wenbowen123/iros20-6d-pose-tracking
A data-driven neural network system for 6D pose tracking of objects in robot manipulation scenarios.

The project implements se(3)-TrackNet, a neural network architecture for long-term 6D pose tracking that operates on RGB-D observations combined with synthetic image conditioning. It addresses domain shift between synthetic training data and real-world images through disentangled feature encoding and a Lie Algebra representation for 3D orientation. The system achieves real-time tracking at 90.9Hz for robotic manipulation tasks including model-based RL, AR/VR, and human-robot interaction.
Frequently asked
- What is wenbowen123/iros20-6d-pose-tracking?
- A data-driven neural network system for 6D pose tracking of objects in robot manipulation scenarios.
- Is iros20-6d-pose-tracking open source?
- Yes — wenbowen123/iros20-6d-pose-tracking is an open-source project tracked on heatdrop.
- What language is iros20-6d-pose-tracking written in?
- wenbowen123/iros20-6d-pose-tracking is primarily written in Python.
- How popular is iros20-6d-pose-tracking?
- wenbowen123/iros20-6d-pose-tracking has 421 stars on GitHub.
- Where can I find iros20-6d-pose-tracking?
- wenbowen123/iros20-6d-pose-tracking is on GitHub at https://github.com/wenbowen123/iros20-6d-pose-tracking.