Navigation of an underground mining machine

Patent metadata

Field	Value
Publication number	US-12475595-B2
Application number	US-202118009848-A
Country	US
Kind code	B2
Filing date	May 28, 2021
Priority date	Jun 18, 2020
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

This disclosure relates to navigation of an underground mining machine. A laser range finder captures first and second 3D point clouds of first and second overlapping parts of the underground mine from first and second positions of the mining machine respectively. A processor determines a first set of candidates for rock bolts as point feature objects from the first 3D point cloud; determines a second set of candidates for rock bolts as point feature objects from the second 3D point cloud; determines an alignment between first shapes defined by at least two of the first set of candidates for rock bolts and second shapes defined by at least two of the second set of candidates for rock bolts; and determines relative location information between the first position of the mining machine and the second position of the mining machine based on the alignment.

First claim

The invention claimed is:

1 . A method for navigation of an underground mining machine, the method comprising:
capturing a first 3D point cloud of a first part of an underground mine from a first position of the mining machine; determining a first set of candidates for rock bolts as point feature objects from the first 3D point cloud by detecting first apex shapes in the first 3D point cloud, the first apex shapes being created by laser light scattering on edges of the rock bolts; capturing a second 3D point cloud of a second part of the underground mine from a second position of the mining machine, wherein the first part and the second part overlap; determining a second set of candidates for rock bolts as point feature objects from the second 3D point cloud by detecting second apex shapes in the second 3D point cloud, the second apex shapes being created by the laser light scattering on the edges of the rock bolts; determining an alignment between first shapes defined by at least two of the first set of candidates for rock bolts and second shapes defined by at least two of the second set of candidates for rock bolts; determining relative location information between the first position of the mining machine and the second position of the mining machine based on the alignment.

2 . The method of claim 1 , wherein determining the alignment comprises determining an alignment value representing a geometric transformation that maps the first shapes to the second shapes.

3 . The method of claim 2 , wherein the geometric transformation comprises a rotation or a translation or both.

4 . The method of claim 1 , wherein the first shapes and the second shapes comprise triangles defined by three candidates for rock bolts.

5 . The method of claim 1 , wherein the method comprises:
creating the first shapes by selecting different combinations of at least two candidates for rock bolts from the first set of candidates for rock bolts; and creating the second shapes by selecting different combinations of at least two candidates for rock bolts from the second set of candidates for rock bolts.

6 . The method of claim 5 , wherein the method comprises:
creating the first shapes by selecting all combinations of at least two candidates for rock bolts from the first set of candidates for rock bolts; creating the second shapes by selecting all combinations of at least two candidates for rock bolts from the second set of candidates for rock bolts.

7 . The method of claim 1 , wherein
each of the first set of candidates for rock bolts defines more than one of the first shapes; and each of the second set of candidates for rock bolts defines more than one of the second shapes.

8 . The method of claim 1 , wherein the method comprises determining multiple alignment values comprising an alignment value between each pair of one of the first shapes and one of the second shapes.

9 . The method of claim 8 , wherein the method comprises:
determining a histogram of the multiple alignment values; and determining the relative location information based on the histogram.

10 . The method of claim 9 , wherein the method comprises:
determining a statistical measure of the histogram; in response to the statistical measure meeting a threshold, determining the relative location information based on a maximum value in the histogram.

11 . The method of claim 1 , wherein the method comprises:
iterating over pairs of shapes, the pairs of shapes comprising one of the first shapes and one of the second shapes; determining an alignment value for one of the pairs of shapes at each iteration; and terminating the iterating over pairs in response to the alignment value meeting a threshold value.

12 . The method of claim 1 , wherein the method comprises detecting apex shapes in a slice of the point cloud.

13 . The method of claim 12 , wherein the method comprises:
projecting points in the slice of the 3D point cloud onto a plane in which the underground mining machine is located; and detecting the apex shapes in the projected points.

14 . The method of claim 13 , wherein the method further comprises accessing the projected points in order of distance from the underground mining machine.

15 . The method of claim 1 , wherein detecting the apex shape comprises detecting a first flank facing towards the underground mining machine which is steeper than a second flank facing away from the mining machine.

16 . The method of claim 15 , wherein the first flank defines an angle from a wall or roof of the underground mine which is between 80 and 100 degrees.

17 . The method of claim 1 , wherein capturing the first 3D point cloud and the second 3D point cloud comprises using a laser range finder that records a distance for multiple rotation angles.

18 . A non-transitory computer-readable medium with program code stored thereon that, when executed by a computer, causes the computer to perform the steps of:
capturing a first 3D point cloud of a first part of an underground mine from a first position of the mining machine; determining a first set of candidates for rock bolts as point feature objects from the first 3D point cloud by detecting first apex shapes in the first 3D point cloud, the first apex shapes being created by laser light scattering on edges of the rock bolts; capturing a second 3D point cloud of a second part of the underground mine from a second position of the mining machine, wherein the first part and the second part overlap; determining a second set of candidates for rock bolts as point feature objects from the second 3D point cloud by detecting second apex shapes in the second 3D point cloud, the second apex shapes being created by the laser light scattering on the edges of the rock bolts; determining an alignment between first shapes defined by at least two of the first set of candidates for rock bolts and second shapes defined by at least two of the second set of candidates for rock bolts; determining relative location information between the first position of the mining machine and the second position of the mining machine based on the alignment.

19 . A navigation system for an underground mining machine, the navigation system comprising:
a laser range finder to
capture a first 3D point cloud of a first part of an underground mine from a first position of the mining machine, and
capture a second 3D point cloud of a second part of the underground mine from a second position of the mining machine, wherein the first part and the second part overlap; and
a processor to
determine a first set of candidates for rock bolts as point feature objects from the first 3D point cloud by detecting first apex shapes in the first 3D point cloud, the first apex shapes being created by laser light scattering on edges of the rock bolts;
determine a second set of candidates for rock bolts as point feature objects from the second 3D point cloud by detecting second apex shapes in the second 3D point cloud, the second apex shapes being created by the laser light scattering on the edges of the rock bolts;
determine an alignment between first shapes defined by at least two of the first set of candidates for rock bolts and second shapes defined by at least two of the second set of candidates for rock bolts; and
determine relative location information between the first position of the mining machine and the second position of the mining machine based on the alignment.

Assignees

• Commw Scient Ind Res Org

Inventors

• Saric Kevin
• Dunn Mark
• Reid Peter
• Thompson Jeremy
• Malos John

Classifications

• G01S7/4817

  relating to scanning · CPC title

• G01C21/20

  Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence) · CPC title

• E21D21/00

  Anchoring-bolts for roof, floor {in galleries or longwall working}, or shaft-lining protection ({ground anchors E02D5/80; anchorings for building constructions E04B1/41, E21D21/00}; dowels or other devices fastened in walls or the like by inserting them in holes made therein for that purpose F16B13/00 {; bolts with visible load G01L1/00}) · CPC title

• E21D9/004

  using light beams for direction or position control · CPC title

• E02F9/264 Primary

  Sensors and their calibration for indicating the position of the work tool · CPC title