AutoMerge: A Framework for Map Assembling and Smoothing in City-Scale Environments

In the era of advancing autonomous driving and increasing reliance on geospatial information, high-precision mapping not only demands accuracy but also flexible construc- tion. Current approaches mainly rely on expensive mapping de- vices, which are time-consuming for city-scale map construction and vulnerable to erroneous data associations without accurate GPS assistance. We present AutoMerge, a novel framework for merging large-scale maps that surpasses these limitations, which (i) provides robust place recognition performance despite differences in both translation and viewpoint, (ii) is capable of identifying and discarding incorrect loop closures caused by perceptual aliasing, and (iii) effectively associates and op- timizes large-scale and numerous map segments in the real- world scenario. AutoMerge utilizes multi-perspective fusion and adaptive loop closure detection for accurate data associations, and it uses incremental merging to assemble large maps from individual trajectory segments given in random order and with no initial estimations. Furthermore, AutoMerge performs pose- graph optimization after assembling the segments to smooth the merged map globally. We demonstrate AutoMerge on both city-scale merging (120km) and campus-scale repeated merging (4.5km×8). The experiments show that AutoMerge (i) surpasses the second-and third-best methods by 0.9% and 6.5% recall in segment retrieval, (ii) achieves comparable 3D mapping accuracy for 120 km large-scale map assembly, (iii), and it is robust to temporally-spaced revisits. To our knowledge, AutoMerge is the first mapping approach to merge hundreds of kilometers of individual segments without using GPS.