Hybrid-Driven With Low-Frequency Enhancement for LGPR Map Reconstruction

Localizing ground-penetrating radar (LGPR) is an emerging place recognition technology based on prior maps, and has received widespread attention in the field of robot localization in challenging environments. However, due to complex geological environments and equipment limitations, the data collected may have missing ground penetrating radar (GPR) traces and irregular sampling issues. The missing of map data can reduce the reliability of spatial accuracy, causing the localization results to deviate from the actual location, and affecting localization accuracy. This article proposes a solution to reconstruct maps by image recovery for offline map production in LGPR tasks to address this issue. We propose a hybrid-driven method that combines the convolutional neural networks (CNNs) with the half-quadratic splitting method under the formulation of maximum a posteriori (MAP). This hybrid-driven framework offers both the flexibility of the modeling approach and the advantages of learning-based semantic acquisition. To enhance the stability of the reconstructed maps, we develop a low-frequency enhancement module since high-frequency information in GPR image is more susceptible to environmental changes. Besides, a mask guidance module is employed in the iterative process, which ensures the invariance of the original data during the iterative recovery process. Experiments in different missing cases show that the proposed method has the best image recovery results compared to other popular methods, and the map reconstruction based on the recovery generates the highest localization accuracy of LGPR.