A Proactive Collision Avoidance Model for Connected and Autonomous Vehicles in Mixed Traffic Flow
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe paper presents a model for proactive collision avoidance, by controlling the speed and lane-change behavior of connected and autonomous vehicles.
The proposed model presented in the flowchart of Figure 3 seems to be non-standard - there are no directions (arrows) ... it should also be a standard algorithm, and probably not a model either. In my opinion it is a sketch!
The author needs to clarify the novelty of the research, the name & standards of the model, the flowchart, the process, the proposal appropriate in this study
The article lacks citations, is not clearly written, highlights the novelty, and the author's contribution. The current article does not clarify the novelty, and the article's title about the collision avoidance model is not appropriate Fig.3-proposed in the article.
Comments on the Quality of English Language
Need to review spelling errors, English sentences, and review the correct standards Fig.3
Author Response
Response to Reviewer’s Comments:
We greatly appreciate the reviewer’s thoughtful feedback. Below we address each of the concerns in detail:
Comment 1:
“The proposed model presented in the flowchart of Figure 3 seems to be non-standard – there are no directions (arrows)... it should also be a standard algorithm, and probably not a model either. In my opinion it is a sketch!”
Response:
Thank you for your constructive feedback. We agree that the original version of Figure 3 lacked formal structure and clarity. In response, we have completely redesigned Figure 3 to follow a standard flowchart format, including the addition of directional arrows, clear decision nodes, and a step-by-step logical sequence. The new figure better reflects the structure of our proposed method.
Furthermore, we would like to emphasize that this work introduces a rule-based proactive collision avoidance model We have clarified this distinction in the revised manuscript to avoid confusion. The logic-driven model is structured based on real-time perception and interaction rules between CAVs and surrounding vehicles (both CAVs and HVs), rather than a black-box learning process or numerical optimization framework. All related revisions are highlighted in yellow in the manuscript.
Comment 2:
“The author needs to clarify the novelty of the research, the name & standards of the model, the flowchart, the process, the proposal appropriate in this study.”
Response:
We appreciate the reviewer’s suggestion. To address this:
- We have clearly stated the name and nature of the proposed model as a rule-based proactive collision avoidance model.
- The flowchart has been restructured (Figure 3) to reflect a standard and readable algorithmic logic.
- The decision-making process and functional steps are now elaborated in the method section.
- The novelty of the research is now explicitly emphasized in the Introduction and Conclusion, as outlined below:
“In the context of emergency collision avoidance for CAVs, most studies focus on fully-CAV scenarios, with limited attention to mixed traffic environments… To bridge these gaps, this study proposes a proactive collision avoidance model for CAVs in mixed traffic environments… By integrating safety distance calculations, cooperative lane-change protocols, and adaptive speed adjustments, the system aims to minimize collision risks while preserving traffic fluidity.”
This enhancement helps better position our contribution in the broader research context.
Comment 3:
“The article lacks citations, is not clearly written, highlights the novelty, and the author's contribution. The current article does not clarify the novelty, and the article's title about the collision avoidance model is not appropriate [for] Fig.3-proposed in the article.”
Response:
Thank you for pointing this out. To improve the clarity and academic grounding of the paper:
- We have rewritten the Introduction and Conclusion to clearly emphasize the research novelty and the author’s contribution, particularly regarding the model’s applicability in mixed traffic environments.
- We have added multiple relevant references (e.g., Wang et al., 2023; Muzahid et al., 2023; Ma et al., 2023; Du et al., 2022; Chen et al., 2024) to properly contextualize our work within recent literature.
- We have also revised Figures 3, 5, and 6 to improve visual clarity and consistency with the written content.
- Regarding the article title, we have reviewed it and believe it is appropriate given the updated content and clarified contribution. However, we remain open to further suggestions from the editor if a revision is preferred.
We sincerely thank the reviewer again for these valuable comments, which have significantly helped us improve the quality and clarity of our paper.
Reviewer 2 Report
Comments and Suggestions for AuthorsThis manuscript addresses collision avoidance in mixed traffic scenarios by examining speed and lane-changing behaviors of connected and autonomous vehicles. While the study presents some promising results, there are several areas that require significant improvement before the paper can be considered for publication:
-
Insufficient Introduction: The introduction section is inadequate and does not provide sufficient background or motivation for the study. A more comprehensive overview of the problem domain and its importance is necessary to contextualize the work.
-
Lack of Literature Review: The manuscript lacks a dedicated literature review section. The authors have not sufficiently engaged with existing research, which weakens the foundation of their work. The field of collision avoidance, particularly in mixed traffic environments, has a rich body of literature that should be referenced and critically discussed.
-
Limited Baseline Comparison: The comparison is limited to a single baseline model (CACC), which does not provide a robust benchmark. Including additional models or approaches from recent literature would enhance the credibility of the performance claims.
-
Unjustified Parameter Choices: Several numerical values ("magic numbers") are used in the simulations without adequate justification or reference. The rationale behind these choices should be explained clearly.
-
Simulation Parameters Presentation: The simulation setup and parameters should be compiled into a clear and concise table to improve readability and reproducibility.
-
Language and Grammar: The manuscript requires thorough proofreading. There are numerous grammatical and spelling issues throughout the text that hinder clarity and professionalism.
Author Response
Reviewer 2
- Insufficient Introduction
Reviewer Comment:
The introduction section is inadequate and does not provide sufficient background or motivation for the study. A more comprehensive overview of the problem domain and its importance is necessary to contextualize the work.
Response:
Thank you for this important comment. We have completely rewritten the Introduction section to provide a clearer overview of the problem domain, highlight the significance of mixed traffic collision avoidance, and emphasize the motivation for this study. Additionally, we cited recent and relevant works to better situate our contributions within the existing literature. The novelty of the proposed method is now clearly articulated in both the Introduction and Conclusion. All revised content has been highlighted in yellow in the updated manuscript.
- Lack of Literature Review
Reviewer Comment:
The manuscript lacks a dedicated literature review section. The authors have not sufficiently engaged with existing research, which weakens the foundation of their work.
Response:
Thank you for pointing this out. We have addressed this concern by integrating a dedicated literature review within the Introduction section, which now provides a structured and critical discussion of existing work. The updated review cites multiple recent studies in both general CAV control and mixed traffic collision avoidance, including:
“To improve the efficiency and safety of mixed traffic flow, several researchers modeled the longitudinal and lateral controls of CAVs (Qin and Wang, 2019; Rahman et al. 2019; Silgu et al. 2021; Li et al., 2022)...”
“In the context of emergency collision avoidance... most studies focus on fully-CAV scenarios... there is a pressing need for models that enable proactive risk mitigation...”
We particularly emphasize that existing studies often overlook heterogeneous interactions and proactive coordination in mixed traffic, which highlights the gap our proposed model aims to fill.
- Limited Baseline Comparison
Reviewer Comment:
The comparison is limited to a single baseline model (CACC), which does not provide a robust benchmark. Including additional models or approaches from recent literature would enhance the credibility of the performance claims.
Response:
Thank you for this suggestion. We selected CACC (Cooperative Adaptive Cruise Control) as the baseline model because it is widely used in existing related studies on CAV behavior in mixed traffic, including Khattak et al. (2022) and others. We have now explicitly explained this selection in the revised manuscript. Given the scope and contribution of our work, we aim to focus on demonstrating the proactive advantage of our rule-based model against conventional CACC coordination. In future work, we plan to include comparisons with additional learning-based and model-predictive approaches.
- Unjustified Parameter Choices
Reviewer Comment:
Several numerical values ("magic numbers") are used in the simulations without adequate justification or reference.
Response:
Thank you for this insightful observation. We have carefully reviewed and revised the simulation setup, removed all unexplained “magic numbers,” and provided justifications and references for key simulation parameters. Details are now provided in the experimental section and marked in yellow.
- Simulation Parameters Presentation
Reviewer Comment:
The simulation setup and parameters should be compiled into a clear and concise table to improve readability and reproducibility.
Response:
Thank you. We have now re-described simulation parameters and process for clarity and reproducibility. Additionally, Figures 5 and 6 have been redrawn to enhance visual quality and better reflect the simulation outputs. These improvements aim to make the experimental section more accessible to readers.
- Language and Grammar
Reviewer Comment:
The manuscript requires thorough proofreading. There are numerous grammatical and spelling issues throughout the text that hinder clarity and professionalism.
Response:
We sincerely appreciate this feedback. The manuscript has undergone a comprehensive English language revision, including grammar, spelling, and clarity. All language-related issues have been corrected to meet the standards of professional academic writing.
We are very grateful for your thoughtful and constructive review, which has helped us significantly improve the quality of the manuscript. All major revisions are clearly highlighted, and we hope the revised version now meets the publication standards.
Reviewer 3 Report
Comments and Suggestions for AuthorsA Proactive Collision Avoidance Model for Connected and Autonomous Vehicles in Mixed Traffic Flow
This paper focuses on the pressing issue of collision risks between Connected and Autonomous Vehicles (CAVs) and Human-Driven Vehicles (HVs) in mixed traffic flow environments, proposing a proactive collision avoidance model. The manuscript is well-organized, with a clear research goal and solid theoretical foundation. The methodological design is comprehensive, offering strong potential for both theoretical contribution and practical application.
The study introduces a novel framework that integrates real-time interaction for speed control and lane-changing decisions. By incorporating dynamic safety distance calculations, cooperative lane-change protocols, and adaptive speed adjustments, the model proactively mitigates collision risks in mixed traffic scenarios. Simulation results on the SUMO platform demonstrate the model’s superiority over conventional Cooperative Adaptive Cruise Control (CACC) models in terms of average speed, time loss, and conflict frequency, validating its effectiveness and safety benefits.
Notably, the paper thoroughly details the construction of the model, including clear explanations of the SUMO simulation environment and dynamic behavior modeling for CAVs and HVs. The use of the Wiedemann99 model and dynamic programming further strengthens the model’s capability in handling the complex decision-making required in mixed traffic conditions.
From the perspective of application, this work provides practical insights for the safety optimization of CAV in the transition period of mixed traffic operation and provides valuable guidance for the design of auto drive systems and traffic management in the future. However, the manuscript contains lengthy expressions, grammar issues, and formatting problems. Suggest improving language and merging technical terminology to enhance overall presentation quality.
1.The following grammar has issues.
Line 15
In the model, the subject vehicle first collects the information of surrounding lanes and judges the traffic conditions...
In the model, the subject vehicle first collects information about surrounding lanes and judges the traffic conditions...
Line 35
...including the car following and lane changing managements of the mixed traffic.
...including the car following and lane changing management of the mixed traffic.
Line 39
(Papadoulis et al. 2019) developed a decision-making CAV control algorithm, that allows a CAV to first have longitudinal control...
(Papadoulis et al. 2019) Developed a decision-making CAV control algorithm, that allows a CAV first to have longitudinal control...
Line 41
... identify nearby CAVs and make lateral decisions in a mixed traffic ，yet their approach lacks dynamic cooperation with surrounding vehicles in mixed traffic.
... identify nearby CAVs and make lateral decisions in a mixed traffic, yet their approach lacks dynamic cooperation with surrounding vehicles in mixed traffic.
Line 43
(Khattak et al. 2022) developed a CAV-based lane management application for mixed autonomy operation of CAVs and HVs...
(Khattak et al. 2022) Developed a CAV-based lane management application for mixed autonomy operation of CAVs and HVs...
Line 307
Lateral collision avoidance is a big challenge when CAVs and HVs moves together on a multi-lane roadway...
Lateral collision avoidance is a big challenge when CAVs and HVs move together on a multi-lane roadway...
Line 317
...or change lane directly, or change lane with the cooperation of other CAVs.
...or change lane directly, or change lanes with the cooperation of other CAVs.
Line 323
...the efficiency and safety benefits provided by the collision avoidance model was evaluated in the Python-SUMO simulation experiment...
...the efficiency and safety benefits provided by the collision avoidance model were evaluated in the Python-SUMO simulation experiment...
- Table 1 spans across pages and requires the addition of a header for a continuation table.
- The formula should be centered and the numbering should be aligned to the right.
- “2.2. Collision Avoidance Modeling of Speed”Inconsistent formatting of subheadings and paragraphs.
“3.1.4. Model Parameter Values and Simulation Settings” The subtitle has inconsistent font and format.
- It is recommended to have at least 30 references, and the format of the following references needs to be changed:
References 1
Shupei Wang , Ziyang Wang , Rui Jiang , Feng Zhu, Ruidong Yan , Ying Shang.(2024) A multi-agent reinforcement learningbased longitudinal and lateral control of CAVs to improve trafffc efffciency in a mandatory lane change scenario Transportation Research Part C:158 104445
Wang S, Wang Z, Jiang R, et al. A multi-agent reinforcement learning-based longitudinal and lateral control of CAVs to improve traffic efficiency in a mandatory lane change scenario[J]. Transportation Research Part C: Emerging Technologies, 2024, 158: 104445.
References 3
Pin Lv ,Jinlei Han, Jiangtian Nie , Yang Zhang , Jia Xu ,Chao Cai and Zhe Chen (2023). Cooperative Decision-Making of Connected and Autonomous Vehicles in an Emergency. IEEE transactionson vehicular technology, Vol. 72, NO. 2.
Lv P, Han J, Nie J, et al. Cooperative decision-making of connected and autonomous vehicles in an emergency[J]. IEEE Transactions on Vehicular Technology, 2022, 72(2): 1464-1477.
References 5
Khattak, Z. H., Smith, B. L., Fontaine, M. D., Ma, J., & Khattak, A. J. (2022). Active lane management and control using connected and automated vehicles in a mixed traffic environment. Transportation Research Part C: Emerging Technologies, 139, 103648.
Khattak Z H, Smith B L, Fontaine M D, et al. Active lane management and control using connected and automated vehicles in a mixed traffic environment[J]. Transportation research part C: emerging technologies, 2022, 139: 103648.
References 7
Li, Y., Pan, B., Xing, L., Yang, M., & Dai, J. (2022). Developing dynamic speed limit strategies for mixed traffic flow to reduce collision risks at freeway bottlenecks. Accident Analysis & Prevention, 175, 106781.
Li Y, Pan B, Xing L, et al. Developing dynamic speed limit strategies for mixed traffic flow to reduce collision risks at freeway bottlenecks[J]. Accident Analysis & Prevention, 2022, 175: 106781.
References 9
Tao Wang, Minghui Ma, Shidong Liang, Jufen Yang, Yansong Wang (2025). Robust lane change decision for autonomous vehicles in mixed traffic: A safety-aware multi-agent adversarial reinforcement learning approach. Transportation Research Part C: Emerging Technologies,172, 105005
Wang T, Ma M, Liang S, et al. Robust lane change decision for autonomous vehicles in mixed traffic: A safety-aware multi-agent adversarial reinforcement learning approach[J]. Transportation Research Part C: Emerging Technologies, 2025, 172: 105005.
References 10
Papadoulis, A., Quddus, M., & Imprialou, M. (2019). Evaluating the safety impact of connected and autonomous vehicles on motorways. Accident Analysis & Prevention, 124, 12-22.
Papadoulis A, Quddus M, Imprialou M. Evaluating the safety impact of connected and autonomous vehicles on motorways[J]. Accident Analysis & Prevention, 2019, 124: 12-22.
References 11
Porfyri, K. N., Mintsis, E., & Mitsakis, E. (2018). Assessment of ACC and CACC systems using SUMO. EPiC Series in Engineering, 2, 82-93.
Porfyri K N, Mintsis E, Mitsakis E. Assessment of ACC and CACC systems using SUMO[J]. EPiC Series in Engineering, 2018, 2: 82-93.
References 12
Qin, Y., & Wang, H. (2019). Cell transmission model for mixed traffic flow with connected and autonomous vehicles. Journal of Transportation Engineering, Part A: Systems, 145(5), 04019014.
Qin Y, Wang H. Cell transmission model for mixed traffic flow with connected and autonomous vehicles[J]. Journal of Transportation Engineering, Part A: Systems, 2019, 145(5): 04019014.
References 13
Rahman, M. S., Abdel-Aty, M., Lee, J., & Rahman, M. H. (2019). Safety benefits of arterials’ crash risk under connected and automated vehicles. Transportation Research Part C: Emerging Technologies, 100, 354-371.
Rahman M S, Abdel-Aty M, Lee J, et al. Safety benefits of arterials’ crash risk under connected and automated vehicles[J]. Transportation Research Part C: Emerging Technologies, 2019, 100: 354-371.
References 14
Silgu, M. A., Erdağı, Ä°. G., Göksu, G., & Celikoglu, H. B. (2021). Combined control of freeway traffic involving cooperative adaptive cruise controlled and human driven vehicles using feedback control through SUMO. IEEE Transactions on Intelligent Transportation Systems, 23(8), 11011-11025.
Silgu M A, Erdağı Ä° G, Göksu G, et al. Combined control of freeway traffic involving cooperative adaptive cruise controlled and human driven vehicles using feedback control through SUMO[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(8): 11011-11025.
References 15
Hao Du , Supeng Leng, Jianhua He, Kai Xiong , Longyu Zhou (2024). Digital twin empowered cooperative trajectory planning of platoon vehicles for collision avoidance with unexpected obstacles. Digital Communications and Networks, 10(6),1666-1676 .
Du H, Leng S, He J, et al. Digital twin empowered cooperative trajectory planning of platoon vehicles for collision avoidance with unexpected obstacles[J]. Digital Communications and Networks, 2024, 10(6): 1666-1676.
References 16
Zhou, J., & Zhu, F. (2021). Analytical analysis of the effect of maximum platoon size of connected and automated vehicles. Transportation Research Part C: Emerging Technologies, 122, 102882.
Zhou J, Zhu F. Analytical analysis of the effect of maximum platoon size of connected and automated vehicles[J]. Transportation Research Part C: Emerging Technologies, 2021, 122: 102882.
Author Response
Response:
Thank you very much for your valuable comment. In response, we have conducted a comprehensive revision of the manuscript to address the identified issues and improve the overall presentation quality.
Specifically, we have:
- Simplified lengthy expressions to make the text more concise and improve readability, especially in the Introduction, Methodology, and Results sections.
- Performed a thorough grammar and language check to correct awkward phrasing, spelling mistakes, punctuation errors, and tense inconsistencies throughout the manuscript.
- Standardized technical terminology to maintain consistency and avoid ambiguity. For example, terms such as “CAV,” “HV,” and “collision avoidance model” are now used uniformly throughout the text.
- Resolved formatting inconsistencies, including table formatting, figure captions, section headings, and equation styles.
- Additionally, we have reformatted all references to follow the APA citation style, ensuring consistency and compliance with academic standards.
We believe that these revisions have significantly improved the linguistic quality, clarity, and presentation of the manuscript. All relevant changes have been highlighted in yellow in the revised version.
We sincerely thank the reviewer again for helping us enhance the quality and professionalism of our work.
Reviewer 4 Report
Comments and Suggestions for AuthorsOverall, this study is excellent for understanding autonomous vehicles, CAVs, and HVs when they are traveling on an expressway with several lanes. It can safely guide drivers and passengers while also reducing accidents. In your research, you propose a unique model that can proactively prevent collisions involving both CAVs and HVs. In fact, few of my past experiences and studies were based on the Python-SUMO and AVs and AGVs in industrial solutions I have designed in my lab. Only the rule-based collision avoidance model allows any CAV to control its longitudinal following speed and lateral lane-change choice when it comes to a case of choice.
The model's topic CAV first determines the type of vehicle preceding it before evaluating its acceleration rate and the lane circumstances in the vicinity of a collision. In various environmental circumstances, the subject CAV may choose to follow the lead car at the suggested pace, slow down immediately, continue looking for lane-change opportunities, change lanes directly, or change lanes with assistance from other CAVs. Definitely, this model can be a lifesaver in real cases of accidents, or collisions could possibly be avoidable on national or state's busiest highways.
Your results are very promising because you have utilized the Python-SUMO simulation experiment in your research, which clearly demonstrates the true value of TTC (time to collision). Overall, the stated collision avoidance (CACC) model has a highly significant advantage in improving traffic efficiency and safety in a mixed traffic environment. Please add a few more citations if possible, and also kindly mention the future scope of the study, as this information will be very promising and interesting for other researchers and automotive industries looking to implement the CACC model to prevent collisions on express highways.
The implementation of the CACC model not only enhances real-time decision-making in mixed traffic scenarios but also opens avenues for advanced research on vehicle-to-everything (V2X) communication and its integration with autonomous vehicle technologies. Future research could look into how well CACC systems work on express highways/multi-lane ways in both the busiest cities and state highway settings, how machine learning can help predict collisions, and how carmakers and traffic management can work together to improve traffic flow on express highways.
Author Response
Response:
We sincerely thank the reviewer for the positive evaluation and encouraging remarks regarding the novelty, simulation design, and practical relevance of our proposed model. We greatly appreciate your recognition of the rule-based proactive collision avoidance model, particularly its ability to support both longitudinal and lateral decision-making in mixed traffic scenarios. Your insights regarding its potential applicability on expressways and its real-world value are highly motivating for our continued research.
In response to your helpful suggestions:
- We have added several recent references to strengthen the literature foundation and improve the depth of discussion. All new citations and updates are clearly marked in the revised manuscript.
- As recommended, we have also included a dedicated paragraph in the Conclusion section discussing the future research directions of this work. Specifically, we have added the following:
“In future work, we plan to enhance the rule-based collision avoidance model by incorporating learning-based adaptability, such as reinforcement learning and large language models, to better handle dynamic and uncertain traffic behaviors. Furthermore, we aim to extend the model to more complex traffic scenarios, including highway merges and urban intersections, to assess its generalizability under higher traffic complexity. Additional integration with V2X communication will also be explored to further support cooperative maneuvering and collision risk prediction.”
We truly appreciate your thoughtful and constructive suggestions, which have helped us both broaden the academic relevance of the paper and better position our model for real-world applications and future advancements.
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe content of the updated article basically meets the requirements of a scientific article.
However, the summary and conclusion could be improved to highlight the novelty of the research results.
Comments on the Quality of English LanguageCheck spelling and long English sentences
Author Response
Reviewer Comment:
The summary and conclusion could be improved to highlight the novelty of the research results.
Response:
Thank you very much for your insightful comment. In response, we have carefully revised both the Introduction and Conclusion sections to better emphasize the novelty and contributions of our research. The revised Conclusion now explicitly summarizes the unique aspects of our rule-based collision avoidance model for mixed traffic environments, including its low reliance on parameter calibration, high portability, and proactive decision-making capabilities involving both CAVs and HVs.
Additionally, we have conducted a thorough proofreading of the entire manuscript, correcting grammar issues, improving word choice, and simplifying overly complex or ambiguous sentences. These improvements enhance the overall readability and presentation quality of the paper.
All revised sections, including updates to the Conclusion, have been clearly marked in red in the manuscript for your convenience.
We greatly appreciate your suggestion, which has helped us improve the clarity and impact of our work.
Reviewer 2 Report
Comments and Suggestions for AuthorsThanks for addressing my comments.
Author Response
Reviewer Comment:
Thanks for addressing my comments.
Response:
Thank you for your kind feedback and for helping us improve the manuscript.
