Core AI Technology and Development Trend of Autonomous Vehicle Safety Perception

Main Article Content

Sixuan Lin
DOI: https://doi.org/10.70267/aitia.20260113

Keywords

autonomous driving, environmental perception, AI, driving safety, core technology, future trends

Abstract

With the rapid development of artificial intelligence (AI) technology, autonomous vehicle have become an important part of the future transportation system. As the core link of auto drive system, environment awareness has a direct impact on the performance of the whole system. Therefore, this paper systematically combs the development process of core AI technology in the field of autonomous vehicle perception through comparative analysis, and deeply discusses the evolution of different technology paths. First of all, this paper reviews the historical background of the safety development of autonomous vehicle, and analyzes the main challenges facing the current perception technology; Then, this article compares the research results of different representative scholars and different key technology routes from three key dimensions, revealing the inherent logic and future trends of the development of perception technology. This article aims to provide theoretical reference for technological innovation and safety system construction in the field of autonomous driving safety, and to assist in the large-scale application of autonomous driving technology under the premise of safety and controllability.

Abstract 0 | PDF Downloads 0

References

  • [1] Huang H, Jiang Y, Wang Z, et al. Perceptions of driverless vehicles among social media influencers in China: A case analysis of Apollo Go[J]. Transport Policy, 2026, 179: 104017.
  • [2] Ansarinejad M, Ansarinejad K, Lu P, et al. User Experience of Navigating Work Zones with Automated Vehicles: Insights from YouTube on Challenges and Strengths[J]. Smart Cities, 2025, 8(4): 120.
  • [3] Shao H, Xie D, Huang Y. A survey of intelligent sensing technologies in autonomous driving[J]. ZTE Communications, 2021, 19(3): 56.
  • [4] Li Guofa, Ouyang Delin, Wu Hao, etc Key technologies and development trends of intelligent perception in complex scenarios of advanced autonomous driving [J]. Chinese Journal of Highways, 2026,39 (1): 289-312
  • [5] Shi D, Zhao C, Zhao C, et al. Depth-aware unpaired image-to-image translation for autonomous driving test scenario generation using a dual-branch GAN[J]. Frontiers in Neurorobotics, 2025, 19: 1603964.
  • [6] Chen Chun, Li Xingfeng, Zhou Shuhong Multidimensional Perspective on Autonomous Driving Safety: Key Challenges and Collaborative Governance Framework [J]. Automotive Digest, 2026, (2): 1-11
  • [7] Cheng Z, Zhu J, Feng Z, et al. Driving Safety Risk Analysis and Assessment in a Mixed Driving Environment of Connected and Non-Connected Vehicles: A Systematic Survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(5): 5747-5781.
  • [8] Huang L, Li P, Zhang J, et al. Robust Lane Line Detection for Intelligent Vehicles under Complex Illumination Conditions Based on Image Processing[J]. Traitement du Signal, 2025, 42(3): 1343-1352.
  • [9] Wang Q, Zhou Z, Zhang Z. Fog-YOLO: A Real-Time Object Detector for Foggy Autonomous Driving Scenarios[J]. Symmetry, 2026, 18(2): 322.
  • [10] Ma M, Zhu Z, Zhao S, et al. R-RNet: Probability-Driven Networks for Pedestrian Trajectory Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2026, 27(1): 857-867.
  • [11] Zheng D, Zhao Y, Tian W, et al. Self-Supervised Absolute-Scale Multi-Sensor Fusion Odometry via Multi-Layer Feature Fusion and Pose Refinement for Autonomous Driving[J]. IEEE Transactions on Automation Science and Engineering, 2026, 23: 995-1008.
  • [12] Zhang X, Bao J, Chi J, et al. Comprehensively evaluating the perception systems of autonomous vehicles against hazards[J]. Information Fusion, 2026, 127: 103729.
  • [13] Zeng Junwei,Qian Yongsheng,Wang Wenhai,Xu Dejie,Li Haijun. The impact of connected automated vehicles and platoons on the traffic safety and stability in complex heterogeneous traffic systems[J]. Physica A: Statistical Mechanics and its Applications,2023,629
  • [14] Ren S, He K, Girshick R, et al. Object Detection Networks on Convolutional Feature Maps[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(7): 1476-1481.
  • [15] ]Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
  • [16] Chen Z, Liu B. A High-Accuracy PCB Defect Detection Algorithm Based on Improved YOLOv12[J]. Symmetry, 2025, 17(7): 978.
  • [17] Wei J, As’arry A, Anas Md Rezali K, et al. A Review of YOLO Algorithm and Its Applications in Autonomous Driving Object Detection[J]. IEEE Access, 2025, 13: 93688-93711.
  • [18] Terven J, Córdova-Esparza D M, Romero-González J A. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS[J]. Machine Learning and Knowledge Extraction, 2023, 5(4): 1680-1716.
  • [19] Pandey M ,Tripathi P ,Jaiswal T . A Robust Approach to Object Detection in Images using Improved TCenterNet Method[J]. Recent Advances in Electrical & Electronic Engineering,2024,18(2):202-211.
  • [20] Zhang Y ,Zhou Z.SAE-PointPillars: Adaptive Spatial Feature Fusion Based PointPillars 3D Target Detection Algorithm[J]. IAENG International Journal of Computer Science,2025,52(6):
  • [21] Tang Q, Yang J, He X, et al. Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion[J]. Computer Vision and Image Understanding, 2021, 202: 103086.
  • [22] Tan Yongqian, Zeng Fanju Single image dehazing algorithm based on adaptive superpixel segmentation and multi model transmittance estimation optimization [J]. Advances in Laser and Optoelectronics, 2025, 62 (20): 41-54
  • [23] Zhang G, Fang W, Zheng Y, et al. SDBAD-Net: A Spatial Dual-Branch Attention Dehazing Network Based on Meta-Former Paradigm[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(1): 60-70.
  • [24] Wang F, Gu J, Wang Y, et al. TFRHaze: a multimodal dehazing algorithm based on vision transformer and self-attention mechanism[J]. Journal of Electronic Imaging, 2025, 34(06).
  • [25] Vazquez-Corral J, Finlayson G D, Bertalmío M. Physical-based optimization for non-physical image dehazing methods[J]. Optics Express, 2020, 28(7): 9327.
  • [26] Si J, Niu Y, Wang B. A Review of Nonlinear Filtering Algorithms in Integrated Navigation Systems[J]. Sensors, 2025, 25(20): 6462.
  • [27] Cheng J, Chen H, Xue Z, et al. An Online Exploratory Maximum Likelihood Estimation Approach to Adaptive Kalman Filtering[J]. IEEE/CAA Journal of Automatica Sinica, 2025, 12(1): 228-254.
  • [28] Yao X, Guo J, Hu J, et al. Using Deep Learning in Semantic Classification for Point Cloud Data[J]. IEEE Access, 2019, 7: 37121-37130.
  • [29] VazquezCorral Javier,Finlayson Graham D,Bertalmío Marcelo. Physical-based optimization for non-physical image dehazing methods. [J]. Optics express,2020,28(7):
  • [30] Lian J, Wang Z, Yang D, et al. Pedestrian Facial Attention Detection Using Deep Fusion and Multi-Modal Fusion Classifier[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(1): 967-980.
  • [31] Wang R, Cheng J, Yu J. Timewise Intentions and Time-Varying Distribution Network for Pedestrian Trajectory Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(11): 21123-21134.
  • [32] Kaman S, Javeriya S B, Makandar A. Hybrid CNN-based detection of forged facial images using Gabor filters and local binary patterns[J]. Discover Computing, 2025, 28(1): 244.
  • [33] XIE H ,ZHAO H ,XU C , et al.All-day perception for intelligent vehicles: switching perception algorithms based on WBCNet[J]. Science China(Information Sciences),2024,67(11):269-284.
  • [34] Qiao S, Tang R, Pan L, et al. Where to Go: A Spatial Social Force Graph Neural Network for Predicting Pedestrian Trajectories From Videos With Complex Motion Scenarios[J]. IEEE Transactions on Computational Social Systems, 2025: 1-16.
  • [35] Zhou X, Chen X, Yang J. Heterogeneous hypergraph transformer network with cross-modal future interaction for multi-agent trajectory prediction[J]. Engineering Applications of Artificial Intelligence, 2025, 144: 110125.
  • [36] Zeng J, Qian Y, Wang W, et al. The impact of connected automated vehicles and platoons on the traffic safety and stability in complex heterogeneous traffic systems[J]. Physica A: Statistical Mechanics and its Applications, 2023, 629: 129195.
  • [37] Colombi A, Scianna M. Modelling human perception processes in pedestrian dynamics: a hybrid approach[J]. Royal Society Open Science, 2017, 4(3): 160561.
  • [38] Zhang Y, Yan H, Lu X. An enhanced HMM map matching algorithm incorporating personal road selection preferences[J]. Scientific Reports, 2025, 15(1): 35962.
  • [39] Deo N, Rangesh A, Trivedi M M. How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction[J]. IEEE Transactions on Intelligent Vehicles, 2018, 3(2): 129-140.
  • [40] Xie Huiyu, Du Zhibin, Sun Yaxuan Overview of autonomous vehicle Sensing System [J]. Times Auto, 2019, (18): 29-30
  • [41] Qiao S, Gao F, Wu J, et al. An Enhanced Vehicle Trajectory Prediction Model Leveraging LSTM and Social-Attention Mechanisms[J]. IEEE Access, 2024, 12: 1718-1726.
  • [42] Cai Si, Gao Lijie Research on autonomous vehicle Environment Awareness System [J]. Auto Parts, 2021, (11): 105-107
  • [43] Yang L, Lin X, Hou Y, et al. Application of an Improved Adaptive Unscented Kalman Filter in Vehicle Driving State Parameter Estimation[J]. International Journal of Adaptive Control and Signal Processing, 2025, 39(5): 1021-1035.
  • [44] Sathya S K ,Kumar M S . Realistic scenario-based trajectory control, path planning, and collision avoidance for autonomous vehicles[J]. Expert Systems With Applications,2026,319132078-132078.
  • [45] Xin G, Chu D, Lu L, et al. Multiagent Trajectory Prediction With Difficulty-Guided Feature Enhancement Network[J]. IEEE Robotics and Automation Letters, 2025, 10(3): 2582-2589.
  • [46] Cao Wuhong, Cai Yingfeng, Liu Ze, etc End to end autonomous driving decision model based on improved human feedback reinforcement learning [J]. Automotive Engineering, 2026,48 (1): 24-36
  • [47] Aeberhard M, Rauch S, Bahram M, et al. Experience, Results and Lessons Learned from Automated Driving on Germany’s Highways[J]. IEEE Intelligent Transportation Systems Magazine, 2015, 7(1): 42-57.
  • [48] Yuan R, Abdel-Aty M, Xiang Q, et al. A Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(1): 1204-1216.
  • [49] Liang J, Tan C, Yan L, et al. Interaction-Aware Trajectory Prediction for Safe Motion Planning in Autonomous Driving: A Transformer-Transfer Learning Approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(10): 17080-17095.
  • [50] Zhu W, Dai J, Zhou X, et al. A Multi-Fusion Early Warning Method for Vehicle–Pedestrian Collision Risk at Unsignalized Intersections[J]. World Electric Vehicle Journal, 2025, 16(7): 407.
  • [51] Ji M, Wu Q, Fan P, et al. Graph Neural Networks and Deep Reinforcement Learning-Based Resource Allocation for V2X Communications[J]. IEEE Internet of Things Journal, 2025, 12(4): 3613-3628.
  • [52] Samadzadegan F, Toosi A, Dadrass Javan F. A critical review on multi-sensor and multi-platform remote sensing data fusion approaches: current status and prospects[J]. International Journal of Remote Sensing, 2025, 46(3): 1327-1402.
  • [53] Liu S, Jiang B, Mao Z, et al. Adaptive Fractional-Order Fault-Tolerant Coordinated Tracking Control of Heterogeneous Multiagent Systems Against Multiple Faults Under Deception Attacks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2025, 61(2): 1860-1870.
  • [54] Wu Y, Huang X, Cao B, et al. DAG Blockchain-Assisted Asynchronous Federated Mutual Learning for Autonomous Driving[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(5): 6263-6275.
  • [55] Chen J, He J, Chen F, et al. Empowering IoT-Based Autonomous Driving via Federated Instruction Tuning With Feature Diversity[J]. IEEE Internet of Things Journal, 2025, 12(6): 6095-6108.
  • [56] Cai X, Zhao P, Liu S, et al. Enhancing Federated Learning in Connected and Autonomous Vehicles Through Cost Optimization and Advanced Model Selection[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(4): 5276-5289.
  • [57] Chang X, Obaidat M S, Ma J. et al. Efficient Federated Learning via Adaptive Model Pruning for Internet of Vehicles With a Constrained Latency[J]. IEEE Transactions on Sustainable Computing, 2025, 10(2): 300-316.

Article Sidebar

PDF
Published
Sep 13, 2026
Conference Proceedings Volume
Vol. 16 (2026): Proceedings of the 2026 International Conference on AI and Technological Innovation Applications (AITIA 2026)
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Lin, Sixuan. “Core AI Technology and Development Trend of Autonomous Vehicle Safety Perception”. Exploring Science Academic Conference Series, vol. 16, Sept. 2026, https://doi.org/10.70267/aitia.20260113.