruct a target fruit. We present SG-DOR (Scene Graphs with Direction-Conditioned Occlusion Reasoning), a relational framework that, given instance-segmented organ point clouds, infers a scene graph encoding physical attachments and direction-conditioned occlusion. We introduce an occlusion ranking task for retrieving and ranking candidate leaves for a target fruit and approach direction, and propose a direction-aware graph neural architecture with per-fruit leaf-set attention and union-level aggregation. Experiments on a multi-plant synthetic pepper dataset show improved occlusion prediction (F1=0.73, NDCG@3=0.85) and attachment inference (edge F1=0.83) over strong ablations, yielding a structured relational signal for downstream intervention planning.

翻译：在密集作物冠层中进行机器人采摘，需要有效的干预策略。这些策略不仅依赖于几何信息，还依赖于明确的、方向条件的关系，以识别哪些器官遮挡了目标果实。我们提出了SG-DOR（基于方向条件遮挡推理的场景图），这是一个关系推理框架。给定实例分割后的器官点云，该框架能够推断出一个编码物理附着关系和方向条件遮挡信息的场景图。我们引入了一项遮挡排序任务，用于针对目标果实和接近方向检索并排序候选叶片，并提出了一种方向感知的图神经网络架构。该架构采用了针对每个果实的叶片集合注意力机制和联合层级聚合方法。在多植株合成辣椒数据集上的实验表明，相较于强大的消融模型，我们的方法在遮挡预测（F1=0.73，NDCG@3=0.85）和附着关系推断（边F1=0.83）方面均有提升，从而为下游干预规划提供了结构化的关系信号。