Collision Risk Situation Clustering to Design Collision Avoidance Algorithms for Maritime Autonomous Surface Ships

Round 1

Reviewer 1 Report

The article addresses the current issue of the safe operation of MASS. Its main objective was to analyze vessel encounters and identify typical and unique scenarios that can be used to prepare test scenarios for collision avoidance algorithms on MASS in the future.

The paper is prepared with due diligence, but the assumptions and presentation of the results need to be refined. Below are some general comments that should be taken into account to improve the quality of the article:

1 The possibility of using results obtained from monthly observations on a single, selected body of water raises concerns. This is, in fact, noted in the conclusions. However, it should have been discussed further in the body of the article.

2 The classification of vessel encounters into different types should be presented more clearly. It seems to disagree completely with the usual division used in navigation (COLREG). Moreover, the criterion adopted may give two different results. E.g. for a passage from Q1 to Q4 it could be overtaking, crossing courses, or opposite courses encounter.

3. The use of the term “domain” in a sense other than that normally used in the safety of navigation can be misleading.

4. Ship's draught is not one of the static data transmitted by AIS, there are more categories than static and dynamic. The source cited in the text [33] does not state that there are only two types of information.

In addition, the article still needs to be revised for minor linguistic and editing mistakes. E.g.

·         Line 32 – sentence “because ship collisions are the most frequent” is not clear

·         Line 40 – “on the coast” - I guess that means on land

·         Different notation of the word “testbed” E.g. lines 42 and 45

·         Figure 4 - It seems that for CRS(n) there should be a type “combined” used

..

..

..

Author Response

Dear reviewer,

Thank you for your precious comments.

Hereby the authors revised the manuscript and arranged in the attached file.

Please see the attached file.

Author Response File: Author Response.pdf

Reviewer 2 Report

The main points are as follows:

1. The language used is significantly below the required standard. There are numerous confusing sentences ("many ship collisions occur on the coast" - no, they don't). Also, many sentences are too wordy and should be simplified.

2. The structure of the paper should be reconsidered. The problem should be clearly stated, the methodology described and outcomes presented and discussed. Briefly, a standard scientific methodology is not followed. for example, in the conclusions certain limitations are mentioned but not explained or at least identified.

3. However, the idea behind the paper is interesting. The problem tackled will definitely be important in the future.  Also, the methodology seems appropriate (although it is not clearly presented).

Consequently, the authors are invited to rewrite the paper and resubmit it.

Kind regards,

dz

Author Response

Dear reviewer,

Thank you for your precious review comment.

The authors revised the manuscript as the file attached.

Please see the attached file.

Thank you again.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Thank you for taking into account the comments provided in the first review and the clarifications provided. I have no additional comments.

Reviewer 2 Report

There are no additional comments or suggestions.