Comments (4)
lennarthaller
commented on July 26, 2024
Because feeding the orb slam visual odometry to the sensor fusion algorithms like EKF in robot_localization package is not a solution, as I cannot make it as an absolute position that will make the covariances to collapse.
I don't think I understand what you mean here. What is your ultimate goal? Do you really want to improve your wheel odometry or do you want to get a good position estimate of your robot?
If it is the latter I'd suggest leaving the odometry as it is and extending the pose publisher of orb_slam_2_ros to publish a PoseWithCovarianceStamped which can be consumed by the robot_localization package.
from orb_slam_2_ros.
abylikhsanov
commented on July 26, 2024
Yeah, the latter. Does the orb slam gives the covariancr indecies? Also, do
they collapse after loop closure?
I am also thinking to add wheel odometry whenever the track is lost, do you
think it is a good idea?
Regarding the orb slam, I have launched the file but getting logs that 0
matches found and the map vector is empty, but I am supplying the raw
images (not rectified) with camera info prameters. What could it be?
On Wed, 14 Aug 2019 at 12:17, Lennart Haller ***@***.***> wrote:
Because feeding the orb slam visual odometry to the sensor fusion
algorithms like EKF in robot_localization package is not a solution, as I
cannot make it as an absolute position that will make the covariances to
collapse.
I don't think I understand what you mean here. What is your ultimate goal?
Do you really want to improve your wheel odometry or do you want to get a
good position estimate of your robot?
If it is the latter I'd suggest leaving the odometry as it is and
extending the pose publisher of orb_slam_2_ros to publish a
PoseWithCovarianceStamped
<http://docs.ros.org/api/geometry_msgs/html/msg/PoseWithCovarianceStamped.html>
which can be consumed by the robot_localization package.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#37?email_source=notifications&email_token=ADH2L7JY2W3QIVLHXTAHMMDQEPLVBA5CNFSM4ILMS7B2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD4ILKQA#issuecomment-521188672>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ADH2L7J5R6XORCSEDJPAISDQEPLVBANCNFSM4ILMS7BQ>
.
--
Kind regards
Abyl
from orb_slam_2_ros.
abylikhsanov
commented on July 26, 2024
Ok, I can see that it publishes the covariance. One question, where exactly does the Tracking thread store the position values? Because I am planning to store some wheel odometry values and use them whenever the visual will be lost.
from orb_slam_2_ros.
Ador2
commented on July 26, 2024
Tcw is 4x4 transformation matrix (camera frame to world frame), first 3x3 elements are the rotation matrix and elements(rows(1,2,3), column(4)) are x,y,z translations respectively.
from orb_slam_2_ros.
Related Issues (20)
- orb_slam2_ros orb_slam2_d415
- Visualize and save the trajectory HOT 2
- Tf has two or more unconnected trees HOT 3
- no image received using realsense d435i and orb_slam2_d435_rgbd.launch HOT 1
- catkin build fails (Melodic) HOT 2
- Adjust Scale Factor for Metric Conversion
- orb_slam2_ros crashes when camera image topic is available HOT 5
- Slam doesn’t detect movement HOT 2
- How to correctly make a transformation?
- Though the topic name had been aligned, but still not subscribe. HOT 1
- Pose topic very inacurate - D435i
- Using Pointcloud Map.bin outside orbslam
- "If I want to test using a dataset, what should I do?"
- Im not able to receive the image
- colcon build failed undefined reference to `DUtils::Random::SeedRandOnce()' <ORB_SLAM3_ROS2> HOT 1
- how to build from source on aarch64, opencv 4.* - FAQ
- cant start with ROS2 - Wrong path to vocabulary
- camera_frame_id_param_ and target_frame_id_param_: correspond to what frame exactly?
- Compatibility with ROS2 Humble
- No rule to make target (libg2o.so), Failed to build orb_slam3_ros
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from orb_slam_2_ros.