Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Round 1

Reviewer 1 Report

The authors discuss the Unmanned Aircraft Vehicles (UAVs) safety
conflict detection and resolution methods. They tried to extend the
existing two UAVs to multi-UAVs conflict resolution as reinforcement
learning problem. The authors implement an algorithm based on graph
neural networks and solve multi-UAV conflict through a cooperative
strategy. The paper is well-written with some minor errors.

1.The equations used in the manuscript require clear explanation.
Therefore, the authors are suggested to explain the equations.

2.For full transparency and replicability, the authors should attach /
make available computer code and data to replicate the study easily.
Highly recommended is code with comments which precisely generates the
exact figures and result as in the paper. 

Author Response

Please see attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

I suggest that authors refer to two or three review articles in the field in the literature to make it easier for readers to access the literature. The results are not clearly stated and you need to state the exact relationship between the results and the objectives of the research.

Author Response

Please see attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper implement an algorithm based on graph neural networks. And agents are able to successfully solve the multi-UAV conflicts through a cooperative strategy. But it is very necessary to add more formula description and comparative analysis with algorithm.

Author Response

Please see attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

The display of the results can be more reasonable and clear.