Perception Technologies for Autonomous Transportation: A Comparative Analysis of LiDAR, Radar, Camera, and Sonar

Details

• Creators:
  Soltanirad, Mohammad ; Baghersad, Mahdi
• Corporate Creators:
  Texas Tech University. Department of Civil, Environmental, and Construction Engineering ; University of Alabama at Birmingham. Dept. of Civil, Construction, and Environmental Engineering
• Contributors:
  Gilani, Vahid Najafi Moghadam
• Subject/TRT Terms:
  Analysis Autonomous Vehicles Cameras Data Fusion Laser Radar Perception Sensors Sonar Technology
• DOI:
  https://doi.org/10.82042/crpase.11.4.2967
• Resource Type:
  Journal Article
• Right Statement:
  Open Access; https://creativecommons.org/licenses/by/4.0/
• Geographical Coverage:
  United States
• Corporate Publisher:
  Computational Research Progress in Applied Science & Engineering (CRPASE)
• Abstract:
  This paper presents a comprehensive comparative analysis of the primary perception technologies, LiDAR, Radar, Camera, and Sonar, that underpin modern intelligent transportation systems and autonomous vehicles. While numerous studies have examined individual sensor technologies, this paper's primary contribution lies in its holistic, cross-modal analysis, presenting a unified framework that directly links sensor performance metrics to specific transportation application requirements. It reviews the operating principles, variants, and data processing algorithms for each modality. The study evaluates these sensors across critical performance metrics, including spatial accuracy, resolution, robustness in adverse environmental conditions, and cost, grounding these comparisons in quantitative data from established industry benchmarks. The study emphasizes multi-sensor fusion strategies, discussing the architectures and trade-offs involved. Furthermore, the paper provides a detailed discussion on application-specific sensor selection and the open challenges facing the field, such as validation and the role of simulation. The analysis concludes that while each sensor has unique strengths, such as LiDAR's centimeter-level accuracy (typically ±2-5 cm) or radar's direct, high-precision velocity sensing (often ±0.1 m/s), a multi-modal, fused-sensor approach is essential for achieving the safety, reliability, and operational robustness required for the widespread deployment of autonomous transportation.
• Content Notes:
  This is an open access article under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license https://creativecommons.org/licenses/by/4.0/. Please cite this article as: M. Soltanirad, M. Baghersad, Perception Technologies for Autonomous Transportation: A Comparative Analysis of LiDAR, Radar, Camera, and Sonar, Computational Research Progress in Applied Science & Engineering, CRPASE: Transactions of Civil and Environmental Engineering 11 (2025) 1–10, Article ID: 2967. https://doi.org/10.82042/crpase.11.4.2967
• Format:
  PDF
• Collection(s):
  Autonomous Vehicles
• Main Document Checksum:
  urn:sha-512:807b683a8b01c842ef52496d3ac0a16726f9b38d94b3d5339b4adbc4af661f36f88a75dd67a178eaa1f9a1e5673d6c6ba862f381ba4be844d9e461c7d91d90ad
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/87734/dot_87734_DS1.pdf
• File Type:
  [PDF - 586.52 KB ]