Map completion from partial observation using the global structure of multiple environmental maps
This work addresses the challenge of efficient mapping for autonomous mobile robots in indoor environments, representing an incremental advance by integrating map completion networks into SLAM.
The paper tackles the problem of map completion from partial observations in SLAM by incorporating a deep generative model trained on existing maps, achieving a 1.3 times improvement in map estimation accuracy compared to previous methods.
Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently. Autonomous mobile robots generally apply simultaneous localization and mapping (SLAM) methods to understand the reachable area in newly visited environments. However, conventional mapping approaches are limited by only considering sensor observation and control signals to estimate the current environment map. This paper proposes a novel SLAM method, map completion network-based SLAM (MCN-SLAM), based on a probabilistic generative model incorporating deep neural networks for map completion. These map completion networks are primarily trained in the framework of generative adversarial networks (GANs) to extract the global structure of large amounts of existing map data. We show in experiments that the proposed method can estimate the environment map 1.3 times better than the previous SLAM methods in the situation of partial observation.