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

Example about semantic factors #342

Closed
Sanghyun-Cha opened this issue Oct 26, 2020 · 4 comments
Closed

Example about semantic factors #342

Sanghyun-Cha opened this issue Oct 26, 2020 · 4 comments

Comments

@Sanghyun-Cha
Copy link

I'm studying on semantic SLAM, and recently, I read following papers.

  • Kevin Doherty, Dehann Fourie, John Leonard, “Multimodal Semantic SLAM with Probabilistic Data Association”, 2019 International Conference on Robotics and Automation (ICRA), 2019.
  • Dehann Fourie, John Leonard, Michael Kaess. "A nonparametric belief solution to the Bayes tree." 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016.

Is there some example code about using semantic factors?

@dehann
Copy link
Member

dehann commented Oct 27, 2020

Hi @Sanghyun-Cha , apologies for the slow reply -- will add docs regarding these examples soon and notify you here again. In the meantime the main feature you will be interested in is e.g. 100% certain about :x1 side of regular binary factor, but then fractional certainty about what the association is on ":l1", mocked as a,b,c for illustration

addFactor!(fg, [:x1; :l1a; :l1b; :l1c], fct, multihypo=[1; 0.4; 0.5; 0.1])

There are a few things to tweak if interested but will explain once, clearly in docs.

There is a basic example here:
https://github.com/JuliaRobotics/IncrementalInference.jl/blob/master/test/testMultiHypo2Door.jl

There is some really old code here, but perhaps useful for reference (note looking at this again though, its really old so don't go too far down that path). Better to wait for the documentation to come. Here is the really old code:
https://github.com/JuliaRobotics/Caesar.jl/blob/master/examples/wheeled/vicprk/VicPrkEstimator.jl

Will be best to use the latest IncrementalInference.jl v0.17.0 and RoME.jl v0.10.0 which we will be tagging in the next couple of days so just hang tight on that too or use ] add RoME#master and ] add IncrementalInference#master. You can free back to stable package tags with ] add RoME later.

Hi @keevindoherty,

Not sure if you are perhaps able to share code relating to the semantic slam paper 2019 not yet available. I recall some simulation code here:
https://github.com/JuliaRobotics/Caesar.jl/tree/master/examples/simulation

Thanks either way!
Dehann

@Sanghyun-Cha
Copy link
Author

Thank you for your reply! It helped me a lot.

@dehann
Copy link
Member

dehann commented Nov 4, 2020

Hi @Sanghyun-Cha , here is some more documentation following this issue:
https://juliarobotics.org/Caesar.jl/latest/concepts/dataassociation/

@dehann dehann modified the milestones: v0.0.x, v0.10.1 Nov 4, 2020
@Sanghyun-Cha
Copy link
Author

Thanks for the information!

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

No branches or pull requests

2 participants