Intelligent Path Tracking for Single-Track Agricultural Machinery Based on Variable Universe Fuzzy Control and PSO-SVR Steering Compensation
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThis paper proposed a path tracking algorithm combining a segmented preview model with variable universe fuzzy control, and a heading deviation prediction model based on Support Vector Regression (SVR) optimized by Particle Swarm Optimization (PSO) was introduced, and a steering angle compensation controller was designed, enabling dynamic adjustment of the preview distance for better curvature adaptation, improving turning accuracy. From the simulation and experimental results, it can indeed maintain good curve tracking ability. The research results have certain practical significance.
But overall, there are also some shortcomings.
（1）In Figure 12, it is evident that the Variable universe fuzzy control algorithm requires more turns to achieve a smaller average lateral deviation. Therefore, why is the statistics on turns in Table 5 inconsistent with the figure.
（2）The simulation involves the indicator of path alignment distance, and it is recommended to add corresponding content to the field experiment section. The experimental path can be divided into three parts: upper line segment, turning segment, and straight line segment, and relevant data can be collected separately for better comparability.
（3）The format of the tables in the text may need to be modified, and there are also some necessary spaces, such as line80、101、411 et al.
Author Response
Please see attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsIn this paper, a monorail intelligent path tracking for agricultural machinery based on variable universe fuzzy control and PSO-SVR steering compensation is designed for the complex hilly and mountainous areas, and the effectiveness of the designed algorithm is verified by simulation and real vehicle experiments, which provides a new idea for the navigation system of agricultural machinery and has certain significance in the field of agricultural navigation.
1: Article 2.2 describes the steering and working principle of the vehicle, introduces the vehicle moving forward, turning left and right, and does not mention the reversing principle of the vehicle; Whether the vehicle has a reversing function, if there is a reversing function, please add the principle description.
2: Article 169-170 lines have a turning radius of R and a distance between the wheels and need to be corrected.
3: The equation of state of equation (18) in the article is too abrupt and lacks the formula to be derived.
4: The description of Table 4 in lines 486-502 of the article is not clear, and although the control algorithm proposed in Table 4 has a low frequency of rotations, the average lateral error is large, and the specific reasons need to be analyzed.
5: There is little analysis of the real vehicle test in this paper, and the designed paths are all left turns, no right turns, it is suggested that the designed paths should be comprehensively left and right turns for real vehicle tests to verify the effectiveness of the designed algorithms.
6: The reference format is not standardized and needs to be further corrected.
Author Response
Please see attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsThe article named Intelligent Path Tracking for Single-Track Agricultural Machinery Based on Variable Universe Fuzzy Control and PSO-SVR Steering Compensation proposes a path tracking algorithm combining a segmented preview model with variable universe fuzzy control, enabling dynamic adjustment of the preview distance for better curvature adaptation. However, in order to accept it, the authors must take into account the following observations:
It is advisable to review the typography and formatting of the equations, using the appropriate equation style (for example, numbering, centering, and use of mathematical notation consistent with the rest of the document).
Unify the typographic style in the figures, using the same font format as used in the equations to ensure visual consistency.
It is recommended that the note mentioned in lines 176 and 257 be presented in table format to improve clarity, organization of the information, and its rapid interpretation by the reader.
Recommendation: Expand the description of Figure 7, specifying in greater detail the variables shown and their interpretation in the study context.
It is recommended that the equation format be used on lines 314 and 315 to improve the presentation and facilitate the mathematical reading of the content.
Authors should adequately differentiate the variables and parameters used in the various equations, ensuring consistent notation and avoiding ambiguities that could hinder the reader's understanding.
It is advisable to include the corresponding units on the axes of the figures in the results section to enhance clarity, ensure accurate interpretation of the data, and improve the scientific presentation of the work.
The authors should use the meter scale in Figures 14a and 15a to maintain uniformity in the units used and facilitate the spatial interpretation of the results shown.
A glossary must be added at the end of the document, including definitions of acronyms, technical terms, and symbols used, to facilitate understanding of the content, especially for non-specialist readers.
It is suggested that bold type be avoided when defining variables or in explanatory notes to maintain uniformity in the document style and avoid unnecessary typographical distractions.
Modify Figure 16, as it does not provide adequate spacing between the graphs. Increasing the spacing will enhance readability and facilitate a more straightforward interpretation of the displayed data.
It is recommended that a discussion section compare the methodologies used in this work with similar approaches reported in the literature. This analysis will contextualize the results obtained, identify advantages or limitations of the proposed method, and highlight its contribution to the state of the art.
https://doi.org/10.3390/sym17020301
https://doi.org/10.3390/app14177654
It is recommended to reduce the percentage of plagiarism.
Author Response
Please see attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
Comments and Suggestions for AuthorsIn the evaluated article, the authors aim to improve the accuracy and stability of trajectory tracking by an autonomous agricultural vehicle in complex terrain conditions (especially under variable path curvature and track slippage). To this end, they propose a trajectory tracking algorithm that combines a segmented preview model with variable universe fuzzy control and steering angle compensation using support vector regression (SVR) optimized by particle swarm optimization (PSO).
The topic addressed in the paper is relevant and pertains to a clear gap in the field of autonomous agricultural vehicles, particularly in terms of adaptive path tracking control and steering compensation for vehicles with limited maneuverability.
Compared to existing publications, the novel contribution lies in the steering angle compensation module based on SVR-PSO, which is resistant to nonlinearities and environmental disturbances. This claim is supported by both simulation results and field experiments, which show a significant reduction in the number of turns and in the mean lateral error compared to baseline methods. The authors reference key works in trajectory tracking algorithms, fuzzy logic, SVR, PSO, and agricultural robotics. The cited literature includes both recent and foundational studies, indicating that the literature review is up to date.
Overall, the figures are clear and effectively illustrate the stages of the algorithm, particularly Figures 4–10. The presented block and data flow diagrams help the reader understand the implementation.
From a content point of view, the work is not very objectionable. However, I would recommend some improvements.
a) The parameter tuning process for the fuzzy controller and SVR-PSO should be described in greater detail. As it stands, it is unclear how generalizable the selected values are and how strongly they influence the results.
b) Statistical significance testing for the presented results should be addressed. In Tables 4–6, statistically significant differences could be marked, which would enhance the credibility of the comparisons.
c) Have the authors tested the algorithm at higher speeds or under more extreme terrain conditions?
d) Have the authors analyzed the computational load and feasibility of real-time implementation, which is critical for embedded system applications? It would be valuable to include such a discussion in the text.
e) The simulation results (Figures 11–12) and field experiments (Figures 14–16) are well chosen, but the paper lacks information on the number of experimental repetitions or standard deviations.
Additionally, I have the following editorial remarks:
a) Section 3 and subsection 3.1 are incorrectly formatted.
b) In lines 160–163, assumptions are described. For better clarity, I suggest listing them in bullet points rather than in a continuous paragraph.
c) I suggest moving Figure 3 before the equations, which would improve readability with respect to the analysis of the provided formulas.
d) In line 201, I suggest replacing "here" with "where."
e) In lines 245–247, the word "Where" is bolded and capitalized. This seems unnecessary, and the word should rather start with a lowercase letter.
f) In lines 290, 317, 344, 429, 440, and 473, similar corrections apply: "Where" should likely be lowercase and unbolded.
g) Figures 12, 14, and 15 could be labeled more clearly, along with more informative captions.
Author Response
Please see attachment.
Author Response File: Author Response.pdf
