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

Explore hidden areas at first #9

Open
DmytroKushnirSoftserveinc opened this issue Feb 28, 2019 · 4 comments
Open

Explore hidden areas at first #9

DmytroKushnirSoftserveinc opened this issue Feb 28, 2019 · 4 comments
Assignees
Labels
mostly_done essential severity of issue is resolved, but it worth leaving on a table to make few tips

Comments

@DmytroKushnirSoftserveinc
Copy link
Contributor

DmytroKushnirSoftserveinc commented Feb 28, 2019

From the active_SLAM paper :
idea is to have a separate class of frontiers which are within the lidar range, but is not mapped: the usual reason is occlusion from some obstacles. As those areas are generally cheapest to explore it makes sense to search them at first.
-- done

-- upd Iter 1 completed

@DmytroKushnirSoftserveinc
Copy link
Contributor Author

DmytroKushnirSoftserveinc commented Feb 28, 2019

Idea: use a shorter timeout for marking them as unreachable, as they are potentially situated at the narrow paths.
-- done

@DmytroKushnirSoftserveinc
Copy link
Contributor Author

DmytroKushnirSoftserveinc commented Feb 28, 2019

Idea: try to reach the 'oldest' "Hidden" areas at first in order to minimize the cases when you have to plan your way back to the unmapped piece of territory left behind.

@DmytroKushnirSoftserveinc
Copy link
Contributor Author

Solve the problem when we have a wall on a way to close frontier (when frontier is in the other room).
OR: do not mark such frontiers as hidden at all

@DmytroKushnirSoftserveinc
Copy link
Contributor Author

DmytroKushnirSoftserveinc commented Mar 18, 2019

the idea of hidden frontiers need more exploration, implemented version seems like the only helper for heuristic ranking... as opened but still underexplored area is evaluated as such;
Contrary: it gives 'chained' exploration effect, but better to do it with nice heuristics.
UPD: shorter distance seems to be a better solution, but still suboptimal.

@DmytroKushnirSoftserveinc DmytroKushnirSoftserveinc changed the title F#6: try to explore hidden areas at first Explore hidden areas at first Mar 21, 2019
@DmytroKushnirSoftserveinc DmytroKushnirSoftserveinc added the mostly_done essential severity of issue is resolved, but it worth leaving on a table to make few tips label Mar 27, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
mostly_done essential severity of issue is resolved, but it worth leaving on a table to make few tips
Projects
None yet
Development

No branches or pull requests

1 participant