Mobile manipulators always need to determine feasible base positions prior to carrying out navigation-manipulation tasks. Real-world environments are often cluttered with various furniture, obstacles, and dozens of other objects. Efficiently computing base positions poses a challenge. In this work, we introduce a framework named MoMa-Pos to address this issue. MoMa-Pos first learns to predict a small set of objects that, taken together, would be sufficient for finding base positions using a graph embedding architecture. MoMa-Pos then calculates standing positions by considering furniture structures, robot models, and obstacles comprehensively. We have extensively evaluated the proposed MoMa-Pos across different settings (e.g., environment and algorithm parameters) and with various mobile manipulators. Our empirical results show that MoMa-Pos demonstrates remarkable effectiveness and efficiency in its performance, surpassing the methods in the literature. %, but also is adaptable to cluttered environments and different robot models. Supplementary material can be found at \url{https://yding25.com/MoMa-Pos}.

翻译：移动机械臂在执行导航-操作任务前，通常需要确定可行的基座位置。现实环境常被各类家具、障碍物及数十种其他物体杂乱地填充。如何高效计算基座位置构成一项挑战。本研究提出名为MoMa-Pos的框架解决该问题。MoMa-Pos首先利用图嵌入架构学习预测一组关键物体，这些物体组合起来足以确定基座位置；随后综合考量家具结构、机器人模型及障碍物因素计算站立位置。我们针对不同设置（如环境与算法参数）及多种移动机械臂对MoMa-Pos进行了全面评估。实验结果表明，MoMa-Pos在性能上展现出显著的有效性与高效性，优于文献中的现有方法，且能适应杂乱环境与不同机器人模型。补充材料见\url{https://yding25.com/MoMa-Pos}。