Improved Collision Avoidance Algorithm of Autonomous Rice Transplanter Based on Virtual Goal Point

Round 1

Reviewer 1 Report

1. When abbreviations first appear in a paper, it should be indicated by their full name. For example, APF in the abstract should be indicated by their full name instead of being annotated in keywords

 2. Please check the variable character format in the manuscript, some variables are not in italics, as S₃ in formula 10.

 3. It is suggest to label the A₂ in Figure5.

 4. Please check if the explanation of A₁ in line 277 is correct, Is it the intersection point of E3 and C3 on the X-axis, respectively,

 5. How was the 52% reduction in lateral distance in line 424 of the manuscript obtained by comparison? Can these two models be directly compared?

 6. What is the relationship between the resultant force and the step length obtained in section 3.1 of the article and the steering system of the vehicle, and how to control the steering and moving of the vehicle?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This contribution presents original ideas in the study and
advances the previous research in this area. The level of the
originality of contribution to the existing knowledge with an
emphasis on the paper’s innovativeness i n both theory
development and methodology used in the study is very high.
This work makes a significant practical contribution and it makes
impact on the research work on the research community.
The quality of arguments, the critical analysis of concepts,
theories and findings, and consistency and coherency of debate are well addressed in this paper.
The paper has a good writing style in term of accuracy, clarity,
readability, organization, and formatting.

Nevertheless, the following issues should be addressed:

 In figure 8. the flow chart of the improved obstacle avoidance algorithm is shown, please clarify if there are some singular situation in which the algorithm does not find the solution. In fact the algorithm is organized  with feedback and in this sense, please explain how you guarantee  that the solution is found.

- In the algorith of Figure 8, a thrshould is defined, Please clarify better how the choice of this threshold influences the "quality" of the solution.

- Minors:

Please improve the quality of the figures and try to comment through the text the results and to refer  the results with the corresponding figures more i depth. This can help the redability of the paper.

Nevertheless good paper which deserves publication.

Concerning the cited literature you can consider the following papers to improve the tutorial aspects of the paper.

M. Hedman et al., "FFTSMC with Optimal Reference Trajectory Generated by MPC in Robust Robotino Motion Planning with Saturating Inputs," 2021 American Control Conference (ACC), New Orleans, LA, USA, 2021, pp. 1470-1477, doi: 10.23919/ACC50511.2021.9482876.

De Simone, M.C. ; Rivera,Z.B. ; Guida, D . Obstacle avoidance system for unmanned ground vehicles by using ultrasonic sensors. Machines, 2018, 6(2),1-13.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

General concept comments:

In this work, the authors propose a trajectory planning method for obstacle avoidance based on the enhanced artificial potential field (APF). The objective is to ensure the safety and efficiency of the operation of an autonomous rice transplanter. The manuscript is interesting and its strengths are solidity, contextualization and detail. Furthermore, the results obtained from the research are relevant, demonstrating that the proposed improved algorithm avoids collisions, being highly effective and realizable. However, some improvements could be made and would certainly improve the quality of the text.

Revision:

The text, in general, is well organized. The authors were efficient in contextualizing the problem, as well as providing justifications for conducting the research; especially in the introduction where current and classic references are adequately mixed to support the work. There is clearly a knowledge gap explored and the related aspects are well outlined by the authors who argue to compensate for the deficiency of current studies by proposing an improved collision avoidance algorithm for unmanned rice transplanters.

I believe that the “material and methods” section is very detailed and the controls presented are adequate to achieve the objectives that were sought. However, analyzes were carried out in a simulated scenario and with field data and these details and controls regarding these procedures should be listed in the “material and methods” section. This information appears in the first paragraphs of sections 4 and 5, but I believe that would not be the best place to present it.

In results (sections 4 and 5), the authors were faithful to the research objectives. Furthermore, the tables and graphs are of adequate quality and number to illustrate its main findings. However, the titles of some tables and Figures are very brief and the titles should be self-explanatory. As already explained, the details and materials used for the analyzes (simulation and field data) should be in the material and methods section. It also remains to be said that the arrangement of some tables could be better organized with the texts. Finally, I believe that comparing and discussing the results of this work with the literature could be very enriching and this was not done by the authors.

The conclusions are presented correctly and highlight the main results in accordance with the stipulated objectives.

Specific Comments:

In “Materials and Methods” - add information about the simulated data and field data that were used in the work. This information appears in the Results section, but I believe the correct place is not there.

In general, in some Figures the titles are very brief (examples: Figure 2, Figure 7, Figure 17, and others), they could be self-explanatory. I recommend that you review and adapt when necessary.

First paragraph of section 4 and first paragraph of section 5: this information should be in the material and method section.

In Tables 2 and 3: the results of these tables should be better explored. I recommend presenting table 2 with explanatory text below and then presenting table 3 and commenting on it.

As already explained, discussions of the results found in the literature could enrich the work. This could be done in sections 4 and 5.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

At the moment, progress is evident in the implementation of autonomous vehicles for agricultural use. An important issue is the ability of autonomous vehicles to recognize potential hazards arising from their trajectory across the field. The article contains relevant content on machine learning for determining the movement trajectories of autonomous vehicles. The content presented is timely. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 5 Report

One goal of mobile robotics research is to build robot controls that can safely perform missions in robot-dedicated environments. To achieve this task, it is necessary to create systems that can perceive their environment, react to unforeseen circumstances to achieve their mission. The aim of prsented study was to develop an efficient, low-cost and collision-free real-time path planning algorithm. Using the artificial potential field method, abbreviated APF, the authors attempted to describe cases involving the avoidance of obstacles whose shape was either circular or elliptical.

The authors focused only on the analysis of the kinematics of the robot's movement, without considering the dynamics, even in the discussion, which I consider to be a major shortcoming of this manuscript. A robot moving in a field is exposed to vibrations caused by the unevenness of the terrain or the muckiness of the soil on which it moves. In my opinion, additional space should therefore have been included in the analysis due to these unforeseen inconveniences. 

The authors did not illustrate the analysed cases very accurately in the graphics presented in the manuscript and presented them too generally. It is required that the authors complete the drawings in or indicate in the drawings the dimensions that they then take into account in the calculations:

- figure 2, no marking or indication of the dimensions W0, W1, L0 and L1

- figure 3, no marking or indication of the value of D0, this drawing is too general in relation to the description under the drawing, should be corrected,

- figure 5, no marking or indication of A points on the drawing, the current description is not sufficient for the reader, this point should be marked on all sub drawings of figure 5,

- figure 10 is also not very legible, radii Rmcr and Rth are not indicated, indicated points and curvature dimensions in brackets are poorly visible and not very legible in figure 10.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

There are no other suggestions after modification, it can be accepted.