Vehicle Motion Prediction Algorithm with Driving Intention Classification
Round 1
Reviewer 1 Report
This paper has many similar content with the following documents:
[1] "Research on Prediction Algorithm of Vehicle Speed Based on Driving Intention Classification", 2021 6th International Conference on Automation, Control and Robotics Engineering (CACRE), 2021
[2] "Research on Multiobjective Trajectory Prediction Algorithm Based on Driving Intent Classification", Journal of Physics: Conference Series, 2021
[3] "Research on Prediction Algorithm of Vehicle Trajectory in Front Based on Driving Intention Classification", 2021 4th International Conference on Data Science and Information Technology, 2021
The authors team needs to edit and rewrite the content to avoid plagiarism.
Author Response
Please see the attachment
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The article submitted for review is very interesting and interesting and contributes to the further development of vehicles in the future.
Notes to the article:
1. Does the proposed calculation method take into account sudden, uncontrolled behavior of the driver resulting from, for example, errors of other drivers, the possibility of animals, pedestrians, cyclists and other objects, and affecting the behavior of the analyzed vehicle?
2. The test vehicle could achieve a maximum speed of 69 km/h. Are there any limitations to the vehicle speed of the calculation method presented? For what maximum speed can the presented method be used?
3. Since the algorithm is designed to work not in laboratory conditions, but in open space, it is necessary to take into account the possibility of the emergence of various confounding, emergency, unexpected factors. Question to the first conclusion: how can the resolution and accuracy of the classification be improved to automatically identify the intention to drive the lead vehicle?
4. The second conclusion. The GPR model and the LSTM model are trained with the historical and current moment speed data and trajectory data of different driving intentions, and after the training is completed, the models output the speed and heading angle prediction results under different driving intentions. The question is, how do they take into account the unpredictable behavior of the vehicle ahead resulting from accidents on the roads?
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
In the article, the authors examine the vehicle motion prediction algorithm with driving intention classification.
The Introduction is not very comprehensive. Figure 1 is more typical for an article in a popular rather than a scientific journal. Many of the sources are discussed rather superficially. The methods are described in detail and clearly in the Section II. The results of the experimental research and their analysis are presented in the Section III. It is not clear for what purpose the Figure 3 is presented. There is no point in presenting a generic picture of a vehicle in a scientific article. This Figure does not provide any additional information. Different colors are used in the Figure 4, but there is no explanation of what these colors mean. The conclusions are based on the results of the research.
In my opinion, authors should add a little more information to the Introduction by examining at least some of the main sources in more detail and take into account the other comments.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The author has edited according to the comments of the reviewer, so the article can be published
