Scan registration for autonomous mining vehicles using 3D‐NDT

By Martin Magnusson, Achim J. Lilienthal, Tom Duckett. J. Field Robotics, 2007

786 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/d320a8e155c26ae0d8b2c397d0f4735918302946

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

1. Giorgio Grisetti
2. Martin Magnusson
3. Cyrill Stachniss
4. Wolfram Burgard
5. Kazuya Takeda
6. Yoshiki Ninomiya
7. Shinpei Kato
8. Jacopo Serafin

In Computer Vision and Pattern Recognition

1. Martin Magnusson
2. Giorgio Grisetti
3. Kazuya Takeda
4. Cyrill Stachniss
5. Yoshiki Ninomiya
6. Shinpei Kato
7. Wolfram Burgard
8. Jacopo Serafin

In Geology

1. Giorgio Grisetti
2. Jacopo Serafin
3. Martin Magnusson
4. Eijiro Takeuchi
5. Yoshiki Ninomiya
6. Achim J. Lilienthal
7. Kazuya Takeda
8. Cyrill Stachniss

Citations in the corpus

• Robust localization using 3D NDT scan matching with experimentally determined uncertainty and road marker matching (2017, background): “The normal distribution transform (NDT) can cope with slight environmental changes because an environmental map is represented by a set of normal distributions [10], [11].”
• The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection (2009, methodology): “In our previous work on 3D-NDT [63, 66], an axis/angle rotation representation was used.”
• Localization in highly dynamic environments using dual-timescale NDT-MCL (2014, methodology): “It employs NDT [2, 3] to represent both, the map and the measurements.”
• NICP: Dense normal based point cloud registration (2015, methodology): “As shown in Table II, in terms of processing time, NDT resulted to be the slowest algorithm in computing a single registration.”
• OctoMap: an efficient probabilistic 3D mapping framework based on octrees (2013, methodology): “Surface representations such as the 3D Normal Distribution Transform (Magnusson et al., 2007) or Surfels (Habbecke and Kobbelt, 2007) were recently used for 3D path planning (Stoyanov et al.”
• An Open Approach to Autonomous Vehicles (2015, methodology): “To be precise, we use the 3D version of NDT to perform scan matching over 3D point-cloud data and 3D map data.(3) As a result, localization can perform at the order of centimeters, leveraging a high-quality 3D Lidar sensor and a high-precision 3D map.”
• Autonomous driving based on accurate localization using multilayer LiDAR and dead reckoning (2017, methodology): “In particular, NDT scan matching is considered an efficient method in terms of its memory and computational costs [9], [10], [11].”