dimensionalOS / dimensionalOS/dimos

Automatic pgo/global map compute on top of previous mem2 databases

Open
#2,243 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

leshy_navigation relocalization
Dominant language
Python
Stars
4.5k
Forks
808
Avg merge
3d 5h
Merged PRs (30d)
233

Description

Current relocalization module requires processing a mem2 database into a global map file
https://github.com/dimensionalOS/dimos/blob/main/docs/capabilities/mapping/relocalization.md

This is ok, but for the future ergonomics, relocalization module can consume mem2 database directly and do the computation required automatically. this eliminates requirement of separate map processing tool for normal user flows (tool stays only for analysis/dev)

add KVstore to actual mem2 database, reloc module recomputes loop closure/global map only if needed. If found in the kvstore, just load it.

Note modules have this build() and start() calls, this belongs in a build() call


Synced from DIM-954 by summer

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Read docs/capabilities/mapping/relocalization.md first, then locate the relocalization module's build() and the mem2 database integration. Implement the stated build-time behavior so the module computes and stores the global map in the database when needed, or loads it from the KVstore when present. Done means normal relocalization can consume the mem2 database without a separate map-processing step.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
databases, robotics
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.