0
$\begingroup$

I plan to implement a sensor fusion of IMU + Visual odometry using an EKF. I came across the excellent robot_localization package which does pretty much all that I want. However, I need to use perform my task without using ROS, and work in an offline setting, where I have a dump of my IMU and Visual odometry data timestamped. Is there a way to use the package as a library, by calling functions as APIs? How would I go about it, has it been done?

If not, are there any alternatives that fuse IMU + visual odometry data using an EKF or a UKF? I ideally wish to code in Python, however I am comfortable in C++ as well.

$\endgroup$
1
$\begingroup$

Why would you not like to use ROS? Seems like if you use this package along with custom code for the rest of the solution it'll be good to go.

Is there a way to use the package as a library, by calling functions as APIs? How would I go about it, has it been done?

It is possible by altering the code to remove ROS dependencies and use the cor filter algorithm in the package. However I won't suggest that. There should probably be other libraries independent of ROS to achieve this. You can try editing the code as a last resort.

I've been using robot_localization package and have been getting satisfying results

| improve this answer | |
$\endgroup$
  • $\begingroup$ Hello @parzival. The program I am building will ultimately run on a custom robot software stack, and not on ROS. Do you happen to know other libraries that are independent of ROS? $\endgroup$ – Shrutheesh Raman Iyer Jul 2 at 5:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.