SG-AMP：面向辣椒植株的场景图引导主动感知与语义感知运动规划
SG-AMP: Scene-Graph-Guided Active Perception and Semantics-Aware Motion Planning for Pepper Plants
查看机构详情
- University of Bonn（波恩大学）
- Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）
- Center for Robotics（机器人中心）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究提出SG-AMP算法，集成多模块技术实现辣椒植株的主动感知与运动规划，在辣椒数据集上取得了语义mIoU等指标的良好表现，且输入条件不确定性优化了NYUv2相关指标。
中文摘要 AI 辅助
本文提出SG-AMP，该算法集成了带输入条件不确定性的鲁棒深度补全、持久全景建图、植株场景图推理以及语义感知主动视角运动规划。除了检查观测到的不确定区域外，场景图还明确假设未观测到的辣椒-花梗附着关系，并引导近距离传感指向这些区域。候选视角根据预期信息增益进行选择，同时依赖类别的运动成本区分受保护的辣椒、花梗和茎与可条件通行的 foliage。在辣椒数据集上，感知网络达到55.27%的语义mIoU、38.67%的PQ和40.62mm的深度RMSE，而输入条件不确定性将NYUv2的NLL从-1.6518提升至-1.6925，AUSE从0.0102降至0.0087。
英文摘要
We present SG-AMP, integrating robust depth completion with input-conditioned uncertainty, persistent panoptic mapping, plant scene-graph reasoning, and semantics-aware active view-motion planning. Beyond inspecting uncertain observed regions, the scene graph explicitly hypothesizes unobserved pepper--peduncle attachments and directs close-range sensing toward them. Candidate views are selected according to expected information gain, while class-dependent motion costs distinguish protected peppers, peduncles, and stems from conditionally traversable foliage. On pepper data, the perception network achieves $55.27\%$ semantic mIoU, $38.67\%$ PQ, and $40.62\,\mathrm{mm}$ depth RMSE, while input-conditioned uncertainty improves NYUv2 NLL from $-1.6518$ to $-1.6925$ and AUSE from $0.0102$ to $0.0087$.
