人工智能学院姚美宝副教授指导赵焕峰同学的论文“DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment”近日被ICRA 2024会议（清华推荐A类，CCF-B类）接收。
ICRA，全称为机器人与自动化国际会议（International Conference on Robotics and Automation），是机器人领域最有影响力的国际学术会议之一。作为IEEE机器人和自动化学会的旗舰会议，ICRA汇集世界顶尖的研究人员和领先的企业，分享机器人和自动化领域的新想法和新进展。ICRA 2024将于2024年5月13日至5月17日在日本横滨举办。
论文题目：DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment
第一作者：赵焕峰
指导教师：姚美宝
收录会议：ICRA 2024
会议类别：清华推荐A类，CCF-B类
论文概述：
动态对象会导致点云地图的分布多样化，降低机器人下游任务的性能。为了解决该问题，本文提出了一种基于实时动态实例感知的静态地图构建框架，称为DynaInsRemover。该框架利用实例之间的几何差异有效地移除动态对象，同时保留静态点云地图的更多细节。该框架包含用于初始动态实例检测的Instance Occupancy Check模块和用于恢复误报实例的Instance Belief Update模块。在SemanticKITTI数据集上进行了DynaInsRemover性能的定量评估，并在现实世界环境中进行了验证。实验评估表明，该框架在动态环境中取得了十分有效的结果。
Title: DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment
First author: Huanfeng Zhao
Corresponding author: Meibao Yao
Conference: ICRA 2024, CCF-B
Abstract:
Dynamic objects diversify the distribution of point cloud in the map, degrading the performance of the robotic downstream tasks. To address this problem, we present a novel real-time dynamic instance-aware static mapping framework called DynaInsRemover, which exploits the geometric discrepancies between instances to efficiently remove dynamic objects preserve more details of static map. It contains the Instance Occupancy Check module for initial dynamic instance proposal and the Instance Belief Update module for reverting false positives. We quantitatively evaluate our approach performance on SemanticKITTI and validate it in real-world environment. Experimental evaluations show that our method achieves very promising results in dynamic environments.
