Formation Transformation Based on Improved Genetic Algorithm and Distributed Model Predictive Control
Round 1
Reviewer 1 Report
A summary: This study proposes a distributed formation transformation algorithm that decomposes the formation transformation problem into target matching problems and trajectory planning problems. According to the actual formation transformation requirements, the target allocation index was proposed, and the improved genetic algorithm was used to achieve target matching. The adaptive cross-mutation probability was designed, and the population was propagated without duplicates by the hash algorithm. The multi-objective algorithm of distributed model predictive control is used to design smooth and conflict-free trajectories for the UAVs in formation transformation, and the trajectory planning problem is transformed into a quadratic programming problem under inequality constraints. Finally, point-to-point collision-free offline trajectory planning is realized by simulation. I read the article, and this paper is well-written and contributes to the body of literature. However, I do have some concerns with the current version that need correction during the revision. I believe the following comments can further enhance this paper's quality.
General concept comments:
1- In the abstract, please add the performance improvements with numbers and %ages rather than fuzzy words. Also, the details of the proposed method in incomplete.
2- In the introduction, please write the implications (theoretical and technical significance) of your work in the contribution section by highlighting existing problems well. Also please write the contribution with bullets.
3- Please write the conclusion as a separate section by summarizing the main contents.
4- Also, the authors should provide some analysis regarding the time and space complexity of the proposed method.
5- Some more discussion about the result before the conclusion is desirable. Authors can provide some details of experiments and challenges that can stem from working in dynamic environments.
6- Although this method seems rational, what are some challenges or limitations of this work?
7- What is the uniqueness and novelty of this paper compared to existing work? I think many such works have already been proposed with extensive evaluations.
Specific comments:
Line #: 72, the English should be improved.
Line #: 105: The equation number is missing.
After line # 434 add some information regarding the challenges one can face while implementing the same algorithm.
I found some English mistakes in the paper, and therefore, a careful proofreading is needed.
Author Response
Dear reviewer,
Thank you very much for taking the time to review this manuscript. We sincerely appreciate your valuable comments and insightful suggestions. We have thoroughly considered each of your comments and have made every effort to address them appropriately. Below, we present the reviewer's comments in normal font, and specific concerns have been numbered. Our response is given in normal font as well, and the changes/additions to the manuscript are highlighted in red text.Please see the attachment.
Best regards
Author Response File: 
Author Response.docx
Reviewer 2 Report
This article proposes a distributed formation transformation method to solve the problem of multiple unmanned aerial vehicle formation transformation. Initially, the algorithm decomposes the formation transformation problem into two independent problems: target matching and trajectory planning. The improved genetic algorithm is used to achieve target matching, the multi-objective algorithm with distributed model predictive control is used to solve the trajectory planning problem， and the trajectory planning problem is transformed into a quadratic programming problem, which has certain scientific significance. However, there are many shortcomings in the article that need further modification. The suggestions given are as follows:
1. This article only decomposes the formation transformation problem into two independent sub problems, what is the innovation of the proposed algorithm?
2. In the experimental simulation in section 4.3, the number of formation UAVs selected is 13 UAVs, but it can be seen from the simulation verification of UAV target assignment algorithm that when 13 UAVs are used, the improved genetic algorithm proposed in this article is worse than the Hungarian algorithm. How to demonstrate the superiority of the algorithm proposed in this article.
3. Please conduct a detailed analysis of the simulation results in the article, e.g. section 4.1.
4. In section 4.3, there are two figures (figure15 and figure19)that are too small to read clearly.
5. The title contains "distributed", but the article does not mention it. What is the manifestation of distributed?
6. In section 4.2, simulation experiments were conducted using the initial formation of 4 UAVS as rectangles, but in the system algorithm simulation experiment in section 4.3, 13 UAVS were selected instead. How to prove the feasibility of the algorithm?
7. In the simulation diagram in section 4.1, figure 8 only selects the formation consisting of 5 and 10 UAVs, and compares the Hungarian algorithm with the algorithm proposed in this article on the index of crossing times. However, the algorithm is evaluated by the fitness function, which includes three parts: total moving distance, minimum time and crossing times.
8. Reference [1] and reference [10] are duplicated in the citation list.
9. When the simulation results were presented in section 4, corresponding simulation parameters were not provided, such as the proportion factors a1, a2, a3, etc. in the fitness function.
The English grammar of this article is basically correct, and the expression and logical structure of the literature are relatively clear and coherent. The literature meets academic writing standards. Therefore, there is not much problem with the English part.
Author Response
Dear reviewer,
Thank you very much for taking the time to review this manuscript. We sincerely appreciate your valuable comments and insightful suggestions. We have thoroughly considered each of your comments and have made every effort to address them appropriately. Below, we present the reviewer's comments in normal font, and specific concerns have been numbered. Our response is given in normal font as well, and the changes/additions to the manuscript are highlighted in red text.Please see the attachment.
Best regards
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
I have carefully checked the authors' responses and the revised work. The authors have made the necessary changes in the paper. I don't have any further comments on this paper.
Some grammar and expression mistakes need correction during the final submission.
Author Response
Dear reviewer,
Thank you very much for taking the time to review this manuscript. We sincerely appreciate your valuable comments and insightful suggestions. We have thoroughly considered each of your comments and have made every effort to address them appropriately. Below, we present the reviewer's comments in italics and bold font, and specific concerns have been numbered. Our response is given in normal font, and the changes/additions to the manuscript are highlighted in red text.
Best regards
Author Response File: Author Response.docx
Reviewer 2 Report
Through this revision, this article has made some improvements, but there are still some shortcomings that need further improvement. The suggestions given are as follows:
1. The title of this paper is "Formation Transformation of Distributed Model Predictive Control Strategy", but what are the innovative points about DMPC in this paper?
2. This paper uses the distributed Model predictive control method, and the simulation results only verify the feasibility of the algorithm. What are the advantages compared with other methods, and how to prove them?
3. The paper only simulates and verifies the formation transformation of 13 drones. What happens when there are fewer or more drones?
4. In section 4.3, Figures 15 and 19 are still very blurry, please improve.
5. Some sentences still need to be considered.For example, the sentence on line 109.
The English grammar of this article is basically correct, and the expression and logical structure of the literature are relatively clear and coherent. The literature meets academic writing standards. Therefore, there is not much problem with the English part.But some sentences still need to be considered.
Author Response
Dear reviewer,
Thank you very much for taking the time to review this manuscript. We sincerely appreciate your valuable comments and insightful suggestions. We have thoroughly considered each of your comments and have made every effort to address them appropriately. Below, we present the reviewer's comments in italics and bold font, and specific concerns have been numbered. Our response is given in normal font, and the changes/additions to the manuscript are highlighted in red text.
Best regards
Author Response File: Author Response.docx
