Applying a Novel Image Recognition Curve-Fitting Control Strategy Combined with a Cloud Monitoring Technique into an Electric Self-Driving Vehicle (ESDV) to Improve Its Operation Efficiency

This article deals with the field of autonomous driving of electric vehicles, and this topic is highly relevant and interesting for readers. The aim of this research is to develop a control strategy for track tracking using image detection cameras with real-time transmission to a cloud-based monitoring website, which allowed researchers to adjust control parameters and quickly remove road obstacles.

In the introduction, the authors mention the motivation for working on this research. The control system is described in detail in terms of the components used. Similar works with references to relevant relevant publications are also listed. The article is interesting but has several serious flaws.

1

The chassis kinematics are not clear from Figure 2. The description of the vehicle is unclear and incomplete. If the functional model includes 2 motors in the rear wheels, how about turning the front wheels? Are the front wheels freewheeling? If the skid steer is the difference in the speed of the front wheels, then the front wheels will resist turning the chassis. This can cause track tracking problems and cause deviations. How is it in this model?

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have added Figure 3 and relevant instructions, then updated the front and rear wheels’ specifications in Table 1.

A servo motor steers the ESDV’s two front wheels, and two DC motors drive the two rear wheels. The four wheels used this time are anti-skid tires. Therefore, there will generally be no slippage problem in ambient operation and no significant wheel speed difference.

The details have been added in Lines 122-139, Pages 5 and 6.

2

What function does a servomotor perform? Does it spin the front wheels? But then, is the turning the same for both wheels or is the turning radius respected, as is the case with Ackermann Steering?

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have added Figure 3 and relevant instructions, then updated the front and rear wheels’ specifications in Table 1.

This ESDV’s steering design allows the two front wheels to steer at the same angle, not using the Ackermann steering.

The details have been added in Lines 122-139, Pages 5 and 6.

3

Is the position of the vehicle somehow recorded by some sensors? There is no position sensor in the component list.

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have added Figure 3 (b) and relevant instructions to this revised manuscript.

In this study, the ESDV uses the main camera for road image recognition, controls the vehicle to run in the lane, and the secondary camera for lane side marking recognition; two ultrasonic sensors judge whether there are obstacles in front and rear. When there are obstacles, the horn will emit a warning sound. Furthermore, this study did not use a position sensor.

The details have been added in Lines 131-139, Page 6.

4

What units do the parameters on page 12 have: "a = 0.02, b = −0.581, and c = 30.03" and "d = −0.08, e = 5.8, and f = −60"?

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have added Figure 11, updated Figure 12 (original Figure 10), and more related descriptions. The parameters a, b, c, d, e, and f are constant. Thereby, the parameters have no units.

The details have been added in Lines 237-261, Pages 13 and 14.

5

Please distinguish which quantities are scalar and which are vector or matrix. See the article template.

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have updated Figure 12 (original Figure 10), and related descriptions.

The details have been added in Lines 245-261, Pages 13 and 14.

6

The conclusion of the article is very brief. It is not clear what the novelty and main contribution of this research is compared to other works. The solution to the defined problem is similar to other works and it is not clear what makes the article different. Benefits and improvements over other outcomes need to be better described.

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have enhanced the novelty and contribution explanation of this revised manuscript.

The details have been added in Lines 325-355, Pages 17 and 18.

7

A more detailed discussion is missing than scientific articles of this type tend to have. There is also a lack of a critical view of the obtained results and weak points of the proposed solution. It is then necessary to establish plans for future research to solve these problems.

Reply:

Many thanks to the Reviewer’s reminder. For this revision of the manuscript, we have rewritten scholarly analytical figures (as shown in Figures 10 to 12), equations (as shown in Equations (1) and (2)), and detailed explanations.

The details have been added in Lines 224-261, Pages 12, 13, and 14.

8

This article looks like a student paper and lacks scientific contribution. I recommend significantly reworking the article.

Reply:

Many thanks to the Reviewer’s reminder. For this revision of the manuscript, we have rewritten scholarly analytical figures (as shown in Figures 10 to 12), equations (as shown in Equations (1) and (2)), and detailed explanations.

The details have been added in Lines 224-261, Pages 12, 13, and 14.

The issue of self-driving vehicles is very important and current. Given that worldwide the number of motor vehicles is constantly increasing, and the share of electric vehicles is also growing rapidly, the topic addressed by the authors of the paper is very useful and has a high chance of being implemented in the electric vehicle manufacturing industry. Any scientific contribution towards increasing the efficiency and quality of automated driving of a vehicle produces important effects from a financial point of view as well.

The ESDV proposed by the authors in the paper uses two cameras to detect images and transmit them to the real-time vehicle path monitoring web page, allowing users to adjust control parameters and promptly identify road obstacles.

The authors aimed to develop an image-based trajectory control strategy (IRCF) combined with a cloud monitoring technique and apply it to electric self-driving vehicles (ESDV) to improve operation efficiency. The IRCF control method proposed by the authors was compared with the traditional Hough line detection method on a 110-meter road, and the results showed that the proposed control method is more effective than the methods presented in the literature.

As a result, the integration of the proposed control method into the automatic driving assistance system can improve the operation efficiency of the ESDV. Furthermore, the combination of obstacle detection and traffic sign detection functions for ESDV used in this paper better meets the actual operation requirements of ESDV on the road.

1

The camera used for path detection provides real-time imaging. Their processing is also done in real time. What is the maximum speed at which the vehicle can travel so that the images can be proce.

Reply:

Many thanks to the Reviewer’s reminding. In this study, the speed of ESDV can reach 3 km/h, which is very stable for image transmission to cloud monitoring. In addition, ESDV’s camera provides real-time imaging to cloud monitoring through Wifi, so the Wifi speed is high and ensures good image quality.

2

From the data presented in Table 2, it follows that the speed of the vehicle (experimental model), controlling the travel trajectory using the method proposed in the paper is 1.68 m/s (6.048 km/h), lower than when using methods presented in the literature with 7.18%. Is this not a disadvantage of the proposed method?

Reply:

Many thanks to the Reviewer’s reminder. We have modified the ESDV’s speed in Table 2.

3

Under what conditions the experimental results obtained using the experimental model can be generalized for real vehicles? Clarifications are needed in this regard.

Reply:

Many thanks to the Reviewer’s reminder. Our explanation is as follows. Most conventional auxiliary control systems for self-driving cars use LiDAR for environmental analysis and stability control, incurring substantial costs and computational demands. In contrast, the IRCF control strategy demonstrated a particular aptitude for roads marked with white lane markings as campuses and industrial areas. This strategy not only curtailed design expenditures but also reduced computational complexities.

The details have been added in Lines 345-349, Page 18.

4

Are relations 1 and 2 also valid if the vehicle path is non-linear? Clarifications are needed.

Reply:

Many thanks to the Reviewer’s reminder. The authors explain as follows. This study proposes to take the circular road as an example and the ESDV stable operation from the proposed IRCF control strategy. The proposed IRCF control strategy adopts the analysis of the two white lines of the road to take five points and perform curve fitting to allow the ESDV to operate in the lane. If the driving lane path is non-linear, the proposed IRCF control strategy will continuously analyze the two white lines on the road and let the ESDV operate in the lane. The advantage of the IRCF control strategy is to analyze the actual white markings on the road so that it can find the lane promptly boundary and is flexible.

The details have been added in Lines 271-278, Pages 14 and 15.

5

The values of coefficients a, b, c, d, e, f in relations 1 and 2 are not justified by the authors. Clarifications are needed regarding the establishment of the respective values.

Reply:

Many thanks to the Reviewer’s valuable suggestions. We have added Figure 11, updated Figure 12 (original Figure 10), and more related descriptions.

The details have been added in Lines 237-261, Pages 13 and 14.

6

In table 1 battery capacity is measured in mAh not Ah. What is the reason?

Reply:

Many thanks to the Reviewer’s reminder. We have modified the battery capacity of Table 1.

7

In table 1, the nominal voltage of the headlights is specified, but the power value is not specified. Why?

Reply:

Many thanks to the Reviewer’s reminder. We have modified the headlight specification of Table 1.

8

In the situation where the white strips of the road get dirty, the vehicle movement control system still works. Clarifications are needed in this regard.

Reply:

Many thanks to the Reviewer’s valuable suggestions. Our explanation is as follows.

In this study, the proposed IRCF control strategy analyzes the left and right white lines, and the left and right white lines are divided into five points, respectively. Then, the road boundary is drawn by curve fitting. If the white line in a local section is blurred, it will cause deviation in the road boundary drawn by curve fitting, but the ESDV continues to run. As soon as this short fuzzy white line section passes, the proposed IRCF control strategy will continue to analyze the white line boundary of the road, and ESDV will quickly correct and drive on the planned road by the proposed IRCF control strategy. If the left and right white lines become dirty in a large area, the proposed IRCF control strategy cannot operate normally. First, the ESDV will stop when it encounters an obstacle. Furthermore, the ESDV has cloud monitoring technology, which can help researchers observe the operating status of the ESDV and perform troubleshooting, etc.

The details have been added in Lines 290-300, Page 15.      

9

The explanation of Figure 5 is written twice, the first time before Figure 5, and the second time after Figure 5. The necessary correction must be made.

Reply:

Many thanks to the Reviewer’s reminder. We have modified the paragraph.