6D SLAM—3D mapping outdoor environments

By Andreas Nüchter, Kai Lingemann, Joachim Hertzberg, Hartmut Surmann. J. Field Robotics, 2007

482 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/d4f6a3f133229178d73bf7cb0c42f693856197e2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration (2016, unknown): “Index Terms—3D point-set registration, global optimization, branch-and-bound, SE(3) space search, iterative closest point F”
Low-drift and real-time lidar odometry and mapping (2017, methodology): “For localization and mapping, one way is to perform stop-and-scan to avoid motion distortion in point clouds (Nuchter et al. 2007).”
LOAM: Lidar Odometry and Mapping in Real-time (2014, background): “Lidar has become a useful range sensor in robot navigation [10].”
Towards a benchmark for RGB-D SLAM evaluation (2011, unknown): “Different sensor modalities have been explored in the past, including 2D laser scanners [12], [3], 3D scanners [14], [16], monocular cameras [13], [7], [9], [19], [20] and stereo systems [8].”
OctoMap: an efficient probabilistic 3D mapping framework based on octrees (2013, methodology): “This point cloud approach has been used in several 3D SLAM systems such as those presented by Cole and Newman (2006) as well as in the SLAM approach of Nüchter et al. (2007).”
The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection (2009, methodology): “have used 3D range scans for loop detection [81].”
Loam livox: A fast, robust, high-precision LiDAR odometry and mapping package for LiDARs of small FoV (2019, unknown): “With the ability to provide long range, highly accurate 3D measurements of the surrounding environment, light detection and ranging (LiDARs) is becoming an essential sensor in many robotic applications, such as autonomous driving vehicles [1], drones [2, 3], surveying, and mapping [4, 5].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “D range scans, the point set registration methods (e.g. ICP) (Nüchter et al. 2007) are also used for scan matching and localizing the robot.”
Visual-lidar odometry and mapping: low-drift, robust, and fast (2015, background): “For 3D mapping, a typical sensor is a (2-axis) 3D lidar [13].”
Towards semantic maps for mobile robots (2008, methodology): “(However, note that subsequent steps do require that the data consist of surface points in space, as delivered by laser scan data!) Therefore, we include a sketch of the 6D SLAM part in this paper to make it self-contained; but we keep it short, and refer to [33] for details.”
Globally consistent 3D mapping with scan matching (2008, methodology): “Section 7). Due to these performance issues, we presented several speed-ups for closest point computation in the scan matching context, i.e., approximate k-d tree search and cached k-d tree search [22, 23 ].”
Depth camera based indoor mobile robot localization and navigation (2012, background): “Specific to the problem of building 3D maps with 6 degrees of freedom (6D) localization is 6D SLAM [7], [8] that builds maps using 3D points in space, but these methods do not reason about the geometric primitives that the 3D points approximate.”
Visual simultaneous localization and mapping: a survey (2012, background): “Among the exteroceptive sensors it is possible to ﬁnd: sonar (Tardós et al. 2002; Ribas et al. 2008), range lasers (Nüchter et al. 2007; Thrun et al. 2006), cameras (Se et al. 2005; Lemaire et al. 2007; Davison 2003; Bogdan et al. 2009) and global positioning systems (GPS) (Thrun et al. 2005a).”
Evaluation of 3D registration reliability and speed - A comparison of ICP and NDT (2009, methodology): “We have investigated two algorithms for matching pairs of independently acquired 3D scans: ICP [2], [4], [11] and NDT [3], [10].”