摘要
为了理解和处理复杂越野场景中环境要素形状不规则、地形多变及路面属性复杂等问题,提出了一种基于多模态融合感知的3D语义占据预测方法.首先,基于图像和激光雷达融合网络获取初始3D语义标签;然后,对越野场景稀疏点云采用贝叶斯稠密化算法补全3D语义占据标签;最后,生成包含复杂环境要素大小、位置和语义信息的3D语义占据栅格地图.试验结果表明,该方法能够有效地提取和表示复杂越野环境中的3D信息,为复杂越野环境下无人履带平台的路径规划提供了更加准确和丰富的先验信息.
A novel three-dimensional(3D)semantic occupancy prediction method was proposed to analyze and handle the complex off-road environments characterized with diverse geometric,terrain,and road surface fea-tures.Firstly,a 3D semantic label was achieved based on a unified framework with the integration of image and LiDAR data.And then,the 3D semantic and occupancy labels were enriched with the Bayesian densification al-gorithm for the sparse point clouds in off-road scene.Finally,a 3D semantic occupancy grid map was generated,incorporating the size,position,and semantic attributes of environment objects.Experiment results show that the proposed method can extract and represent effectively the 3D environmental information in challenging off-road scenarios,providing a robust foundation for enhanced planning and decision-making in unmanned tracked vehicles.
作者
陈慧岩
司璐璐
王旭睿
王文硕
CHEN Huiyan;SI Lulu;WANG Xurui;WANG Wenshuo(School of Mechanical Engineering,Beijing Institute of Technology,Beijing 10081,China)
出处
《北京理工大学学报》
EI
CAS
北大核心
2025年第1期1-10,共10页
Transactions of Beijing Institute of Technology
基金
国家部委基金资助项目(50911020602)。
关键词
无人履带平台
多模态融合
3D语义占据预测
unmanned tracked vehicle
multimodal fusion
3D semantic occupancy prediction
