Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions

Akos Kovacs; Erno Horvath; Miklos Unger; Nobert Marko; Rudolf Krecht; Tamas Budai

arxiv: 2605.29518 · v1 · pith:BTPHFBVL · submitted 2026-05-28 · cs.NI · cs.AI

Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions

Rudolf Krecht , Tamas Budai , Erno Horvath , Akos Kovacs , Nobert Marko , Miklos Unger This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-06-29 01:00 UTCgrok-4.3pith:BTPHFBVL record.json open to challenge →

classification cs.NI cs.AI

keywords connected autonomous vehiclesnetwork optimizationcooperative perceptionchallengesfuture directionsmultidisciplinary methodsurbanization

0 comments

The pith

A review of network optimization for connected and autonomous vehicles aims to eliminate misconceptions and outline future directions using methods such as cooperative perception.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper reviews the network optimization aspects of connected and autonomous vehicles in light of trends like urbanization and population growth. It seeks to correct misconceptions in public opinion about the technology. The authors draw on their experience to present multidisciplinary methods including cooperative perception along with use-cases and experiment results. They share these to clarify challenges and point toward future development paths. A sympathetic reader would care because clearer information on these network issues could support safer and more efficient vehicle systems.

Core claim

The authors establish that a comprehensive review of network optimization aspects of autonomous vehicles, incorporating multidisciplinary methods such as cooperative perception, can eliminate misconceptions and outline the future of the field, informed by their insights, knowledge, use-cases, and experiment results.

What carries the argument

Cooperative perception as a multidisciplinary method that enables shared sensing to support network optimization in connected and autonomous vehicles.

If this is right

Global trends such as urbanization will increase the importance of optimized networks for vehicle connectivity.
Public misconceptions about autonomous vehicles can be reduced through reviews that include concrete use-cases and results.
Future vehicle systems will depend on integrating methods like cooperative perception beyond single-vehicle approaches.
Experiment results from current CAV work will directly inform practical network optimization strategies.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The review could support better planning for communication infrastructure in growing cities.
Cooperative perception might lower the sensor and bandwidth requirements for individual vehicles.
A direct test would involve measuring network performance in mixed fleets with and without the described perception sharing.

Load-bearing premise

The authors' extensive experience with CAVs supplies unique insights, knowledge, use-cases, and experiment results that meaningfully advance the review beyond existing literature.

What would settle it

A real-world deployment or simulation where cooperative perception shows no measurable improvement in network latency or reliability for autonomous vehicles would challenge the value of the methods presented.

read the original abstract

Global megatrends, such as urbanization, population growth, and emerging network solutions are accelerating the development of the Connected and Autonomous Vehicles (CAVs) industry. There are many truths, some misconceptions, and even some excitement about CAVs in the public's opinion. The main objective of the current article is to provide a comprehensive review, eliminate misconceptions, and outline the future of the network optimization aspects of autonomous vehicles by presenting various multidisciplinary methods, such as cooperative perception. Given our extensive experience with CAVs, we are aiming to share some of the insights and knowledge we have gained, along with relevant use-cases and experiment results.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a review paper on network optimization for connected autonomous vehicles that organizes existing challenges and methods but adds unclear new value beyond standard surveys.

read the letter

This paper is a review that pulls together network optimization issues for connected and autonomous vehicles. It frames the topic around urbanization and new network tech, then points to multidisciplinary angles like cooperative perception to handle things like perception and coordination.

It does a reasonable job listing the main challenges and tying them to real-world trends. The authors mention their own experience with use-cases and experiment results, which could give it some practical grounding if those sections are detailed and properly cited.

The soft spot is the lack of visible depth in the abstract. Reviews stand or fall on whether they actually synthesize the literature or just catalog it, and the claim to eliminate misconceptions requires showing specific errors in prior work with evidence. Without the full text it's impossible to check if the coverage is balanced or if the authors' insights go beyond what other surveys already cover.

This is for readers who want an entry point into the networking side of autonomous vehicles, especially those crossing from telecom or AI. Experts already working in the area will probably find it thin unless the full version has strong synthesis.

It deserves peer review because the topic matters and a well-executed survey could help coordinate work across fields, even if the final version needs tightening on citations and balance.

Referee Report

1 major / 1 minor

Summary. The manuscript is a review paper on the network optimization aspects of Connected and Autonomous Vehicles (CAVs). It seeks to provide a comprehensive review of the field, eliminate misconceptions about CAVs, outline future directions, present multidisciplinary methods such as cooperative perception, and share insights, use-cases, and experiment results based on the authors' extensive experience with CAVs, in the context of global megatrends like urbanization and population growth.

Significance. If the review successfully synthesizes the literature, clarifies misconceptions with evidence, and provides novel insights from practical experience, it could serve as a valuable reference for researchers and practitioners in computer networks and intelligent transportation systems. The focus on network optimization is timely given the increasing integration of CAVs with emerging network solutions.

major comments (1)

Abstract: The central objective to 'eliminate misconceptions' requires explicit identification of targeted misconceptions and demonstration (via cited evidence or experiment results) of how they are resolved; without this structure in the main text, the review's claimed contribution to correcting public opinion remains unsubstantiated.

minor comments (1)

Abstract: The reference to 'experiment results' would benefit from a one-sentence indication of their scope (e.g., simulation vs. real-world testbed) to better align reader expectations with the promised use-cases.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and the recommendation of minor revision. We address the single major comment below.

read point-by-point responses

Referee: Abstract: The central objective to 'eliminate misconceptions' requires explicit identification of targeted misconceptions and demonstration (via cited evidence or experiment results) of how they are resolved; without this structure in the main text, the review's claimed contribution to correcting public opinion remains unsubstantiated.

Authors: We agree that the abstract states the objective of eliminating misconceptions but that this claim would be strengthened by explicit identification and structured resolution. In the revised manuscript we will insert a new subsection (likely in the Introduction) that enumerates the principal misconceptions concerning network optimization for CAVs, maps each to the relevant literature synthesis or experimental results presented later in the paper, and briefly indicates how the review clarifies or corrects it. This addition will make the contribution traceable without altering the overall scope or length substantially. revision: yes

Circularity Check

0 steps flagged

No significant circularity in this review paper

full rationale

This is a survey paper whose stated objective is to review network optimization aspects of CAVs, eliminate misconceptions, and share insights/use-cases from the authors' experience. The abstract and described content contain no derivations, equations, predictions, fitted parameters, or self-referential definitions. All claims rest on cited prior work rather than internal construction. No load-bearing steps match any of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a review that rests on synthesis of prior literature in network optimization and autonomous vehicles; no new free parameters, axioms, or invented entities are introduced in the abstract.

pith-pipeline@v0.9.1-grok · 5643 in / 1026 out tokens · 45940 ms · 2026-06-29T01:00:28.562727+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

15 extracted references · 2 canonical work pages · 1 internal anchor

[1]

Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges,

Y. Han, H. Zhang, H. Li, Y. Jin, C. Lang and Y. Li, “Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges,” arXiv, 2023

2023
[2]

3D Object Detection for Autonomous Driving: A Survey,

R. Qian, X. Lai and X. Li, “3D Object Detection for Autonomous Driving: A Survey,” Pattern Recognition, vol. 130
[3]

Developing and Testing Robust Autonomy: The University of Sydney Campus Data Set,

W. Zhou, J. S. Berrio, C. De Alvis, M. Shan, S. Worrall, J. Ward and E. Nebot, “Developing and Testing Robust Autonomy: The University of Sydney Campus Data Set,” IEEE Intelligent Transportation Systems Magazine, vol. 12, no. 4, pp. 23 - 40, 2020. 9 IEEE Network, vol. 37, no. 4, July/August 2023

2020
[4]

Fast and Robust Registration of Partially Overlapping Point Clouds,

E. Arnold, S. Mozaffari and M. Dianati, “Fast and Robust Registration of Partially Overlapping Point Clouds,” IEEE Robotics and Automation Letters, vol. 7, pp. 1502-1509, 2021

2021
[5]

3D Semantic Scene Completion: A Survey,

L. Roldão, R. de Charette and A. Verroust -Blondet, “3D Semantic Scene Completion: A Survey,” International Journal of Computer Vision, vol. 130, no. 8, pp. 1978-2005, 2022

1978
[6]

F -Cooper: Feature Based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds,

Q. Chen, X. Ma, S. Tang, J. Guo, Q. Yang and S. Fu, "F -Cooper: Feature Based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds," in Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, New York, NY, USA, Association for Computing Machinery, 2019, pp. 88-100

2019
[7]

Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs,

D. Kim and J. Kim, “Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs,” in 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, Republic of, 2022

2022
[8]

ROS on DDS,

W. Woodall, “ROS on DDS,” 2022. [Online]. Available: https://design.ros2.org/articles/ros_on_dds.html. [Accessed 12 December 2022]

2022
[9]

Autonomous driving under V2X environment: state-of-the-art survey and challenges,

X. Yang, Y. Shi, J. Xing and Z. Liu, “Autonomous driving under V2X environment: state-of-the-art survey and challenges,” Intelligent Transportation Infrastructure, 2022

2022
[10]

DSRC & C -V2X Comparison for Connected and Automated Vehicles in Different Traffic Scenarios,

Y. Jin, X. Liu and Q. Zhu, “DSRC & C -V2X Comparison for Connected and Automated Vehicles in Different Traffic Scenarios,” ArXiv, vol. abs/2203.12553, 2022

work page arXiv 2022
[11]

Interworking of DSRC and Cellular Network Technologies for V2X Communications: A Survey,

K. Abboud, H. A. Omar and W. Zhuang, “Interworking of DSRC and Cellular Network Technologies for V2X Communications: A Survey,” IEEE Transactions on Vehicular Technology, vol. 65, no. 12, pp. 9457 -9470, 2016

2016
[12]

A 5G Synchronous Optical Networking Management System,

Y.-H. Lin, T.-C. Chuang and Y. Huang, “A 5G Synchronous Optical Networking Management System,” 2022 23rd Asia - Pacific Network Operations and Management Symposium (APNOMS), pp. 1 -4, 2022

2022
[13]

LSTM -based QoS prediction for 5G -enabled Connected and Automated Mobility applications,

S. Barmpounakis, L. Magoula, N. Koursioumpas, R. Khalili, J. M. Perdomo and R. P. Manjunath, “LSTM -based QoS prediction for 5G -enabled Connected and Automated Mobility applications,” in 2021 IEEE 4th 5G World Forum (5GWF), 2021

2021
[14]

Raven: Improving Interactive Latency for the Connected Car,

L. HyunJong, J. Flinn and B. Tonshal, “Raven: Improving Interactive Latency for the Connected Car,” in Association for Computing Machinery, New Delhi, India, 2018

2018
[15]

Survey on Vehicular Ad Hoc Networks and Its Access Technologies Security Vulnerabilities and Countermeasures

K. B. Kelarestaghi, M. Foruhandeh, K. Heaslip and R. M. Gerdes, “Survey on Vehicular Ad Hoc Networks and Its Access Technologies Security Vulnerabilities and Countermeasures,” ArXiv, vol. abs/1903.01541, 2019

work page internal anchor Pith review Pith/arXiv arXiv 1903

[1] [1]

Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges,

Y. Han, H. Zhang, H. Li, Y. Jin, C. Lang and Y. Li, “Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges,” arXiv, 2023

2023

[2] [2]

3D Object Detection for Autonomous Driving: A Survey,

R. Qian, X. Lai and X. Li, “3D Object Detection for Autonomous Driving: A Survey,” Pattern Recognition, vol. 130

[3] [3]

Developing and Testing Robust Autonomy: The University of Sydney Campus Data Set,

W. Zhou, J. S. Berrio, C. De Alvis, M. Shan, S. Worrall, J. Ward and E. Nebot, “Developing and Testing Robust Autonomy: The University of Sydney Campus Data Set,” IEEE Intelligent Transportation Systems Magazine, vol. 12, no. 4, pp. 23 - 40, 2020. 9 IEEE Network, vol. 37, no. 4, July/August 2023

2020

[4] [4]

Fast and Robust Registration of Partially Overlapping Point Clouds,

E. Arnold, S. Mozaffari and M. Dianati, “Fast and Robust Registration of Partially Overlapping Point Clouds,” IEEE Robotics and Automation Letters, vol. 7, pp. 1502-1509, 2021

2021

[5] [5]

3D Semantic Scene Completion: A Survey,

L. Roldão, R. de Charette and A. Verroust -Blondet, “3D Semantic Scene Completion: A Survey,” International Journal of Computer Vision, vol. 130, no. 8, pp. 1978-2005, 2022

1978

[6] [6]

F -Cooper: Feature Based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds,

Q. Chen, X. Ma, S. Tang, J. Guo, Q. Yang and S. Fu, "F -Cooper: Feature Based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds," in Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, New York, NY, USA, Association for Computing Machinery, 2019, pp. 88-100

2019

[7] [7]

Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs,

D. Kim and J. Kim, “Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs,” in 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, Republic of, 2022

2022

[8] [8]

ROS on DDS,

W. Woodall, “ROS on DDS,” 2022. [Online]. Available: https://design.ros2.org/articles/ros_on_dds.html. [Accessed 12 December 2022]

2022

[9] [9]

Autonomous driving under V2X environment: state-of-the-art survey and challenges,

X. Yang, Y. Shi, J. Xing and Z. Liu, “Autonomous driving under V2X environment: state-of-the-art survey and challenges,” Intelligent Transportation Infrastructure, 2022

2022

[10] [10]

DSRC & C -V2X Comparison for Connected and Automated Vehicles in Different Traffic Scenarios,

Y. Jin, X. Liu and Q. Zhu, “DSRC & C -V2X Comparison for Connected and Automated Vehicles in Different Traffic Scenarios,” ArXiv, vol. abs/2203.12553, 2022

work page arXiv 2022

[11] [11]

Interworking of DSRC and Cellular Network Technologies for V2X Communications: A Survey,

K. Abboud, H. A. Omar and W. Zhuang, “Interworking of DSRC and Cellular Network Technologies for V2X Communications: A Survey,” IEEE Transactions on Vehicular Technology, vol. 65, no. 12, pp. 9457 -9470, 2016

2016

[12] [12]

A 5G Synchronous Optical Networking Management System,

Y.-H. Lin, T.-C. Chuang and Y. Huang, “A 5G Synchronous Optical Networking Management System,” 2022 23rd Asia - Pacific Network Operations and Management Symposium (APNOMS), pp. 1 -4, 2022

2022

[13] [13]

LSTM -based QoS prediction for 5G -enabled Connected and Automated Mobility applications,

S. Barmpounakis, L. Magoula, N. Koursioumpas, R. Khalili, J. M. Perdomo and R. P. Manjunath, “LSTM -based QoS prediction for 5G -enabled Connected and Automated Mobility applications,” in 2021 IEEE 4th 5G World Forum (5GWF), 2021

2021

[14] [14]

Raven: Improving Interactive Latency for the Connected Car,

L. HyunJong, J. Flinn and B. Tonshal, “Raven: Improving Interactive Latency for the Connected Car,” in Association for Computing Machinery, New Delhi, India, 2018

2018

[15] [15]

Survey on Vehicular Ad Hoc Networks and Its Access Technologies Security Vulnerabilities and Countermeasures

K. B. Kelarestaghi, M. Foruhandeh, K. Heaslip and R. M. Gerdes, “Survey on Vehicular Ad Hoc Networks and Its Access Technologies Security Vulnerabilities and Countermeasures,” ArXiv, vol. abs/1903.01541, 2019

work page internal anchor Pith review Pith/arXiv arXiv 1903