Map Matching and Data Association for Large-Scale Two-dimensional Laser Scan-based SLAM

Abstract

Reliable data association techniques for simultaneous localization and mapping (SLAM) are necessary for the generation of large-scale maps in unstructured outdoor environments. Data association techniques are required at two levels: the local level represents the inner loop of the mapping algorithm, and the global level where newly mapped areas are matched to previously mapped areas to detect repeated coverage and close loops. Local map building is achieved using a robust iterative scan matching technique incorporated into an extended Kalman filter where the state consists of the current pose and previous poses sampled periodically and at a fixed lag from the current time. The introduction of states at a fixed time lag significantly reduces the growth of errors in the location estimate and the resultant map. For global matching, we enhance existing histogram cross-correlation techniques, introducing entropy sequences of projection histograms and an exhaustive correlation approach for reliable matching in unstructured environments. This enables loop closure without depending on prior knowledge of map alignment. These data association techniques are incorporated into the Atlas SLAM framework, enabling the generation of accurate twodimensional laser maps over tens of kilometers in challenging outdoor environments.

Towards Exploiting the Advantages of Colour in Scan Matching

“…The cost function is changed in order to match points that belong to similar surfaces in the variant proposed by Triebel et al [9]. Bosse and Zlot [17] have proposed an improvement based on "the addition of robust optimization techniques to handle outliers and imperfect correspondences between the data". A traditional improvement applied to ICP is to incorporate additional information to the points of the clouds [18,19].…”

Robust place recognition for 3D range data based on point features

“…A combination of rotation-invariant features is extracted from the scans and a binary classifier based on boosting is used to recognize previously visited locations. Bosse and Zlot [4] also presented a loop closing solution for 2D range data. They build local maps from consecutive 2D scans for which they compute histogram-based features.…”

Keypoint design and evaluation for place recognition in 2D lidar maps

“…The combination of orientation and projection histograms has been previously used for localization, where cross-correlations between the histograms determine the relative alignment of two maps [15], [16]. Projection histograms are constructed by projecting each point onto the x-and y-axes of the coordinate frame determined by the keypoint orientation.…”

“…We can visualize the global structure of the map as an adjacency matrix where each element (i, j) indicates whether submap i is adjacent to submap j. Figure 7a shows the ground truth adjacency structure for the kenmore pradoroof dataset which has been constructed using the Atlas framework [16].…”