LiDAR-Based Local Path Planning Method for Reactive Navigation in Underground Mines

Round 1

Reviewer 1 Report

The article presented a path-planning strategy for reactive navigation in underground mines based on the 2D Lidar data. While the article is written based on the field application, which is valuable to the audience interested in implementing Autonomous LHD on their sites, some revisions are recommended for publication.

1)      Professional language revision is recommended. The language is sometimes awkward, and some sentences are hard to understand.

2)      As mining automation is a very active field, especially in recent years, more recent publications should be available on path planning in mining sites.  The reference the authors cited is somewhat outdated except for a few.

3)      Hough transform is a conventional method; its performance varies depending on how it is implemented. It is typically known that having drawbacks in computation time. Thus, a comparison with Hough transformation doesn’t convince the audience that the proposed method is outstanding. As the authors mentioned that network-based approaches are popular, a comparison with one of those methods might be more suitable.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

 Introduction

Abbreviation “autonomous guided vehicles (AGV)” must be written as “Autonomous Guided Vehicle”.

 

Line 25: “ab-solute” must be “absolute”, please revise all the paper.

Line 43: please remove “etc.” or replace it by “such as”. Please check all paper, never use “etc.”.

Line 54: “indoor and indoor environment” I think that it must be “indoor and outdoor environment”.

Line 59: please replace “scholars” by “authors” and then add reference(s), please check all the text.

2. Study Materials

Line 99: please don’t use “we, our and us” try to use the passive voice. please check all the text.

3.1. Binary map

If the walls are far from the vehicle and have not a flat surface, how we can distinguish the wall or the ceiling points from the ground points.

What is the value of map “resolution”?

Line 166: please details these methods.

“within a polygon” what you means (inside the polygon)?

How you define this polygon?

Why you want to determine whether a point is within a polygon?

Line 177: attention for the capital letters, please check all the paper.

3.3. Centerline extraction

Line 186: where is the origin point?

3.5. Method comparison and robustness evaluation

It is important to cite a reference how explains the Hough transform such as the follows:

Tarsha Kurdi, F., Landes, T., Grussenmeyer, P., 2007. Hough-transform and extended RANSAC algorithms for automatic detection of 3d building roof planes from Lidar data. ISPRS Workshop on Laser Scanning 2007 and SilviLaser 2007, Espoo, Finland, Sept. 12-14th. ISPRS International Archives of Photogrammetry, Remote Sensing and Spatial Information Systems. Vol. XXXVI, Part 3 / W52, 2007, pp. 407-412.

 

Borrmann, D., Elseberg, J., Lingemann, K. et al. The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design. 3D Res 2, 3 (2011). https://doi.org/10.1007/3DRes.02(2011)3

4.1. Dataset 1

4.1.1. In the case of going straight

Please add a transition paragraph between two section titles. please check all the paper.

Conclusion

Please highlight the future work in the conclusion.

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

The automatic driving of underground LHD is one of the key technologies to realize intelligent mining. Because of the special structure of the underground environment, reaction navigation is the most widely used method in the mine. This paper presents a lidar-based local path planning method for reactive navigation. The method is novel, and its effectiveness of the method is proved by a large number of experimental data. In general, the paper is well written, and the paper is suggested for publishing after addressing the comments.

 Remarks:

1. Line 56 "un-derground" should be changed to "underground".

2. Lines 267-269 are not clear and should be rewritten.

3. Section 5.1 only deals with the influence of map resolution on the accuracy and efficiency of the proposed method. I suggest modifying the title to highlight this parameter.

4. "error" in line 301 should be an uncountable noun. There are many similar cases in this text. Please correct.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

Reactive navigation is a very practical technology in the automatic driving of underground mine vehicles. Local path planning is one of the key technologies that affect the smooth driving of vehicles. This paper presents a new method for local path planning. In this method, the lidar data is converted into a binary image, and then the tunnel center line is extracted from the image and smoothed by the Bezier curve. This approach is interesting. however, I have a few questions.

 

(1)   In section 3.4, why choose the third-order Bezier curve?

(2)   Whether the smooth path through the Bezier curve meet the requirements of vehicle safety driving?

(3)   Whether the vehicle kinematics model is considered in the local path planning process?

(4)   It is very important to combine this method with a control algorithm to realize the reactive navigation of vehicles. Are you considering further research in this direction in your future work?

(5)   There are some grammatical errors in the paper, please check carefully for corrections.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The authors addressed necessary feedback as much as they could. I appreciate it. 

Reviewer 2 Report

My concerns have been addressed satisfactorily