dimensionalOS / dimensionalOS/dimos
agent encode for PoseStamped
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 808
- Avg merge
- 3d 5h
- Merged PRs (30d)
- 233
Description
if my skill returns some posestamped (and other stuff potentially)
PoseStamped needs to be rendered to an agent (maybe as text description relative to the robot body) so agent knows "this pose is 5 meters to my 3 o clock" and more then that - agent should be able to ask to navigate to it, rotate towards it etc (I guess can just support global coordinate nav)
This way I can ask the agent "what is the coolest place you saw last 5 minutes" this is a memory2 query - probably semantic query, returns images and poses, agent should be able to look at the image, be able to describe it, and navigate to pose
Synced from DIM-764 by summer
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
The issue mentions PoseStamped outputs from skills, memory2 semantic queries, images, and navigation or rotation requests, but names no files or tests. Start by locating the skill-output and navigation entry points, then clarify how poses should be rendered and which actions must be supported; done means an agent can interpret returned poses and act on them.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, robotics
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100