-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add VSLAM proposal #92
Conversation
Signed-off-by: jike5 <[email protected]>
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here.
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Welcome @jike5! It looks like this is your first PR to kubeedge/community 🎉 |
|
||
## 2 Proposal | ||
|
||
We propose using one of the classic SLAM frameworks: ORB-SLAM2 as the basis. Just like ORB-SLAM2 or other classic frameworks, the SLAM system mainly includes four modules: tracking, local optimization, loop closure detection and global optimization. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Suggest: adding links to your referenced technologies
|
||
The second method offloads all optimizations to the cloud, which greatly reduces the pressure on edge resources, but requires strong network stability. At the same time, the edge side only needs to maintain a small-scale local map (below 10 frames), and the local map can be updated easily by clearing local map on the edge and repalcing it with new received local map update from the cloud. | ||
|
||
Based on the above discussion, based on the reliable network communication provided by kubeedge and edgemesh and some open source work available for reference(such as [edge-slam][https://github.com/droneslab/edgeslam]), we intend to use the second method for this work. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Replace: [edge-slam][https://github.com/droneslab/edgeslam]
to [edge-slam](https://github.com/droneslab/edgeslam)
|
||
To maintain the synchronization between local map and global map, the cloud will send the latest subset of global map to edge frequently. If the update is **redundant** or **latency**, the edge will not use it. | ||
|
||
## 4 Workers Communication |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If there is no more information, delete it.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If there is no more information, delete it.
Got it!
Nice job!
Use Cases: Case studies are powerfully informative tools that can help you win bids with your proposals. The truth is, case studies are handy because your audience may be critical of overt claims, and the best way to dispel that doubt is to back yourself up with solid data. Case studies are valuable resources, but they must be carefully implemented to be totally effective, particularly within a convincing proposal. |
Signed-off-by: jike5 <[email protected]>
/lgtm & /ping @fisherxu |
@JoeyHwong-gk: changing LGTM is restricted to collaborators In response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. |
The proposal will be added in #109. |
Signed-off-by: jike5 [email protected]
Description
Add proposal for Implementation of an VSLAM Algorithm on KubeEdge project
The design architecture and technical details are included in the proposal
Related Issues
kubeedge/examples#120