Kimera2: Robust and Accurate Metric-Semantic SLAM in the Real World

M Abate, Y Chang, N Hughes, L Carlone - arXiv preprint arXiv:2401.06323, 2024 - arxiv.org
We present improvements to Kimera, an open-source metric-semantic visual-inertial SLAM
library. In particular, we enhance Kimera-VIO, the visual-inertial odometry pipeline powering …

A New Tightly-Coupled Dual-VIO for a Mobile Manipulator With Dynamic Locomotion

J Xu, S Jeon - IEEE/ASME Transactions on Mechatronics, 2024 - ieeexplore.ieee.org
This article introduces a new dual monocular visual-inertial odometry (dual-VIO) strategy for
a mobile manipulator operating under dynamic locomotion, ie, coordinated movement …

RMSC-VIO: Robust Multi-Stereoscopic Visual-Inertial Odometry for Local Visually Challenging Scenarios

T Zhang, J Xu, H Shen, R Yang… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
We present a Multi-Stereoscopic Visual-Inertial Odometry (VIO) system capable of
integrating an arbitrary number of stereo cameras, exhibiting excellent robustness in the …

MCGMapper: Light-Weight Incremental Structure from Motion and Visual Localization With Planar Markers and Camera Groups

Y Xie, Z Huang, K Chen, L Zhu, J Ma - arXiv preprint arXiv:2405.16599, 2024 - arxiv.org
Structure from Motion (SfM) and visual localization in indoor texture-less scenes and
industrial scenarios present prevalent yet challenging research topics. Existing SfM methods …