dimensionalOS / dimensionalOS/dimos

M20 simple nav integration

Open
#2,623 22 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Integrate our simple 2D nav + M20 lidar

git checkout feat/ivan/m20
dimos --transport=zenoh --zenoh-connect=tcp/m20:7447 run m20

Project Scope

The scope of this project is to integrate Simple Nav onto the M20 platform, then iteratively test and tune the system until it meets the agreed indoor navigation objectives.

There is no fixed baseline version for this project. The Simple Nav configuration and parameters will be continuously adjusted based on field-test results. Each test iteration must record the deployed revision, configuration, parameter changes, test scenario, results, and evidence.

The target outcome is stable, autonomous office navigation: the M20 can navigate to reachable locations with a reasonable path and speed; safely stop for unreachable goals; maintain map integrity and runtime stability during extended operation.

Workstreams

  1. Onboard navigation deployment
    • Move the navigation algorithm from the current remote-deployment model to M20 onboard execution.
    • Eliminate the operational dependency on remote point-cloud streaming and remote command delivery.
    • Resolve networking issues required for deployment, monitoring, and control.
  2. Zenoh Bridge removal
    • Remove the Zenoh Bridge from the operational navigation path.
    • Verify that required navigation data and commands continue to function correctly after its removal.
  3. Costmap quality and persistence
    • Tune the costmap to preserve valid historical point-cloud information.
    • Prevent unwanted clearing of historical point-cloud data.
    • Improve map quality, consistency, and navigability.
  4. Global path-planning quality
    • Improve planning output to eliminate zigzagging or unnecessarily oscillating paths.
    • Ensure paths are feasible, smooth enough for the M20, and appropriate for office navigation.
  5. Trajectory-tracking quality
    • Tune the trajectory controller so the M20 follows planned paths reliably at an appropriate speed.
    • Reduce overshoot, unnecessary rotation, oscillation, and tracking error.
  6. Integrated field testing and stability
    • Test reachable and unreachable goals across the office.
    • Validate behavior under extended operation and identify memory leaks, map corruption, network failures, or performance degradation.

Synced from DIM-1079 by ivan

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 files or tests are named. Start by checking out feat/ivan/m20 and running the provided dimos command, then map each workstream to the relevant navigation, networking, costmap, planner, controller, and field-testing entry points. Done requires stable onboard office navigation, validated reachable and unreachable goals, runtime stability, and recorded revisions, parameters, scenarios, results, and evidence.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
networking, robotics
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.