Both sides previous revision
Previous revision
|
|
research:multisensorslam [2022/07/22 18:23] Simon Schaefer |
research:multisensorslam [2022/07/26 16:34] (current) Simon Schaefer |
====== Multi-Sensor SLAM ====== | ====== Multi-Sensor SLAM ====== |
| |
===== Keyframe-Based Visual-Inertial Odometry and SLAM Using Nonlinear Optimisation ===== | |
| |
{{youtube>TbKEPA2_-m4 }}Here, we fuse inertial measurements with visual measurements: due to the complementary characteristics of these sensing modalities, they have become a popular choice for accurate SLAM in mobile robotics. While historically the problem has been addressed with filtering, advancements in visual estimation suggest that non-linear optimisation offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a probabilistic cost function that combines reprojection error of landmarks and inertial terms. We ensure real-time operation by limiting the optimisation to a bounded window of keyframes by applying various marginalisation strategies. Keyframes may be spaced in time by arbitrary intervals, while old measurements are still kept as linearised error terms. | |
| |
**Current collaborators:** | |
<memberlist> | <memberlist> |
<dokuwiki> | <dokuwiki> |
<filter> | <filter> |
<grps>^vslam$</grps> | <grps>^multisensorslam$</grps> |
</filter> | </filter> |
</dokuwiki> | </dokuwiki> |
</memberlist> | </memberlist> |
* Chris Choi (SRL Imperial College London) | * Chris Choi (SRL Imperial College London) |
| |
| |
| ===== Keyframe-Based Visual-Inertial Odometry and SLAM Using Nonlinear Optimisation ===== |
| |
| {{youtube>TbKEPA2_-m4 }}Here, we fuse inertial measurements with visual measurements: due to the complementary characteristics of these sensing modalities, they have become a popular choice for accurate SLAM in mobile robotics. While historically the problem has been addressed with filtering, advancements in visual estimation suggest that non-linear optimisation offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a probabilistic cost function that combines reprojection error of landmarks and inertial terms. We ensure real-time operation by limiting the optimisation to a bounded window of keyframes by applying various marginalisation strategies. Keyframes may be spaced in time by arbitrary intervals, while old measurements are still kept as linearised error terms. |
| |
**Former collaborators:** | **Former collaborators:** |