让机器人更懂辣椒植株的遮挡关系，精准规划采摘路径
SG-DOR: Learning Scene Graphs with Direction-Conditioned Occlusion Reasoning for Pepper Plants
- 基于器官点云构建带方向遮挡关系的场景图
- 遮挡预测F1达0.73，前3候选叶子排序准确率85%
- 适合农业机器人感知与采摘规划研究者
密集作物冠层中的机器人采收需要依赖几何信息之外的显式关系，识别哪些器官会遮挡目标果实。本文提出SG-DOR（方向条件遮挡推理的场景图），给定实例分割的器官点云，推断包含物理连接与方向条件遮挡的场景图。引入遮挡排名任务，对目标果实候选叶片进行排序，并设计具有每果叶集注意力和联合层级聚合的方向感知图神经网络。在多株合成辣椒数据集上的实验表明，遮挡预测F1为0.73，NDCG@3达0.85，连接关系推断边F1达0.83，优于强基线模型，为下游干预规划提供结构化关系信号。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。