dimensionalOS / dimensionalOS/dimos
M20 Obstacle Avoidance
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 808
- Avg merge
- 3d 5h
- Merged PRs (30d)
- 233
Description
https://github.com/dimensionalOS/dimos/issues/2543
Once m20 navigation works via wifi, runs onboard, we can add a small obstacle avoidance module. it's a small module that corrects the path
takes 2 inputs - path, pointcloud (can be global map if updating fast enough, or just local lidar frame)
has one output - corrected path
we need to probably make sure that trajectory controller understands rotation in path poses, not just position (can strafe) so that obstacle avoidance can position the robot appropriately. Obstacle avoidance if it cannot find a body dimensions aware path, it should just path to the last spot it can reach. - I will update here, we are about to merge this
Synced from DIM-1220 by jetson
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing linked issue #2543 and the existing M20 navigation and trajectory-controller entry points. Trace how path and pointcloud data are represented, then define completion around producing a corrected path, respecting pose rotation, and falling back to the last reachable point when no body-dimensions-aware path exists.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- robotics
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100