Intelligent Connected Vehicles Research Articles

Deep Reinforcement Learning-based Mining Task Offloading Scheme for Intelligent Connected Vehicles in UAV-aided MEC

The convergence of unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks and blockchain transforms the existing mobile networking paradigm. However, in the temporary hotspot scenario for intelligent connected vehicles (ICVs) in UAV-aided MEC networks, deploying blockchain-based services and applications in vehicles is generally impossible due to its high computational resource and storage requirements. One possible solution is to offload part of all the computational tasks to MEC servers wherever possible. Unfortunately, due to the limited availability and high mobility of the vehicles, there is still lacking simple solutions that can support low-latency and higher reliability networking services for ICVs. In this article, we study the task offloading problem of minimizing the total system latency and the optimal task offloading scheme, subject to constraints on the hover position coordinates of the UAV, the fixed bonuses, flexible transaction fees, transaction rates, mining difficulty, costs and battery energy consumption of the UAV. The problem is confirmed to be a challenging linear integer planning problem, we formulate the problem as a constrained Markov decision process. Deep Reinforcement Learning (DRL) has excellently solved sequential decision-making problems in dynamic ICVs environment, therefore, we propose a novel distributed DRL-based P-D3QN approach by using Prioritized Experience Replay strategy and the dueling double deep Q-network (D3QN) algorithm to solve the optimal task offloading policy effectively. Finally, experiment results show that compared with the benchmark scheme, the P-D3QN algorithm can bring about 26.24% latency improvement and increase about 42.26% offloading utility.

VFL-Chain: Bulletproofing Federated Learning in the V2X environments

Federated Learning (FL) has gained significant traction as a promising approach to enable collaborative machine learning (ML) while safeguarding data privacy across diverse applications, with the Vehicle-to-Everything (V2X) environment being a notable use case. However, conventional FL systems remain susceptible to model poisoning attacks, wherein malicious participants can introduce inaccurate or deliberately misleading local model updates to the central aggregator. In the context of V2X, such attacks could spawn catastrophic outcomes and jeopardize safety-critical applications. To tackle this pressing concern, we introduce a privacy-preserving and verifiable FL framework, dubbed VFL-Chain, designed to facilitate secure and efficient collaboration among intelligent connected vehicles (ICVs). VFL-Chain aspires to deliver a privacy-centric, verifiable FL experience complemented by a robust incentive mechanism tailored for ICVs. Our proposed solution leverages Bulletproofs to enable efficient verification of model update integrity, which are assimilated within smart contracts on an underlying permissioned blockchain. Furthermore, VFL-Chain presents a fair incentive mechanism that rewards honest participation, fostering a resilient and efficient FL implementation. We conduct an exhaustive security analysis and performance assessment of our proposed system, which underscores its efficacy in countering data poisoning attacks and augmenting the accuracy of FL.

Cost Analysis of Vehicle-Road Cooperative Intelligence Solutions for High-Level Autonomous Driving: A Beijing Case Study

The development of the vehicle-road cooperative intelligence can effectively resolve the current technical impediment and cost quandary associated with high-level autonomous driving. Nevertheless, the intelligent infrastructure entails initial deployment costs and ongoing energy consumption and maintenance costs, necessitating a comprehensive and quantitative analysis of the costs of intelligent infrastructure and the corresponding changes in comprehensive costs. The cost evaluation model for the cooperative intelligent system is designed in this paper, considering the corresponding intelligent infrastructure layout scheme for different road types within the technical framework. The intelligent configuration and corresponding cost transfer from roadside to vehicle side under the synergy effect is also analyzed. Using Beijing as a case study, the results indicate that the deployment of intelligent infrastructure will effectively reduce acquisition and usage costs of high-level intelligent vehicles and achieve a greater “reuse” effect by serving more intelligent connected vehicles (ICVs). Compared to the vehicle intelligence, collaborative intelligence will reduce cumulative total costs by more than ¥200 billion from 2023 to 2050, even with the inclusion of intelligent infrastructure’s costs.

Perception Methods for Adverse Weather Based on Vehicle Infrastructure Cooperation System: A Review.

Environment perception plays a crucial role in autonomous driving technology. However, various factors such as adverse weather conditions and limitations in sensing equipment contribute to low perception accuracy and a restricted field of view. As a result, intelligent connected vehicles (ICVs) are currently only capable of achieving autonomous driving in specific scenarios. This paper conducts an analysis of the current studies on image or point cloud processing and cooperative perception, and summarizes three key aspects: data pre-processing methods, multi-sensor data fusion methods, and vehicle-infrastructure cooperative perception methods. Data pre-processing methods summarize the processing of point cloud data and image data in snow, rain and fog. Multi-sensor data fusion methods analyze the studies on image fusion, point cloud fusion and image-point cloud fusion. Because communication channel resources are limited, the vehicle-infrastructure cooperative perception methods discuss the fusion and sharing strategies for cooperative perception information to expand the range of perception for ICVs and achieve an optimal distribution of perception information. Finally, according to the analysis of the existing studies, the paper proposes future research directions for cooperative perception in adverse weather conditions.

Modeling and analysis of mixed traffic flow capacity and stability considering human-driven vehicle drivers' trust attitude towards intelligent connected vehicles

During the proliferation process of Intelligent Connected Vehicles (ICVs), mixed traffic consisting of Human-Driven Vehicles (HDVs) and ICVs is inevitable. Notably, varying trust attitudes of HDV drivers towards ICVs lead to diverse driving behaviors when they interact with ICVs. The impact of these differential driving behaviors on the operational characteristics of the mixed traffic flow is currently unclear. This study focuses on examining the capacity and stability of ICV mixed traffic flow in a single-lane, no-overtaking scenario. We investigate the car-following behaviors of HDV drivers with different trust attitudes towards ICVs. From this, we discern the expected distribution probabilities of vehicles exhibiting varying behaviors in the mixed flow. Utilizing these findings, a theoretical model has been developed to analyze the fundamental diagram and stability of mixed traffic flow, considering the trust attitudes of HDV drivers toward ICVs. Through numerical analysis and simulation experiments, the impact of HDV drivers' trust attitudes in ICVs on the capacity and stability of mixed traffic flow was examined. The results show that ICV integration can bolster traffic flow capacity. Further, heightened trust attitude in ICVs among HDV drivers magnifies the positive effect of ICVs on traffic operational efficiency. However, if the ICV penetration rate remains below 70% and the trust level of HDV drivers towards ICVs does not reach a critical threshold, the integration of ICVs could potentially reduce traffic stability. Conversely, once the ICV penetration rate surpasses 70%, a simultaneous increase in ICV penetration rate and the trusting attitude of HDV drivers towards ICVs significantly improves the stability of mixed traffic flow.

Fine-Grained Radio Frequency Fingerprint Recognition Network Based on Attention Mechanism.

With the rapid development of the internet of things (IoT), hundreds of millions of IoT devices, such as smart home appliances, intelligent-connected vehicles, and wearable devices, have been connected to the network. The open nature of IoT makes it vulnerable to cybersecurity threats. Traditional cryptography-based encryption methods are not suitable for IoT due to their complexity and high communication overhead requirements. By contrast, RF-fingerprint-based recognition is promising because it is rooted in the inherent non-reproducible hardware defects of the transmitter. However, it still faces the challenges of low inter-class variation and large intra-class variation among RF fingerprints. Inspired by fine-grained recognition in computer vision, we propose a fine-grained RF fingerprint recognition network (FGRFNet) in this article. The network consists of a top-down feature pathway hierarchy to generate pyramidal features, attention modules to locate discriminative regions, and a fusion module to adaptively integrate features from different scales. Experiments demonstrate that the proposed FGRFNet achieves recognition accuracies of 89.8% on 100 ADS-B devices, 99.5% on 54 Zigbee devices, and 83.0% on 25 LoRa devices.

ICVTest: A Practical Black-Box Penetration Testing Framework for Evaluating Cybersecurity of Intelligent Connected Vehicles

Intelligent connected vehicles (ICVs) are equipped with extensive electronic control units which offer convenience but also pose significant cybersecurity risks. Penetration testing, recommended in ISO/SAE 21434 “Road vehicles—Cybersecurity engineering”, is an effective approach to identify cybersecurity vulnerabilities in ICVs. However, there is limited research on vehicle penetration testing from a black-box perspective due to the complex architecture of ICVs. Additionally, no penetration testing framework has been proposed to guide security testers on conducting penetration testing for the whole vehicle. The lack of framework guidance results in the inexperienced security testers being uncertain about the processes to follow for conducting penetration testing. Moreover, the inexperienced security testers are unsure about which tests to perform in order to systematically evaluate the vehicle’s cybersecurity. To enhance the penetration testing efficiency of ICVs, this paper presents a black-box penetration testing framework, ICVTest. ICVTest proposes a standardized penetration testing process to facilitate step-by-step completion of the penetration testing, thereby addressing the issue of inexperienced testers lacking guidance on how to initiate work when confronted with ICV. Also, ICVTest includes 10 sets of test cases covering hardware and software security tests. Testers can select appropriate test cases based on the specific cybersecurity threats faced by the target object, thereby reducing the complexity of penetration testing tasks. Furthermore, we have developed a vehicle cybersecurity testing platform for ICVTest that seamlessly integrates various testing tools. The platform enables even novice testers to conduct vehicle black-box penetration testing in accordance with the given guidance which addresses the current industry’s challenge of an overwhelming number of testing tasks coupled with a shortage of skilled professionals. For the first time, we propose a comprehensive black-box penetration testing framework and implement the framework in the form of a cybersecurity testing platform. We apply ICVTest to evaluate an electric vehicle manufactured in 2021 for assessing the framework’s availability. With the aid of ICVTest, even testers with limited experience in automotive penetration can effectively evaluate the security risks of ICVs. In our experiments, numerous cybersecurity vulnerabilities were identified involving in-vehicle sensors, remote vehicle control systems, and in-vehicle controller area network (CAN) bus.

Data-Mechanism Adaptive Switched Predictive Control for Heterogeneous Platoons With Wireless Communication Interruption

Benefiting from the advancement of intelligent transportation systems (ITSs), intelligent connected vehicles (ICVs) are ushering in a once-in-a-generation development opportunity. Considering the widespread presence of heterogeneous vehicles with disturbances and uncertain dynamics in actual platoon scenarios as well as the multimodel switching produced by unavoidable interruptions in the communication process, this paper proposes a data–mechanism adaptive switched predictive (DASP) control strategy. The characteristics of the mechanism model are mapped based on state data to more accurately describe the system’s dynamic characteristics and improve the interpretability of variables. The introduction of Givens rotations and switching criteria enables online adaptive switching of the controller. A robustness analysis of heterogeneous platoon switching control under bounded disturbance is presented, and sufficient conditions for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal{L}_{2}$</tex-math> </inline-formula> string stability are provided. Finally, CarSim simulations and real-time bench experiments are reported to demonstrate the effectiveness of the DASP algorithm for heterogeneous multivehicle regulation with communication interruptions.

Knowledge Mapping with CiteSpace, VOSviewer, and SciMAT on Intelligent Connected Vehicles: Road Safety Issue

The rapid development of the Intelligent connected vehicle (ICV) industry has stimulated technological innovation in energy and communication while also highlighting the need for effective policies and road safety measures. Understanding and addressing road safety issues in the context of ICVs can contribute to ICV development and safe driving. This paper employs a knowledge mapping approach to scientifically and intuitively demonstrate research on the road safety issues of ICV over the last decade. By utilizing bibliometric tools such as CiteSpace, VOSviewer, and SciMAT, a total of 3661 original articles from the Web of Science are examined to explore three aspects. Firstly, the study investigates the collaborative relationships among authors and institutions within the industry. Secondly, it summarizes major research topics by analyzing and clustering keywords. Lastly, the paper identifies research hotspots and predicts future research directions. The findings reveal a dynamic field characterized by close collaboration among diverse institutions, with China and the United States emerging as the most active countries and mathematics and computer science journals becoming mainstream. According to three bibliometric tools, the research topics primarily revolve around three areas: Vehicular ad hoc Networks (VANET), intelligent transportation systems (ITS), and network security. Machine learning and V2X communication are predicted to be essential research topics in the next stage. Research on traffic accidents still has potential as the number of ICVs increases.

Characteristic Analysis and Decision Model of Lane-Changing Game for Intelligent Connected Vehicles

To study the lane-change interaction characteristics of intelligent connected vehicles (ICVs) and reduce the risk of vehicle lane-changing decisions, a decision model based on the lane-changing game characteristics of the ICV is proposed in this paper. In the modeling process, the characteristics of vehicle lane-changing interaction behavior are analyzed based on evolutionary game theory and the vehicle game lane-changing payoff functions are quantified. The stability of the game equilibrium points is analyzed by using a dynamic evolution equation, and sensitivity analysis of the main factors affecting vehicle lane changes and the time to the collision of vehicles is conducted. The SUMO software is used to simulate and verify the vehicle game decision model, and the results show that the game decision system converges to different optimal strategy combinations under different traffic conditions, and this model can effectively reduce the decision-making conflict and the collision risk of vehicles.

Intrusion Detection in Intelligent Connected Vehicles Based on Weighted Self-Information

The Internet of Vehicles (IoV) empowers intelligent and tailored services for intelligent connected vehicles (ICVs). However, with the increasing number of onboard external communication interfaces, ICVs face the challenges of malicious network intrusions. The closure of traditional vehicles had led to in-vehicle communication protocols, including the most commonly applied controller area network (CAN), and a lack of security and privacy protection mechanisms. Therefore, to protect the connected vehicles and IoV systems from being attacked, an intrusion-detection method is proposed based on the features extracted from the arbitration identifier (ID) field of CAN messages. Specifically, a sliding window is used to continuously extract a frame of streaming CAN messages first. Afterward, the weighted self-information of the CAN message ID is defined, and both the weighted self-information and the normalized value of an ID are extracted as features. Based on the extracted features, a lightweight one-class classifier, the local outlier factor (LOF), is used to identify the outliers and detect malicious network intrusion attacks. Simulation experiments were conducted based on the public CAN dataset provided by the HCR Lab. The proposed method, using four different one-class classifiers, was analyzed, and it is also benchmarked with three information entropy-based intrusion-detection methods in the literature. The experimental results indicate that, compared to the benchmarks, the proposed method dramatically improves the detection accuracy for injection attacks, namely denial-of-service (DoS) and spoofing, especially when the number of injected messages is low.

Side Channel Analysis: A Novel Intrusion Detection System Based on Vehicle Voltage Signals

Intelligent connected vehicles (ICVs) integrate advanced equipment and communication network technologies to realize information exchange and sharing between vehicles and people, roads, clouds, etc., bringing great convenience to people's lives. However, the interconnection of intelligent equipment and vehicles also brings many vulnerable interfaces, threatening the security of in-vehicle networks, e.g., controller area network (CAN) bus. For protecting the security of CAN bus, some researchers propose a data encryption and decryption protocol-based method. Note that due to the resource constraints of computing and bandwidth and the requirements for low-delay data transmission, the research on protocol-based data encryption and decryption method is progressing slowly. For this reason, more researchers study vehicle intrusion detection systems (IDSs) based on side channel analysis. It does not occupy the bandwidth of CAN bus, and detects intrusion by analyzing the physical characteristics of CAN bus. Nevertheless, most of the existing work either cannot locate the source electronic control unit (ECU) of the malicious data frames, or cannot detect malicious data frames from ECUs and external nodes simultaneously, which greatly limits their practical application value. Therefore, we propose a novel IDS based on vehicle voltage signals. Specifically, we map multiple identifiers (IDs) sent for each ECU without developer documentation. In addition, we creatively design FeatureBagging-CNN combined model to detect malicious intrusion. When the external nodes or compromised ECUs send malicious data frames, the system can accurately detect them and locate their sender.

A Regenerative Braking Control Strategy for ICVs Considering the Coupling Effect of Driving Conditions and Driving Styles

Regenerative braking is an important part of automotive energy-saving technology. Under different driving conditions and driving styles, the rules of the driver stepping on the accelerator pedal are different, which makes the regenerative braking intensity vary greatly. Different intensity of energy recovery is carried out under different driving conditions and driving styles, which is conducive to improving the efficiency of energy recovery. Therefore, we propose a regenerative braking control strategy (RBCS) based on an accelerator pedal for intelligent connected vehicles (ICVs) considering the coupling effect of driving conditions and driving styles. Firstly, a modified method of driving style characteristic parameters considering the influence of driving conditions is proposed. Secondly, α、β and γ are defined as accelerator pedal travel, driving condition and driving style correction coefficient respectively. The regenerative braking control strategy based on an accelerator pedal is established, which corrects the regenerative braking intensity according to correction coefficients. Thirdly, the driving data are obtained through the driver-in-the-loop experiment. On this basis, the characteristic parameters of driving style are modified, and the values of α、β and γ are determined. Finally, the vehicle simulation model and hardware-in-the-loop experiment platform are established to verify the RBCS. The results show that the economy of the vehicle is further improved.

BV-ICVs: A privacy-preserving and verifiable federated learning framework for V2X environments using blockchain and zkSNARKs

As part of vehicle to everything (V2X) environments, intelligent connected vehicles (ICVs) generate a large amount of data, which can be exploited securely and effectively through decentralized techniques such as federated learning (FL). Existing FL systems, however, are vulnerable to attacks and barely meet the security requirements for real-world applications. If malicious or compromised ICVs upload inaccurate or low-quality local model updates to the central aggregator, they may reduce the accuracy of the global model, thereby reducing drivers safety and efficiency. This paper aims to alleviate these concerns by presenting BV-ICVs, a blockchain-enabled and privacy-preserving FL framework for ICVs in an edge-envisioned V2X environment. This system uses Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (zkSNARKs) verification that is compiled as smart contracts to prevent malicious, compromised or even rational ICVs from uploading unreliable, erroneous or low-quality model updates. The verification process is embedded within the consensus of the underlying permissioned blockchain, which maximizes both the efficiency of the process and the utilization of computer resources. As demonstrated by discussions, security analysis, and numerical results, BV-ICVs reduced data poisoning attacks and increased the privacy protection and accuracy of FL.

Intelligent, In-Vehicle Autonomous Decision-Making Functionality for Driving Style Reconfigurations

Intelligent connected vehicles (ICVs) constitute a transformative technology attracting immense research effort and holding great promise in providing road safety, transport efficiency, driving comfort, and eco-friendly mobility. As the driving environment becomes more and more “connected”, the manner in which an ICV is driven (driving style) can dynamically vary from time to time, due to the change in several parameters associated with personal traits and with the ICV’s surroundings. This necessitates fast and effective decisions to be made for a priori identifying the most appropriate driving style for an ICV. Accordingly, the main goal of this study is to present a novel, in-vehicle autonomous decision-making functionality, which enables ICVs to dynamically, transparently, and securely utilize the best available driving style (DS). The proposed functionality takes as input several parameters related to the driver’s personal characteristics and preferences, as well as the changing driving environment. A Naive Bayes learning classifier is applied for the cognitive nature of the presented functionality. Three scenarios, with regards to drivers with different personal preferences and to driving scenes with changing environment situations, are illustrated, showcasing the effectiveness of the proposed functionality.

Real-Time Trajectory Prediction Method for Intelligent Connected Vehicles in Urban Intersection Scenarios

Intelligent connected vehicles (ICVs) have played an important role in improving the intelligence degree of transportation systems, and improving the trajectory prediction capability of ICVs is beneficial for traffic efficiency and safety. In this paper, a real-time trajectory prediction method based on vehicle-to-everything (V2X) communication is proposed for ICVs to improve the accuracy of their trajectory prediction. Firstly, this paper applies a Gaussian mixture probability hypothesis density (GM-PHD) model to construct the multidimension dataset of ICV states. Secondly, this paper adopts vehicular microscopic data with more dimensions, which is output by GM-PHD as the input of LSTM to ensure the consistency of the prediction results. Then, the signal light factor and Q-Learning algorithm were applied to improve the LSTM model, adding features in the spatial dimension to complement the temporal features used in the LSTM. When compared with the previous models, more consideration was given to the dynamic spatial environment. Finally, an intersection at Fushi Road in Shijingshan District, Beijing, was selected as the field test scenario. The final experimental results show that the GM-PHD model achieved an average error of 0.1181 m, which is a 44.05% reduction compared to the LiDAR-based model. Meanwhile, the error of the proposed model can reach 0.501 m. When compared to the social LSTM model, the prediction error was reduced by 29.43% under the average displacement error (ADE) metric. The proposed method can provide data support and an effective theoretical basis for decision systems to improve traffic safety.

A Federated Learning-Based Edge Caching Approach for Mobile Edge Computing-Enabled Intelligent Connected Vehicles

Massive map data transmission and the strict demand for the privacy of high-precision maps have brought significant challenges to the cache of high-precision maps in intelligent connected vehicles (ICV). Federal learning (FL) was introduced to reduce the pressure on the edge network and protect privacy. But the high dynamics of cars and limited resources lead to low accuracy and high training delay. We propose a joint optimization scheme of participant selection and resource allocation for federated learning. In each time slice, vehicles are determined whether to participate in training, which minimizes long-term training delay with limited energy consumption. To meet the delay and privacy requirements of high-precision map caching, we present an edge cooperative caching scheme based on federated deep reinforcement learning (F-DRL), which aims to achieve dynamic adaptive edge caching while protecting user privacy. The collaborative caching model is formulated as a Markov decision process (MDP). Dueling Deep Q Network (Dueling-DQN) is used to solve the optimal strategy, and federal learning is used for training. Enough comparative experiments to evaluate the performance of the proposed schemes. The aspects of reliability, cache hit rate, and training accuracy prove that the method effectively improves the training parameters of federated learning while meeting a high-precision map cache’s delay and reliability requirements.

Joint offloading decision and resource allocation in vehicular edge computing networks

With the rapid development of Intelligent Transportation Systems (ITS), many new applications for Intelligent Connected Vehicles (ICVs) have sprung up. In order to tackle the conflict between delay-sensitive applications and resource-constrained vehicles, computation offloading paradigm that transfers computation tasks from ICVs to edge computing nodes has received extensive attention. However, the dynamic network conditions caused by the mobility of vehicles and the unbalanced computing load of edge nodes make ITS face challenges. In this paper, we propose a heterogeneous Vehicular Edge Computing (VEC) architecture with Task Vehicles (TaVs), Service Vehicles (SeVs) and Roadside Units (RSUs), and propose a distributed algorithm, namely PG-MRL, which jointly optimizes offloading decision and resource allocation. In the first stage, the offloading decisions of TaVs are obtained through a potential game. In the second stage, a multi-agent Deep Deterministic Policy Gradient (DDPG), one of deep reinforcement learning algorithms, with centralized training and distributed execution is proposed to optimize the real-time transmission power and subchannel selection. The simulation results show that the proposed PG-MRL algorithm has significant improvements over baseline algorithms in terms of system delay.

Explainable Artificial Intelligence (XAI) for Intrusion Detection and Mitigation in Intelligent Connected Vehicles: A Review

The potential for an intelligent transportation system (ITS) has been made possible by the growth of the Internet of things (IoT) and artificial intelligence (AI), resulting in the integration of IoT and ITS—known as the Internet of vehicles (IoV). To achieve the goal of automatic driving and efficient mobility, IoV is now combined with modern communication technologies (such as 5G) to achieve intelligent connected vehicles (ICVs). However, IoV is challenged with security risks in the following five (5) domains: ICV security, intelligent device security, service platform security, V2X communication security, and data security. Numerous AI models have been developed to mitigate the impact of intrusion threats on ICVs. On the other hand, the rise in explainable AI (XAI) results from the requirement to inject confidence, transparency, and repeatability into the development of AI for the security of ICV and to provide a safe ITS. As a result, the scope of this review covered the XAI models used in ICV intrusion detection systems (IDSs), their taxonomies, and outstanding research problems. The results of the study show that XAI though in its infancy of application to ICV, is a promising research direction in the quest for improving the network efficiency of ICVs. The paper further reveals that XAI increased transparency will foster its acceptability in the automobile industry.

Evolutionary Game and Simulation Analysis of Intelligent Connected Vehicle Industry With Cross-Border Collaborative Innovation

The Made in China 2025 national strategy has prioritized intelligent connected vehicles (ICV) to realize the intelligence and connection transformation and upgrading of the automotive industry, ushering in unprecedented development opportunities. There are two technology paths in the ICV industry: single-vehicle intelligence and vehicle-infrastructure collaboration. Both face problem of low technological innovation efficiency, and key to solving it is breaking down barriers between enterprises and realizing cross-border collaborative innovation. This study offers a new cross-border collaborative innovation development paradigm for the ICV industry, centered on automotive enterprises and technology platform providers. This study examines the impact of changes in key parameters on the evolutionary results using the system dynamics method to analyze the efficiency of cross-border collaborative innovation in the ICV industry. The simulation results showed that cross-border collaborative innovation is inevitable for the ICV industry. Furthermore, compared to the single-vehicle intelligence scenario, the vehicle-infrastructure collaboration scenario shows faster convergence between automotive enterprises and technology platform providers. Finally, the choice of system collaborative innovation strategy is influenced by default cost and the collaborative innovation risk coefficient, whereas the cost-sharing coefficient and network connection fee only have an impact on the cross-border collaborative innovation system’s rate of evolution in the ICV industry.