Improvement of an Adaptive Robot Control by Particle Swarm Optimization-Based Model Identification
Round 1
Reviewer 1 Report
This manuscript introduces a simple and fast PSO-based model identification technique for use in the control of 3 degrees of freedom PUMA-type robot arm via numerical simulations. This is interesting and practical research however, it is highly recommended to address the following concerns.
1. The novelty of this study is not clear, it is recommended to revise the abstract by highlighting the novelty and findings of this study.
2. The importance of this study is not clear. The authors are suggested to state the reason for proposing this algorithm.
3. It is recommended to summarize the contribution of this study at the end of the introduction.
4. It is recommended to increase the understanding of Algorithm 1.
5. The PSO suffers from exploration ability in which it is easily stuck in local optima to solve such problems. The authors are suggested to determine how the proposed algorithm can overcome these challenges.
6. This study suffers from the lack of a deep literature review. It is recommended to give readers the opportunity of reviewing the recent metaheuristic algorithms such as QANA: Quantum-based avian navigation optimizer algorithm, An Improved Moth-Flame Optimization Algorithm with Adaptation Mechanism to Solve Numerical and Mechanical Engineering Problems, and Starling murmuration optimizer: A novel bio-inspired algorithm for global and engineering optimization.
7. The proposed method section with a clear stepwise procedure is recommended.
8. Due to the random nature of the proposed algorithm, a statistical analysis such as the Wilcoxon or Friedman test is recommended.
9. It is recommended to clear the detail of the implementation environment.
10. It is recommended to compare the performance of the proposed algorithm with the related algorithms introduced in this field.
11. Figure 1 is not clear. It is recommended to increase the understanding of this figure.
12. Learning-based control is in the keywords but there is not enough description of it in the manuscript. Please clarify.
13. The convergence behavior analysis is recommended in terms of function evaluation. The number of function evaluations of the proposed algorithm is visualized and compared with the other contenders.
14. The discussion section should be added in a more highlighting, argumentative way. The author should analyze the reason why the tested results are achieved
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The article addresses the problem of robot control using a model based on a particle swarm optimization algorithm.
The article consists of seven chapters. The paper begins with an introduction. Then, in chapter two, the authors describe the adaption strategy in the FPI-based control. The chapter includes both mathematical formulas and a flow chart which helps in understanding the issue. Chapter three presents the model dynamics. This is followed by a brief description of the teaching PSO strategy in chapter four. Chapter five provides an extensive demonstration of the obtained results. The paper is completed with chapters six and seven, which present, in turn, a discussion of the obtained results and final conclusions.
The article is written correctly. The structure of the work corresponds to the requirements for this type of publication. The topic is interesting. The flow of information is logical. The whole is presented in a clear and transparent manner, which helps in understanding.
Although the reviewer has a few comments of a general nature:
1) It is recommended that the Introduction chapter be divided into two chapters, Introduction and State of Art, in order to describe the issue more clearly. I strongly recommend the authors to add one paragraph discussing the difference between their work and the previously performed studies in literature.
2) Authors' own contributions are not clearly stated. The contributions of the article must be emphasized in terms of originality, significance, and performance metrics in the abstract and introduction section. What are the contributions of this paper exactly? Can the authors list them, for example in the form of a bullet list?
3) The conclusion chapter is too short and general in relation to the rest of the text. In addition, it lacks specific numerical results. The reviewer recommends expanding the chapter.
4) For both the analysis of the results obtained in the Discussion chapter and the Summary chapter, it is suggested to use numerical values to show the differences between the cases. This will allow the reader to get a quicker idea of the results.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
This paper presents an identification technique based on simple and fast PSO. The applicability of this method is shown for a 3-DOF PUMA-type robot arm. Numerical results are presented to back the technique. Overall, the paper is nicely written and the results are properly presented. I have just a few suggestions and comments for the authors.
1. Abstract is to the point, which is great. However, a line or two at the start about PSI will be good.
2. The introduction section is nicely written. It is quite thorough. I felt it was a little too long, but the story makes sense. You can perhaps think of splitting it into two sections.
3. Figure 1 needs more information in the text as well as in the caption. It is okay to repeat a few lines from the text, as far as the caption is concerned. What do the arrow colors mean in the figure? The purple arrow at the top is missing annotation. What do the blocks colors mean?
4. Results are nicely presented. Again, I would have liked more descriptive captions. You can refer to any good quality journal paper for example.
5. I loved the zommed-in versions in figs 13-21.
6. I feel the conclusion section was a little too small. Please consider highlighting the results and its general applicability in more details. The future work part is good.
7. I would love to see a little bit more discussion on experiments with actual physical robot.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Most of the comments have been responded to and I recommend the revised manuscript for publication.
Author Response
"Thank you for your efforts and comments. All suggested modifications by the Reviewer had been covered."
Reviewer 2 Report
Thank you. All of the remarks have been addressed. I have no further comments.
Author Response
"Thank you for your efforts and comments. All suggested modifications by the Reviewer had been covered."
