GPL-SLAM：一种基于高斯过程扩展地标的激光SLAM框架
GPL-SLAM: A Laser SLAM Framework with Gaussian Process Based Extended Landmarks
AI总结：
本文提出GPL-SLAM框架，利用高斯过程对物体轮廓进行在线递归建模，在完全贝叶斯框架下联合推断机器人位姿与物体地图，实现高效、准确且具有语义信息的激光SLAM。
摘要：
我们提出了一种新颖的同步定位与建图（SLAM）方法，该方法采用基于高斯过程（GP）的地标（物体）表示。不同于传统的栅格地图或点云配准，我们基于每个物体使用GP轮廓表示对环境进行建模。这些轮廓通过递归方案在线更新，从而实现高效的内存使用。SLAM问题在一个完全贝叶斯框架内被形式化，允许对机器人位姿和基于物体的地图进行联合推断。这种表示提供了语义信息，例如物体的数量及其面积，同时还支持概率性的测量到物体关联。此外，基于GP的轮廓产生了物体形状的置信边界，为安全导航和探索等下游任务提供了有价值的信息。我们在合成实验和真实世界实验中验证了我们的方法，并表明它在多种结构化环境中提供了准确的定位与建图性能。
英文摘要：
We present a novel Simultaneous Localization and Mapping (SLAM) method that employs Gaussian Process (GP) based landmark (object) representations. Instead of conventional grid maps or point cloud registration, we model the environment on a per object basis using GP based contour representations. These contours are updated online through a recursive scheme, enabling efficient memory usage. The SLAM problem is formulated within a fully Bayesian framework, allowing joint inference over the robot pose and object based map. This representation provides semantic information such as the number of objects and their areas, while also supporting probabilistic measurement to object associations. Furthermore, the GP based contours yield confidence bounds on object shapes, offering valuable information for downstream tasks like safe navigation and exploration. We validate our method on synthetic and real world experiments, and show that it delivers accurate localization and mapping performance across diverse structured environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
