首页|隧道环境内无人驾驶车辆目标-决策两级信息融合感知策略

隧道环境内无人驾驶车辆目标-决策两级信息融合感知策略

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
基于隧道内的特殊行驶环境和无人驾驶感知需求,选择合适的传感器及硬件搭建试验车辆,构建了毫米波雷达与摄像头多传感器融合的感知系统;基于YOLOv4 目标级信息融合算法和改进D-S证据理论决策级信息融合算法,提出了一种"目标-决策"两级信息融合策略;最后,在城市道路隧道环境内开展了感知信息两级融合验证试验,试验结果表明:相比单一的摄像头或毫米波雷达感知效果,基于摄像头与毫米波雷达传感器感知ROI区域关联实现的目标级融合结果可以提高 9.51%的识别准确率,弥补了单一传感器在隧道环境内感知技术的不足;基于目标级融合感知结果,利用改进后的 D-S 证据理论算法再进行决策级融合,相比于单一的目标级融合结果,误检率降低了 3.61%,显著提高了检测精度.采取多传感器感知信息目标-决策两级融合策略能够满足隧道特殊环境内无人驾驶车辆可靠感知需求,为推动无人驾驶技术落地应用提供了理论与技术支撑.
Research on Two-level Fusion Strategy of Unmanned Driving Perception Information Target-decision under Tunnel Environments
Based on the special driving environment in the tunnel and the perception requirements of unmanned driving,appropriate sensors and hardware were chosen to build a test vehicle and a per-ception system of multi-sensor fusion of millimeter-wave radar and camera.A two-level information fusion algorithm of"target-decision"was proposed based on YOLOv4 target-level information fusion algorithm and improved D-S evidence theory.Finally,a verification test of perception information two-level fusion was carried out in the urban road tunnel environments.The results show that in the tunnel environments,compared with the single camera or the millimeter-wave radar sensing results,the target-level fusion result based on the association of the camera and the millimeter-wave radar sen-sor to perceive the ROI area may improve the recognition accuracy by 9.51%,making up for the shortcomings of a single sensor in the tunnel environment perception technology.Based on the target-level fusion perception results,using the improved D-S evidence theory algorithm to perform decision-level fusion,compared with the single target-level fusion results,the false detection rate is reduced by 3.61%,which significantly improves detection accuracy.By adopting the multi-sensor sensing infor-mation target-decision-making two-level fusion strategy,it may meet the reliable sensing require-ments of unmanned vehicles in the special tunnel environments,and provide theoretical and technical support for promoting the applications of unmanned controlled technology.

tunnel environmentunmanned driving technologymulti-sensor fusionD-S evi-dence theory"target-decision"two-level fusion strategy

王茂森、鲍久圣、谢厚抗、刘同冈、阴妍、章全利

展开 >

中国矿业大学机电工程学院,徐州,221116

隧道环境 无人驾驶 多传感器融合 D-S证据理论 "目标-决策"两级融合策略

江苏省科技成果转化专项中央高校基本科研业务费专项江苏高校优势学科建设工程项目

BA20230352022XSCX27

2024

10.3969/j.issn.1004-132X.2024.03.005

中国机械工程
中国机械工程学会

中国机械工程

CSTPCD北大核心
影响因子：0.678
ISSN：1004-132X
年,卷(期)：2024.35(3)
  • 27