Feature-Based Occupancy Map-Merging for Collaborative SLAM

• DOI: 10.3390/s23063114
• Publication Date: 2023-03-15T09:22:59Z
• Authors: Sooraj Sunil; Saeed Mozaffari; Rajmeet Singh; Behnam Shahrrava; Shahpour Alirezaee
• Keywords: Occupancy grid mapping; Feature (linguistics); Occupancy; Merge (version control); Grid reference

One of the most frequently used approaches to represent collaborative mapping are probabilistic occupancy grid maps. These maps can be exchanged and integrated among robots reduce overall exploration time, which is main advantage systems. Such map fusion requires solving unknown initial correspondence problem. This article presents an effective feature-based approach that includes processing spatial probabilities detecting features based on locally adaptive nonlinear diffusion filtering. We also present a procedure verify accept correct transformation avoid ambiguous merging. Further, global strategy Bayesian inference, independent order merging, provided. It shown presented method suitable for identifying geometrically consistent across various conditions, such as low overlapping different resolutions. results hierarchical merge six individual at once in constrict SLAM.