dimensionalOS / dimensionalOS/dimos

Collect the same office-walk recording on Go2 with a RealSense 455 mount

Open
#3,779 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Goal

One clean office walk-through recording usable for stereo-nav / VSLAM evaluation.

Route

Walk from one end of the office to the other, keeping AprilTags in view along the way.

Must capture

  • Odometry
  • Every RealSense stream, all at full rate (no dropped or downsampled streams)

Definition of done

  • Recording is uploaded and the path is posted on this ticket
  • Every listed stream is present for the full duration
  • Per-stream measured rate matches the configured rate
  • AprilTags are visible in the color stream across the walk

Platform

Go2, with a RealSense 455 mounted.

Note

The 455 mount has to exist and be rigidly fixed before recording — a mount that shifts mid-run makes the recording unusable.


Synced from DIM-1544 by jeff

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

No source file or test is named; start by confirming that the Go2 has a rigidly fixed RealSense 455 mount and that the recording setup captures odometry and every RealSense stream at full rate. Walk the specified office route with AprilTags visible, then upload the recording and post its path. Done means all streams cover the full duration, measured rates match configuration, and the tags remain visible in color.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, data, robotics
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Clearly specified
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.