Drone-Aided Path Planning for Unmanned Ground Vehicle Rapid Traversing Obstacle Area

Round 1

Reviewer 1 Report

This study explores the practical application of mobile collaborative operations between unmanned vehicles, which optimizes object detection, image recognition, and path planning, and looks forward to achieving the best execution performance of the cooperative operation. It has presented patterns in the experiments and pre-assigned a pair of starting and goal points to each pattern as a corresponding experiment.
The research design is appropriate. The methods and results are adequately described. The results are clearly presented. The conclusions are supported by the results.

The figure and its capture are not on the same page (Figure 4, 30.)
The table and its capture are not on the same page (Table 10.)

The figures and tables have been placed on two pages in several cases. Where possible, merge them on a page by moving the text section.

Check the styles of tables and figures. Follow the same formatting (e.g. line spacing, text and figure spacing).

Minor spell check required.

The results are merely described and are limited to comparing the experimental observation. The authors are encouraged to include a more detailed discussion section and critically discuss the observations from this investigation with existing literature. The findings and their implications should be discussed in the broadest context possible and the limitations of the work highlighted. Future research directions may also be mentioned. This section may be combined with Results.

In general, the article makes a good impression, is devoted to an interesting problem of Path Planning.

Author Response

The manuscript ID: 1675669

Response to reviewer’s comments

 

Reviewer1

Comments and Suggestions for Authors

 

1. The figure and its capture are not on the same page (Figure 4, 30.).

 

Ans.: In this revision, we have adjusted the figure and its capture on the same page (Figures 4 and 30).

 

2. The table and its capture are not on the same page (Table 10.).

 

Ans.: In this revision, we have adjusted the table and its capture on the same page (Table 10).

 

3. The figures and tables have been placed on two pages in several cases. Where possible, merge them on a page by moving the text section.

 

Ans.: In this revision, we have placed the figures and tables on the same page as possible as we can in several cases.

 

4. Check the styles of tables and figures. Follow the same formatting (e.g. line spacing, text and figure spacing).

 

Ans.: In this revision, we have checked the styles of tables and figures to follow the same formatting, including line spacing, text and figure spacing.

 

5. The results are merely described and are limited to comparing the experimental observation. The authors are encouraged to include a more detailed discussion section and critically discuss the observations from this investigation with existing literature. The findings and their implications should be discussed in the broadest context possible and the limitations of the work highlighted. Future research directions may also be mentioned. This section may be combined with Results.

 

Ans.: In this revision at line 537~577, we have included a more detailed discussion section and critically discuss the observations from this investigation with existing literature. The findings and their implications should be discussed in the broadest context possible and the limitations of the work highlighted.

Finally, thank you for giving the valuable comments to improve this article.

 

Author Response File: Author Response.pdf

Reviewer 2 Report

1. Figure 1 is not precise. Please redraw it; the same for Fig 10, 11, 12 
2. The starting of each section is not clear; the authors insert headers and then another subheader; please write a description at the top of each section
3. Figures and tables are not discussed clearly in the main text 
4. Figure 30 is not clear 
5. The comparisons between other algorithms are not clear and lack referencing
6. Results and discussions are not readers friendly, since there are too many figures without clear and organized explanations
7. Please proofread the whole paper carefully 

Author Response

The manuscript ID: 1675669

Response to reviewer’s comments

 

Reviewer 2

Comments and Suggestions for Authors

 

1. Figure 1 is not precise. Please redraw it; the same for Fig 10, 11, 12.

 

Ans.: In this revision, we have modified Figures 1, 10,11, and 12 as precise as possible.

 

2. The starting of each section is not clear; the authors insert headers and then another subheader; please write a description at the top of each section.

 

Ans.: In this revision at lines 110~112, 221~222, 271~273, and 340~341, we have written a description at the top of each section.

 

3. Figures and tables are not discussed clearly in the main text.

 

Ans.: In this revision, we have discussed figures and tables clearly in the main text.

 

4. Figure 30 is not clear.

 

Ans.: In this revision, we have modified Figure 30 as clear as possible.

 

5. The comparisons between other algorithms are not clear and lack referencing.

 

Ans.: In this revision at lines 279~280 and 318~320, we have compared between other algorithms to be clear and with referencing.

 

6. Results and discussions are not readers friendly, since there are too many figures without clear and organized explanations.

 

Ans.: In this revision at line 537~558, we have reorganized the explanations of results and discussions to be readers friendly.

 

7. Please proofread the whole paper carefully.

 

Ans.: In this revision, we have proofread the whole paper carefully.

 

Finally, thank you for giving the valuable comments to improve this article.

Reviewer 3 Report

The authors of this research present an interesting work, by proposing a drone-aided path planning approach to help unmanned ground vehicle (UGV) traverse an unfamiliar area with obstacles. They have used algorithms YOLOv4-CSP to identify obstacles and the New Bidirectional A Star (NBA*) algorithm to plan a route to avoid ground objects.

Major Comments:

• Title: The second part of the title, "Quick...Area" could be removed or at least improved. In particular, the word "Quick" is always a relative measure of the speed of a process, and depending on who is reading the paper, could in fact be slower, compared to other methods.
• Section 3.1.2 - Unmanned ground vehicle (UGV) was already described in a previous paper from the same author and could be avoided; This paper should be in the reference list:  hang, Bao Rong, et al. "Unmanned mobile multipurpose monitoring system—iMonitor." Sens. Mater 33 (2021): 1457.
• Section 3.1.3. Unmanned aerial vehicle (UAV) was already described in a previous paper from the same author and could be avoided; This paper should be in the reference list: Chang, Bao Rong, et al. "Distributed sensing units deploying on group unmanned vehicles." International Journal of Distributed Sensor Networks 17.7 (2021): 15501477211036877.
• Does the path algorithm take into consideration the width and length of the UGV? From Figure 8, it seams that this is not taken into consideration, the path is too close to the obstacles.
• A final comment is related to the behaviour of the system, if the obstacles found on the path are different, such as bridges (the UGV could go beneath) or a path with holes and uniformities.

Minor Comment:

line 16: imagine -> image

line 19: NBA* acronym should be described in the abstract

line 72, 78, 92, 245 : CNN, R-CNN, SLAM,  CTG acronyms meaning should be described.

line 102-104: The sentence is misleading. In fact, the paper present a fast method to obtain the optimal path for the UGV to traverse a path with obstacles, but the speed with which the UGV will go though the path depends on other factors, such as the motor power, electrical drivers and battery energy, and of course, the ability of the human in command of the UGV. In brief, this sentence must be improved.

line 132: Figure 1 quality must be improved. The text on the blue bubbles is not recognisable and unreadable.

line 168: Figure 3 quality should be improved. imonitor instead of imointor.

line 172: Table 3: MHz instead of Mhz; GHz instead of Ghz; check the entire document for this common error.

line 452:  disply -> display

Overall document: The authors use the term "user" many times along the paper, but I believe that this could be modified to "authors" or "we".

 

 

 

 

 

Author Response

The manuscript ID: 1675669

Response to reviewer’s comments

 

Reviewer 3

Comments and Suggestions for Authors

 

1. Title: The second part of the title, "Quick...Area" could be removed or at least improved. In particular, the word "Quick" is always a relative measure of the speed of a process, and depending on who is reading the paper, could in fact be slower, compared to other methods.

 

Ans.: In this revision, we use the word “rapid” a state description instead of the word “quick” an action description in the revision.

 

2. Section 3.1.2 - Unmanned ground vehicle (UGV) was already described in a previous paper from the same author and could be avoided; This paper should be in the reference list: Chang, Bao Rong, et al. "Unmanned mobile multipurpose monitoring system—iMonitor." Sens. Mater 33 (2021): 1457.

 

Ans.: In this revision, the published paper has cited here at line 144, and the key points are briefly described here, allowing readers to quickly understand the content.

 

3. Section 3.1.3. Unmanned aerial vehicle (UAV) was already described in a previous paper from the same author and could be avoided; This paper should be in the reference list: Chang, Bao Rong, et al. "Distributed sensing units deploying on group unmanned vehicles." International Journal of Distributed Sensor Networks 17.7 (2021): 15501477211036877.

 

Ans.: In this revision, the published paper has cited here at line 167, and the key points are briefly described here, allowing readers to quickly understand the content.

 

4. Does the path algorithm take into consideration the width and length of the UGV? From Figure 8, it seems that this is not taken into consideration, the path is too close to the obstacles.

 

Ans.: In this revision at line 385~393, the object detection model displays the position of the obstacle in the binarized image map through the bounding box as shown in Figure 16 (e) and (f), and the portion of that image with the distance between any two obstacles that exceeds 1.3 times the width of the vehicle is used as the image background to plan the candidate paths. Therefore, the planned path is wide enough to let UGV pass. The path planning algorithm in this study mainly draws the shortest-straight-line path between the starting point and the goal point as shown from Figure 16 (g) to (l), and user then can remotely control UGV to move forward through the obstacle area according to the path planning result.

 

5. A final comment is related to the behaviour of the system, if the obstacles found on the path are different, such as bridges (the UGV could go beneath) or a path with holes and uniformities.

 

Ans.: In this revision at line 546~558, the bridges (the UGV could go beneath) or a path with holes and uniformities can be described as the limitations of the work highlighted in the discussion section. They will be mentioned as kind of future research directions in the conclusion section.

 

6. line 16: imagine -> image.

 

Ans.: In this revision, the typo has been corrected.

 

7. line 19: NBA* acronym should be described in the abstract.

 

Ans.: In this revision, NBA* acronym has been described in the abstract.

 

8. line 72, 78, 92, 245 : CNN, R-CNN, SLAM, CTG acronyms meaning should be described.

 

Ans.: In this revision, CNN, R-CNN, SLAM, CTG acronyms meaning have been described in the related work section.

 

9. line 102-104: The sentence is misleading. In fact, the paper presents a fast method to obtain the optimal path for the UGV to traverse a path with obstacles, but the speed with which the UGV will go through the path depends on other factors, such as the motor power, electrical drivers and battery energy, and of course, the ability of the human in command of the UGV. In brief, this sentence must be improved.

 

Ans.: In this revision, we have improved this sentence at line 105~107.

 

10. line 132: Figure 1 quality must be improved. The text on the blue bubbles is not recognisable and unreadable.

 

Ans.: In this revision, we have improved Figure 1 quality.

 

11. line 168: Figure 3 quality should be improved. imonitor instead of imointor.

 

Ans.: In this revision, we have improved Figure 3 quality and corrected the typo in the figure.

 

12. line 172: Table 3: MHz instead of Mhz; GHz instead of Ghz; check the entire document for this common error.

 

Ans.: In this revision, we have corrected typos in Table 3.

 

13. Overall document: The authors use the term "user" many times along the paper, but I believe that this could be modified to "authors" or "we".

 

Ans.: In this revision, we have modified "user" to "we" somewhere.

 

 

Finally, thank you for giving the valuable comments to improve this article.

Round 2

Reviewer 1 Report

All my comments were taken into account and necessary corrections were made. The article looks much better.

Reviewer 2 Report

The authors have responded to all reviewer comments, and the reviewer recommends accepting this paper.