Intelligent Driving Algorithms Based on Varied Sensors: Technical Characteristics and Evolution
DOI:
https://doi.org/10.54097/21ktv813Keywords:
Intelligent driving; environmental perception; multi-sensor; perception algorithms.Abstract
This paper conducts a review study on intelligent driving algorithms based on different sensors. Firstly, it outlines the working principles and characteristics of core sensors for intelligent driving, namely millimeter-wave radar, LIDAR, and cameras. Subsequently, it sorts out the key algorithms corresponding to each sensor: target detection and speed measurement algorithms for millimeter-wave radar, point cloud processing and target detection and tracking algorithms for LIDAR, and computer vision and deep learning algorithms for cameras. It also compares the performance of different algorithms from the dimensions of accuracy, reliability, real-time performance, and cost. Finally, it analyzes the current challenges of the algorithms in terms of complex environment adaptability, balance between real-time performance and accuracy, and multi-sensor collaboration, and looks forward to their development trends, providing a reference for the research and application of intelligent driving perception algorithms.
Downloads
References
[1] Zhu Bin. (2025). Application of environmental perception technology in automotive intelligent safety driving assistance systems. Times Automobile, (07), 190-192.
[2] Wang Chao. (2023). Research on target detection and tracking algorithm based on perception fusion of millimeter wave radar and camera (Master's thesis, Jilin University).
[3] Wang Hai, Xu Yansong, Cai Yingfeng & Chen Long. (2021). Overview of multi-target detection technology for intelligent vehicles based on multi-sensor fusion. Journal of Automotive Safety and Energy, 12(04), 440-455.
[4] Lee S, Yoon Y J, Lee J E, et al. Human–vehicle classification using feature-based SVM in 77-GHz automotive FMCW radar [J]. IET Radar Sonar & Navigation, 2017, 11(10): 1589-96.
[5] Etinger A, Balal N, Litvak B, et al. Non-imaging MM Wave FMCW sensor for pedestrian detection [J]. IEEE Sensors J, 2014, 14(4): 1232-1237.
[6] Cheng Xiaoxiao. (2024). Research on laser SLAM optimization based on multi-sensor fusion and practical application of indoor and outdoor unmanned driving (Master's thesis, Shandong University of Technology). Master. https://link.cnki.net/doi/10.27276/d.cnki.gsdgc.2024.000424. doi:10.27276/d.cnki.gsdgc.2024.000424.
[7] Hu Yanwei, Wang Jianjun, Fan Yuanyuan, Lu Yunpeng, Bai Chongyue & Zhang Jiyun. (2020). 3D modeling and volume calculation of spatial objects based on LIDAR. Chinese Journal of Lasers, 47(05), 496-505.
[8] Dai Jinglan, Chen Zhiyang & Ye Xiuzi. (2007). Application of ICP algorithm in point cloud registration. Journal of Image and Graphics, (03), 517-521.
[9] Qu Tianwei, An Bo & Chen Guilan. (2010). Application of improved RANSAC algorithm in image registration. Journal of Computer Applications, 30(07), 1849-1851+1872.
[10] Youpeng Diao, Longlong Li, Jian Li, Cheng Jiang, Zhiyong Hao & Hairui Jiang. (2025). A real-time intelligent lithology identification based on an optimized Kalman filtering K-nearest neighbors algorithm. Journal of Applied Geophysics, 241, 105830-105830.
[11] Liu Guoping & Lin Kechun. (2024). Research on the development of intelligent connected vehicle technology and standards. Internal Combustion Engine & Parts, (09), 132-134. doi:10.19475/j.cnki.issn1674-957x.2024.09.046.
[12] Zhou Feiyan, Jin Linpeng & Dong Jun. (2017). A survey of convolutional neural networks. Chinese Journal of Computers, 40(06), 1229-1251.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
