Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localization
This work addresses long-term object-based localization for autonomous robots in indoor settings, offering an incremental improvement with tailored 3D annotations and open-source implementation.
The paper tackles the problem of constructing metric-semantic maps for long-term indoor localization by using 3D object detections from monocular RGB frames and floor plan priors, achieving robust localization over nine months in an office environment with online capability on an onboard computer.
Object-based maps are relevant for scene understanding since they integrate geometric and semantic information of the environment, allowing autonomous robots to robustly localize and interact with on objects. In this paper, we address the task of constructing a metric-semantic map for the purpose of long-term object-based localization. We exploit 3D object detections from monocular RGB frames for both, the object-based map construction, and for globally localizing in the constructed map. To tailor the approach to a target environment, we propose an efficient way of generating 3D annotations to finetune the 3D object detection model. We evaluate our map construction in an office building, and test our long-term localization approach on challenging sequences recorded in the same environment over nine months. The experiments suggest that our approach is suitable for constructing metric-semantic maps, and that our localization approach is robust to long-term changes. Both, the mapping algorithm and the localization pipeline can run online on an onboard computer. We release an open-source C++/ROS implementation of our approach.