Vision-Language Model Reasoning for Contextual Semantic Mapping in Intralogistics
面向内部物流的上下文语义建图中的视觉-语言模型推理
机构 * Institute for Material Handling and Logistics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院物流与物料搬运研究所)
专题命中 视觉推理 :VLM(summary_cn,abstract);vision-language model(title)
AI总结 提出结合SLAM、SAM、实例聚类和VLM多视角推理的上下文语义建图流程,零样本推断物体可移动性,实现语义分类98.93% mIoU和可移动性估计89.17% mAcc。
Comments Accepted for publication at the 31st IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)