Comments (3)
dcolli23
commented on September 17, 2024
It's certainly possible that I'm incorrect here due to it being some time since I went through the derivation. But it does strike me as odd that the prediction regularization derivative would not change with a TY that is closer to the dynamics prediction?
Looking again at the paper, it would seem that Eq. 13 supports my suspicion here.
from cdcpd.
lichenTHU
commented on September 17, 2024
Besides, as I want to compare the results of cpd_outputand gurobi_output in Rviz directly, I find the TY is output by TY = cpd(X, Y, TY_pred, Y_emit_prior);, but the Y is already updated by the newest gurobi_output (deformable_object_configuration_->tracked_.points_) in upper codes.
Thus, it also causes that the published message cdcpd/template cannot show the the pure CPD result, and it would cover the gurobi_output completely.
from cdcpd.
dcolli23
commented on September 17, 2024
I put the CPD equation through a symbolic matrix derivation calculator and I was, unsurprisingly, wrong about this. The C++ code is correct in using Y instead of TY.
from cdcpd.
Related Issues (20)
- Document need to download cuda-samples for freenect2 to correctly build? HOT 2
- Add dependency on jsk_visualization ros package HOT 1
- Document dependency on git LFS HOT 1
- Max segment length is computed incorrectly for rope
- reset does not re-compute the template/gripper positions
- RGB, Depth, and Point Cloud topics should not automatically subscribe
- CMake Depends FAISS
- Consider adding pyrosmsg UM ARM lab fork to CDCPD external directory
- Explicitly list dependencies in the README HOT 1
- Update CDCPD Install Scripts HOT 1
- Need to specify that arc_utilities (and other ROS packages) should be cloned under the workspace src folder
- Either update CDCPD offline to work again or remove it
- Incorporate stretch parameter into cloth max segment length calculation
- Demo2 in rosbags does not work HOT 2
- CDCPD Constructor should be refactored
- Bug with non-square cloth template edge initialization HOT 1
- Incorrect edge display in RVIZ when tracking cloth HOT 3
- `cdcpd/template` cannot publish the pure CPD result HOT 5
- Consider different CPD matrix solver for better tracking accuracy/numerical stability
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cdcpd.