A Collaborative Mapping System for a Brain-Inspired SLAM

Brain-inspired SLAM imitates the neural processing mechanism of the navigation system in the rodent brain. The low computational requirements and minimal storage demands make brain-inspired SLAM particularly well-suited for large-scale environment mapping. However, the increasing size of the mapping environment raises the likelihood of failures in map construction. As far as we know, there is currently no research on collaborative brain-inspired SLAM systems to improve mapping efficiency and error tolerance. In this paper, we propose a real-time collaborative mapping system to fuse local experience maps into the global map. In our method, an effective overlapping region detection based on sequence matching is designed to realize data association between local maps. Through these detected overlapped experience nodes, the relative poses are then obtained. Finally, a continuous map fusion graph relaxation (CMF-GR) algorithm is proposed to merge local maps and correct their drifts. In addition, we present a leader-follower collaborative mapping system to verify the proposed method. We validate the effectiveness and accuracy of our approach on publicly available datasets and real-world environments through comparison experiences and quantitative analysis.