Author(s)

ShuoPei Yang^*, TaiLiang Zhang

Affiliation(s)

Jiangsu Xingzhitu Intelligent Technology Co., Ltd., Jiangsu 21500, China.

Corresponding Author

ShuoPei Yang

ABSTRACT

With the advancement of urban autonomous driving technology, perception and decision-making planning in complex road scenarios have become critical challenges. Addressing the shortcomings of existing perception and decision-making frameworks, this paper proposes a collaborative perception and decision-making planning framework for autonomous vehicles in complex urban road environments. The study demonstrates that, through a closed-loop perception-decision coordination mechanism and a hierarchical architectural design, this framework effectively enhances both the perceptual performance and decision-making safety of autonomous vehicles in complex scenarios. The research designs a collaborative perception module that enables multi-source heterogeneous data alignment and spatiotemporal consistency fusion, along with a decision-making and planning module incorporating hierarchical decision models and multi-agent game-theoretic modeling. The proposed framework is validated through a simulation platform and real-vehicle testing environments. Experimental results show that the method outperforms baseline approaches in multiple metrics, including target detection and tracking accuracy, communication efficiency, path planning success rate, and reduction in collision risk. Statistical analysis reveals that the collaborative perception module significantly improves data transmission efficiency through adaptive communication bandwidth compression, while the decision-making and planning module enhances robustness and safety via uncertainty quantification and robust optimization. Ablation studies further validate the contribution of each component to the overall performance and the sensitivity of key hyperparameters. The findings of this paper indicate that the collaborative mechanism can notably enhance the performance of autonomous vehicles in complex urban road scenarios, with the main bottlenecks lying in the real-time requirements of the perception-decision loop and the efficiency of data communication. Compared to existing studies, the proposed method demonstrates clear advantages in terms of performance improvement and applicability across diverse scenarios. Nevertheless, the current research has certain limitations, such as the scope of its underlying assumptions and challenges in scaling to larger vehicle groups. Future work will focus on adaptability in dynamic traffic flows and the scalability of the collaborative mechanism. Overall, this study provides a new theoretical framework and practical guidance for collaborative perception and decision-making in autonomous driving, with significant theoretical and practical implications.

KEYWORDS

Autonomous vehicles; Collaborative perception; Decision-making and planning; Complex urban scenarios; Multi-agent systems

CITE THIS PAPER

ShuoPei Yang, TaiLiang Zhang. A collaborative perception and decision-making planning framework for autonomous vehicles in complex urban road scenarios. World Journal of Engineering Research. 2025, 3(2): 75-84. DOI: https://doi.org/10.61784/wjer3048.

REFERENCES

[1] Han Y, Zhang H, Li H, et al. Collaborative Perception in Autonomous Driving: Methods, Datasets, and Challenges. IEEE Intelligent Transportation Systems Magazine, 2023, 15(6): 131-151. DOI: 10.1109/MITS.2023.3298534.

[2] Zhang X, Tao J, Tan K, et al. Finding Critical Scenarios for Automated Driving Systems: A Systematic Mapping Study. IEEE Transactions on Software Engineering, 2023, 49(3): 991-1026.

[3] Huang H, Huang X, Zhou R, et al. Pre-crash Scenarios for Safety Testing of Autonomous Vehicles: A Clustering Method for In-depth Crash Data. Accident Analysis & Prevention, 2024, 203: 107616.

[4] Gong T, Yu X, Zhang Q, et al. An Emergency Operation Strategy and Motion Planning Method for Autonomous Vehicle in Emergency Scenarios. Accident Analysis & Prevention, 2025, 210: 107842.

[5] Ge L, Zhao Y, Zhong S, et al. Efficient Nonlinear Model Predictive Motion Controller for Autonomous Vehicles from Standstill to Extreme Conditions Based on Split Integration Method. Control Engineering Practice, 2023, 141: 105720.

[6] Tian Y, Ma B. Interpretation and Analysis of the Standard on Passenger Car Body in GB7258 “Technical Conditions for Motor Vehicle Operation Safety”. Journal of Automotive Industry Research, 2024(2): 15-21.

[7] Chen L, Wu P H, Chitta K, et al. End-to-End Autonomous Driving: Challenges and Frontiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 10164-10183.

[8] Gan L, Chu W B, Li G F, et al. Large Models for Intelligent Transportation Systems and Autonomous Vehicles: A Survey. Advanced Engineering Informatics, 2024, 62, Part C, 102786. DOI: https://doi.org/10.1016/j.aei.2024.102786.

[9] Mahmud D, Hajmohamed H, Almentheri S, et al. Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(5): 5674-5709.

[10] Yin T, Huang H, Guo C, et al. Discussion on High-Definition Map Production Technology and Data Model Standardization for Autonomous Driving. China Standardization, 2021(4): 33-37.

[11] Feng D, Haase-Schütz C, Rosenbaum L, et al. Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1341-1360.

[12] Sun P P, Sun C H, Wang R M, et al. Object detection based on roadside LiDAR for cooperative driving automation: A review. Sensors, 2022, 22(23): 9316.

[13] Xu R S, Xiang H, Tu Z Z, et al. V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer. In: Proceedings of the 17th European Conference on Computer Vision. Tel Aviv, Israel: Springer, 2022, 107-124.

[14] Liao Y, Yin Z S, Tian X Y. Intelligent channel estimation of SCFDMA based on GNN for V2I scenarios in Internet of vehicles. Acta Electronica Sinica, 2024, 52(3): 772-782.

[15] Xu H Y, Chen J L, Meng S Y, et al. A survey on occupancy perception for autonomous driving: The information fusion perspective. Information Fusion, 2025, 114: 102671.

[16] Li Y Q, Chen Z, Wang T, et al. Apollo: Adaptive Polar Lattice-Based Local Obstacle Avoidance and Motion Planning for Automated Vehicles. Sensors, 2023, 23(4): 1813.

[17] Sadli R, Afkir M, Hadid A, et al. Map-Matching-Based Localization Using Camera and Low-Cost GPS for Lane-Level Accuracy. Procedia Computer Science, 2022, 198: 255-262.

[18] Wang Yunpeng, Wu Qiong, Song Dewang, et al. Overview of Autopilot Data Set and 3D Object Perception Methods. AI-View, 2023, 10(5): 31-47.

[19] Koopman P. Safety Argument Considerations for Public Road Testing of Autonomous Vehicles. SAE International Journal of Advances and Current Practices in Mobility, 2019(2): 512-523.

[20] Nguyen H D, Choi M, Han K. Risk-informed decision-making and control strategies for autonomous vehicles in emergency situations. Accident Analysis & Prevention, 2023, 193: 107305.

[21] Arnold E, Dianati M, de Temple R, et al. Cooperative perception for 3D object detection in driving scenarios using infrastructure sensors. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(3): 1852-1864.