主办：陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊：1976年
汽车实用技术

汽车实用技术 ›› 2026, Vol. 51 ›› Issue (11): 1-8.DOI: 10.16638/j.cnki.1671-7988.2026.011.001

• 汽车碰撞安全技术 •    

基于多传感器融合的 AGV 循迹与主动 安全避障系统

杨柳，张文静，艾柯代·穆合太尔，陈思翰，杜怡，周文亮*   

  1. 新疆农业大学 交通与物流工程学院
  • 发布日期:2026-06-04
  • 通讯作者: 周文亮
  • 作者简介:杨柳（2003－），女，研究方向为交通运输 通信作者：周文亮（1999－），男，硕士，助教，研究方向为智能驾驶
  • 基金资助:
    省级大学生创新训练计划项目（S202510758080）

Multi-Sensor Fusion-Based AGV Tracking and Active Safety Obstacle Avoidance System

YANG Liu, ZHANG Wenjing, Aikedai Muhtair, CHEN Sihan, DU Yi, ZHOU Wenliang   

  1. College of Transportation and Logistics Engineering, Xinjiang Agricultural University
  • Published:2026-06-04
  • Contact: YANG Liu

PDF

摘要： 针对复杂场景下自动导引车（AGV）环境感知精度与实时性不足，直接影响主动安全 避障性能的痛点问题，文章提出一种基于激光雷达与视觉融合的多传感器协作感知方案。该 方案采用镭神 16 线激光雷达与 Orbbec Astra 摄像头作为感知硬件，通过强耦合的基于平滑和 建图的激光雷达惯性里程计（LIO-SAM）算法实现同步定位与高精度建图，并利用 YOLOv11 模型进行动态障碍物的实时识别与跟踪。实验结果表明，该系统在复杂环境中能够实现稳定、 精确的定位导航与鲁棒避障。研究为解决 AGV 在非结构化环境中的感知难题提供了有效途 径，对其在物流、医疗及港口等特殊场景的智能化应用具有实践参考价值。

关键词: 激光雷达建图；障碍物识别；视觉测距；AGV 循迹避障

Abstract: Aiming at the problem that insufficient environmental perception accuracy and real-time performance of automated guided vehicle (AGV) in complex scenarios directly degrade active safety obstacle avoidance capability, this paper proposes a multi-sensor coupled perception scheme based on LiDAR and vision fusion. The scheme adopts a Leishen 16-line LiDAR and an Orbbec Astra camera as perception hardware, realizes simultaneous localization and high-precision mapping through a tightly-coupled LiDAR inertial odometry via smoothing and mapping (LIO-SAM) algorithm, and employs the YOLOv11 model for real-time detection and tracking of dynamic obstacles. Experimental results demonstrate that the proposed system achieves stable and accurate positioning, navigation and robust obstacle avoidance in complex environments. This research provides an effective approach to solving the environmental perception challenges of AGV in unstructured environments, and possesses practical reference value for the intelligent application of AGV in special scenarios such as logistics, medical treatment and port transportation.

Key words: LiDAR mapping; obstacle recognition; visual ranging; AGV tracking and obstacle avoidance