Fuzzy Fusion of Stereo Vision, Odometer, and GPS for Tracking Land Vehicles

Round 1

Reviewer 1 Report

The manuscript entitled “Fuzzy fusion of stereo vision, odometer and GPS for tracking land vehicles” proposes a novel method to reduce the error in the absolute location of an autonomous electric vehicle using fuzzy logic, with the cooperative data fusion of GPS, odometer, and stereo camera signals performed to improve the estimation of autonomous electric vehicle localization.

The manuscript is well written, has a clear structure, and is easy to follow. The results obtained by the proposed method are clearly presented, but some improvements to the visual presentation could be considered. The conclusions are supported by the conducted analysis and obtained results.

Here are some minor comments I would like the authors to address:

1. In the Introduction section, please provide a paragraph describing the structure of the paper.
2. Please increase the visibility of the data in Figures 6-17.
3. Please consider some improvements to the visual presentation of the results to be more compact and allow easier viewing. Grouping figures into subfigures could be considered here.
4. Please mention some challenges and limitations of the presented study in the Conclusion section.
5. Please elaborate in more detail on the stated directions for future research in the Conclusion section.

Author Response

Firstly, we would like to thank you for your valuable comments on our manuscript. We revised the document carefully by taking these comments into account.

COMMENTS TO THE AUTHOR(S):

The manuscript entitled “Fuzzy fusion of stereo vision, odometer and GPS for tracking land vehicles” proposes a novel method to reduce the error in the absolute location of an autonomous electric vehicle using fuzzy logic, with the cooperative data fusion of GPS, odometer, and stereo camera signals performed to improve the estimation of autonomous electric vehicle localization.

The manuscript is well written, has a clear structure, and is easy to follow. The results obtained by the proposed method are clearly presented, but some improvements to the visual presentation could be considered. The conclusions are supported by the conducted analysis and obtained results.

Here are some minor comments I would like the authors to address:

1. In the Introduction section, please provide a paragraph describing the structure of the paper.
2. Please increase the visibility of the data in Figures 6-17.
3. Please consider some improvements to the visual presentation of the results to be more compact and allow easier viewing. Grouping figures into subfigures could be considered here.
4. Please mention some challenges and limitations of the presented study in the Conclusion section.
5. Please elaborate in more detail on the stated directions for future research in the Conclusion section.

 

ARTICLE CORRECTIONS:

1.- In the final part of the introduction, the description of the structure of the article was added with the following statements:

“The paper is organized as follows: Section 2 presents the Materials and Methods that include the General structure of fuzzy tracking system, the Signals Acquisition, Fuzzy Fusion, the fuzzy system stages (Fuzzification, inference and Defuzzification). In section 3 the results are shown. Subsequently, in section 4 of discussion, the results are analyzed and compared to finally show the Conclusions in section 5.”

2.- The letters and parameters of the graphs were modified to make them look larger and more readable.

3.- Figures have been grouped into subfigures for easy comparison and easy viewing.

4.- Some challenges and limitations of the presented study were mentioned in the conclusions.

“One of the most important challenges of this work at a technical level was the synchronization of the sensing time in the three sensors. Challenge that was solved by adding a mark to the file where the data of each source was saved. Among the most important limitations of this work is the speed of movement of the system, since the vehicle that was used reaches a maximum speed of 40 km/hr.”

5.- Added in more detail on the stated directions for future research in the conclusion section.

“We observe two directions in future research, the first towards adding more sensors in the data fusion, such as: IMU, Electronic Compass, Lidar, among others. The second to improve accuracy with fewer sensors for faster decision processing.”

All the changes were marked in red font on the manuscript.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors

Thanks for providing the manuscript. It is a well prepared and organized work however my most concern here is the type of the manuscript. The presented approach is not a novel one and does not expanding the boundaries of science but it is a very good technical paper. I recommend to change the type of the manuscript from Article to technical paper.

Author Response

Firstly, we would like to thank you for your valuable comments on our manuscript. We revised the document carefully by taking these comments into account.

We have made the request to change the article to the technical section to the editorial committee and they answered us that there is no such section. Thank you for your kind observations. However, we examined the state of the art and there are few works that use fuzzy logic in the field of autonomous vehicle engineering to fuse information from sensors. In addition, our proposal reduces the error to a great extent with respect to the current literature.

 

with regards

 

Reviewer 3 Report

A

A fuzzy-based Takagi-Sufgeno inference model aimed t to reduce the location error of an Autonomous Electric Vehicle is proposed.

This research work does not highlight innovative aspects with respect to the well-known existing literature relating to fuzzy fusion systems. In particular, the performance benefits of the proposed method do not emerge clearly.

Authors should clearly highlight these aspects in the introductory section. The architecture of the proposed method presented in Figure 3 must be described in more detail. In particular, the data acquisition and data fusion processes must be detailed in a structured way. Takagi-Sugeno Fuzzy inference systems have long been used extensively in various industrial processes. There does not seem to be any innovative aspects proposed in the proposed data fusion model.

Paragraph 2.4 which describes the fuzzification phase must be completely restructured.

Authors must highlight the innovative aspects of their method. Takagi-Sugeno Fuzzy inference systems have been well known for some time, their use does not give any added value to the proposed research

Author Response

Firstly, we would like to thank you for your valuable comments on our manuscript. We revised the document carefully by taking these comments into account.

We have corrected the article and the changes were made to the manuscript and are indicated in the attached file so that the tables are properly observed.

 

with regards

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

Authors took into account all my suggestions, significantly improving the quality of their manuscript.

There are still some critical points to be analyzed and improved in the text, listed below: - It is necessary to motivate the choice of Gaussian fuzzy sets with respect to other types of fuzzy sets in the fuzzification process. - The legend of Fig. 6 is missing. - It is necessary to highlight the meaning of figure 9 more clearly. Furthermore, the legend of the figure ("fuzzy system with input odometer") is not clear. - A brief discussion on the trend of MAE latitude and longiture errors in Fig. 10 should be inserted in paragraph 3.1.

Author Response

Dear reviewer,

We have heeded the recommendations that he kindly made to our manuscript. In the attached pdf we explain the changes made in detail and in the manuscript in word file the changes are in green.

Thank you very much

Author Response File: Author Response.pdf