methyldragon / ros-sensor-fusion-tutorial Goto Github PK
View Code? Open in Web Editor NEWAn in-depth step-by-step tutorial for implementing sensor fusion with robot_localization! ๐ฐ
License: MIT License
An in-depth step-by-step tutorial for implementing sensor fusion with robot_localization! ๐ฐ
License: MIT License
Is the functionality implemented by this package consistent with that of robot_pose_ekf?
fatal error: lino_msgs/Velocities.h: No such file or directory
I do not know how to start and follow this tutorial. Do I have to "Buy you a coffee" to start?
@methylDragon Thanks for the awesome tutorial. It will be a great help if provided with a sample dataset.(bagfile).
Kind regards
Is fusing GPS data along with the imu and laser data for creating Gmapping (not for robot localization) possible ?
Hi methylDragon! Thank you for this really nice tutorial.
I was wondering if it would be possible for you to provide a bagfile for us to follow the tutorial using the same data you used.
Thank you in advance!
Hi methylDragon, thanks for the significant tutorial you have made, there was nothing like this before and I think it's really necessary to have a complete and clear tutorial about the obscure field of sensor fusion.
So, I would like to make some questions about two points I think they really need to be explained deeper:
It's really tough to understand how to set it and to get the general view about the process.
For example, I'm trying to fuse an odometry source with the data coming from an IMU. To do this I'm using an ekf filter. At the moment my IMU has a covariance matrix filled with zeros. As you can read from here this is an error:
Missing covariances. If you have configured a given sensor to fuse a given variable into the state estimation node, then the variance for that value (i.e., the covariance matrix value at position (i,i), where i is the index of that variable) should not be 0. If a 0 variance value is encountered for a variable that is being fused, the state estimation nodes will add a small epsilon value (1eโ6) to that value. A better solution is for users to set covariances appropriately.
Ok, so let's set the covariances appropriately. I think I only have two options: calculate it or get the values from the datasheet.
So, let's look at the datasheet. I'm using the X-NUCLEO-IKS01A1 board with LSM6DS0 IMU. The datasheet is here. As you can see there's a table on page 9 that talks about noise, like 'Gyroscope RMS noise in normal/low-power mode', etc. But how can I relate these values to variances? I didn't find anything on the web apart from this answer here where they say:
If you haven't got a background in random processes and signal analysis then you're going to have a rough time relating this back to real-world numbers, particularly if you're doing any kind of sensor fusion. Even the "big boys" in the sensor fusion game can't easily map sensor noise to system behavior without lots of simulation and head-scratching.
The other option is to calculate/approximate the covariance matrix. Again, I didn't find any standard approach to do it. I came up with the idea to just collect data for a while, placing the IMU in a very firm way, then calculating the variance (so assuming the covariance matrix diagonal). Does it make sense an approach like this?
I see that you calculated an estimate of the covariance from the sensor resolution and then you tuned it (from 0.0004 to 0.1404). How did you tune it and how did you get this number?
Moreover, do you know if there's a standard approach to set the covariance matrix? What's the complete spectrum of the alternatives?
You've also tuned the initial_estimate_covariance and process_noise_covariance matrices, how did you do it?
Lastly, if you have some references to books or papers about this stuff could you please share them?
Thanks for all what you're doing to make the sensor fusion topic clearer for everyone.
Hello! I found in the tutorial you mentioned that:
If you have an odometry EKF node, also remember to remap the inputs to the AMCL node
<remap from="odom" to="odometry/filtered" />
I'm not quite sure about what it means, I have the similar layered EKFs for global localization and odometry, respectively. And they have their own published topic as odometry/filtered_map and odometry/filtered_odom. I'm not sure which to put to the remap command, and why I need to remap it in any way, the filtered odom is supposed to go to EKF instead of AMCL right?
Thanks a lot!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.