当前位置: X-MOL 学术arXiv.cs.RO › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dual-SLAM: A framework for robust single camera navigation
arXiv - CS - Robotics Pub Date : 2020-09-23 , DOI: arxiv-2009.11219
Huajian Huang, Wen-Yan Lin, Siying Liu, Dong Zhang and Sai-Kit Yeung

SLAM (Simultaneous Localization And Mapping) seeks to provide a moving agent with real-time self-localization. To achieve real-time speed, SLAM incrementally propagates position estimates. This makes SLAM fast but also makes it vulnerable to local pose estimation failures. As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle. This paper attempts to correct this problem. We note that while local pose estimation is ill-conditioned, pose estimation over longer sequences is well-conditioned. Thus, local pose estimation errors eventually manifest themselves as mapping inconsistencies. When this occurs, we save the current map and activate two new SLAM threads. One processes incoming frames to create a new map and the other, recovery thread, backtracks to link new and old maps together. This creates a Dual-SLAM framework that maintains real-time performance while being robust to local pose estimation failures. Evaluation on benchmark datasets shows Dual-SLAM can reduce failures by a dramatic $88\%$.

中文翻译:

Dual-SLAM:强大的单相机导航框架

SLAM(同步定位和映射)旨在为移动代理提供实时自我定位。为了实现实时速度,SLAM 增量地传播位置估计。这使得 SLAM 速度快,但也容易受到局部姿态估计失败的影响。由于局部姿态估计是病态的,局部姿态估计失败经常发生,使整个 SLAM 系统变得脆弱。本文试图纠正这个问题。我们注意到,虽然局部姿态估计是病态的,但较长序列上的姿态估计是良性的。因此,局部姿态估计错误最终表现为映射不一致。发生这种情况时,我们保存当前地图并激活两个新的 SLAM 线程。一个处理传入帧以创建新地图,另一个处理恢复线程,回溯将新旧地图链接在一起。这创建了一个双 SLAM 框架,该框架保持实时性能,同时对局部姿态估计失败具有鲁棒性。对基准数据集的评估表明,Dual-SLAM 可以将故障减少 88 美元\%$。
更新日期:2020-09-24
down
wechat
bug