Mission Chain Driven Unmanned Aerial Vehicle Swarms Cooperation for the Search and Rescue of Outdoor Injured Human Targets

Round 1

Reviewer 1 Report

Very interesting research in a decently drafted manuscript that needs some mild revisions. The writing is strong, albeit rough in a few places; and the graphics are very effective to raise a generally scientific readership to understand the topics presented: UAV clusters using LoRa, machine vision and bioradar. The proposed methods are strongly illustrated, but only mildly compared to potential alternatives.

• The manuscript is clear, relevant for the field and presented in a well-structured manner. The cited references are current (mostly within the last 5 years) including some from 2022. The manuscript is scientifically sound, and the experimental design is appropriate to test the hypothesis. The manuscript’s results are reproducible based on the details given in the methods section. The figures/tables/images/schemes appropriate and properly show the data. They are easy to interpret and understand. The data is interpreted appropriately and consistently throughout the manuscript. The conclusions are consistent with the evidence and arguments presented.

Abstract is okay but is not likely to entice the readership to continue reading the rest of the manuscript.

• Results are only presented in weak, qualitative fashion. Highest quality expression of main conclusions or interpretations is quantitative results discussed in the broadest context possible, e.g., percent performance improvement compared to a declared benchmark. “…The results show that this strategy can identify…which is meaningful…” is very weakly stated results compared to “…xxx percent performance improvement over alternative methods was achieved….”

Introduction is decently done with some omitted very recent literature and some mild abuse of multi-citation without elaboration.

• Quadrotor applications are briefly reviewed. Existing UAV network solutions are decently reviewed. Learning approaches are not reviewed. Assertion of usage of stochastic A.I. (DL and CNN) are made in absence of mentioning deterministic artificial intelligence in the literature review, despite its recent application to a wide variety of drones: remotely operated vehicles, unmanned underwater vehicles, spacecraft, even drone actuator DC motors.
• Please elaborate a reason for the reader to investigate each of the quadruple cited references [5-8] in the introduction.
• The sentence in line 78, “Thanks to this, single-stage networks deployed on Nvidia edge devices are optimized to meet real-time and accuracy requirements” is followed in line 80 by “Subsequently, after the UAV cluster obtains the target detection….” without telling the reader the authors’ selected methodology.

Equations are completely absent making the manuscript less scientifically sound and well presented, lowering the overall manuscript quality.  A very pithy explanation of bioradar equations was published by Gouveia et al., in 2019: https://doi.org/10.3390/s19030604 and another excellent work by Kathuria, et al. in 2021: https://doi.org/10.3390/s21113737

Figures are really well done.

Tables are decently done to introduce problem formation (aiding repeatability), but quantitative results are neglected.  Please re-read and correct lines 318 and 319.

• Inclusion of a table defining variables and acronyms in an appendix is welcome and effective. Please add such.

Author Response

Please the attached file.

Author Response File: Author Response.docx

Reviewer 2 Report

The paper presents interesting and original research in terms of the use of UAVs for searching injured people. The authors propose a new complete method which can be used in practice. The method is well described and practical tests are also clearly presented.

The manuscript is well written and should be published.

Remarks:

Line 296, please check if the description for the Figure 10 is correct.

Author Response

Please see the attached file.

Author Response File: Author Response.docx