Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update EVGP Localization #298

Open
Daniel-Martin576 opened this issue Dec 9, 2019 · 5 comments
Open

Update EVGP Localization #298

Daniel-Martin576 opened this issue Dec 9, 2019 · 5 comments
Assignees
Labels
EVGP EV Grand Prix

Comments

@Daniel-Martin576
Copy link
Contributor

Daniel-Martin576 commented Dec 9, 2019

Since apparently we can't use our GPS's RTK capabilities during comp we need to update our localization by adding lidar scan matching and testing how much our map drifts when we remove the RTK capabilities while testing in Gazebo.

We might also need to potentially experiment with vision odometry (rovio or viso2) if there still a large error between our predicted pose and the ground truth even with scan matching.

@Daniel-Martin576 Daniel-Martin576 added EVGP EV Grand Prix Simulator and removed Simulator labels Dec 9, 2019
@JasonGibson274
Copy link
Contributor

Is this adding scan matching to the EKF in robot_localization?

@Daniel-Martin576
Copy link
Contributor Author

Yeah, we will be combining all the pose estimations through EKF.

@ebretl
Copy link
Contributor

ebretl commented Feb 16, 2020

I'm planning to work on this because it seems interesting. I can't assign myself to the issue, but I'll post an update once I have some progress

@btdubs
Copy link
Contributor

btdubs commented Feb 16, 2020

Are you planning on adding scan matching or do you have something else in mind?

@ebretl
Copy link
Contributor

ebretl commented Feb 16, 2020

Probably just setting up one of these http://wiki.ros.org/laser_scan_matcher

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
EVGP EV Grand Prix
Projects
None yet
Development

No branches or pull requests

4 participants