RoboLoc: A Benchmark Dataset for Point Place Recognition and Localization in Indoor-Outdoor Integrated Environments

초록

ABSTRACT Robust place recognition is essential for reliable localization in robotics, particularly in complex environments with frequent indoor？outdoor transitions. However, existing LiDAR­based datasets often focus on outdoor scenarios and lack seamless domain shifts. In this paper, we propose RoboLoc, a benchmark dataset designed for GPS­free place recognition in indoor？outdoor environments with floor transitions. RoboLoc features real­world robot trajectories, diverse elevation profiles, and transitions between structured indoor and unstructured outdoor domains. We benchmark a variety of state­of­the­art models, point­based, voxel­based, and BEV­based architectures, highlighting their generalizability domain shifts. RoboLoc provides a realistic testbed for developing multi­domain localization systems in robotics and autonomous？navigation.

키워드