Heterogeneous Map Merging: State of the Art

Abstract

Multi-robot mapping and environment modeling have several advantages that makeit an attractive alternative to the mapping with a single robot: faster exploration, higherfault tolerance, richer data due to different sensors being used by different systems. However,the environment modeling with several robotic systems operating in the same area causes problemsof higher-order—acquired knowledge fusion and synchronization over time, revealing the sameenvironment properties using different sensors with different technical specifications. While theexisting robot map and environment model merging techniques allow merging certain homogeneousmaps, the possibility to use sensors of different physical nature and different mapping algorithms islimited. The resulting maps from robots with different specifications are heterogeneous, and eventhough some research on how to merge fundamentally different maps exists, it is limited to specificapplications. This research reviews the state of the art in homogeneous and heterogeneous mapmerging and illustrates the main research challenges in the area. Six factors are identified thatinfluence the outcome of map merging: (1) robotic platform hardware configurations, (2) maprepresentation types, (3) mapping algorithms, (4) shared information between robots, (5) relativepositioning information, (6) resulting global maps.

NR5G-SAM: A SLAM Framework for Field Robot Applications Based on 5G New Radio

“…In this work, we address the full SLAM problem in which we are interested in generating a map, while estimating the posterior probability of the robot's full trajectory x and map m given the sensor measurements z and control inputs u over time, p(x 1:t , m|z 1:t , u 1:t ), as opposed to online SLAM, which considers only the most recent pose for state estimation. While conventional SLAM builds a geometrical map of the environment (e.g., see [74]), we use cellular RSSI measurements to obtain a mapping between signal strength measurements [11,75] and the locations of the base stations that transmit them. We represent the signal propagation via REMs, which are useful as part of the research around radio-based SLAM approaches [76,77], having the potential to assist robot localization [78].…”

Fast Loop Closure Selection Method with Spatiotemporal Consistency for Multi-Robot Map Fusion

“…The vital issue of multi-robot SLAM is relative pose estimation, and most existing works deal with this issue by analyzing the inter-robot loop closures and then detecting and filtering the outliers. Researchers present a comprehensive review to illustrate the challenges for multi-robot SLAM map fusion [22,23], many of which attempt to propose a robust loop closure method to address the problem of outliers introduced by perceptual aliasing and perform map fusion. For initialization problems, the concept of "anchor nodes" is proposed to convert individual nodes of each pose graph into a global frame [24].…”

A Review on Map-Merging Methods for Typical Map Types in Multiple-Ground-Robot SLAM Solutions

“…The complete map-merging process is shown in Figure 2. In recent years, several reviews on multi-robot SLAM have been presented in the literature, such as [2,9,[18][19][20]. The emphases of these works differ from each other: Saeedi et al [9] first briefly introduced the existing single-robot SLAM algorithms and then explained the issues with multi-robot systems.…”

“…However, the map-merging problem, which is significantly affected by communication, has not been investigated in detail in this work. Andersone [20] summarized the latest research in homogeneous and heterogeneous map merging and pointed out six important factors that influence map merging. The state-of-the-art multi-robot SLAM solutions are summarized in the above works from different perspectives.…”

“…To supplement the above review works on multi-robot SLAM and provide the readers with a more comprehensive understanding in map fusion, in this paper, the map-merging methods for three typical map types are reviewed in detail. In recent years, several reviews on multi-robot SLAM have been presented in the literature, such as [2,9,[18][19][20]. The emphases of these works differ from each other: Saeedi et al [9] first briefly introduced the existing single-robot SLAM algorithms and then explained the issues with multi-robot systems.…”