feat: initial HSAP platform

Huaxu Sentinel Active Safety Platform with embedded algorithm code,
Docker Compose setup, and vendored dataset scaffolds for clone-and-run.

Co-authored-by: Cursor <cursoragent@cursor.com>

algorithms/dms_yolo/code/docs/en/reference/optim/muon.md

@@ -0,0 +1,28 @@
+---
+description: Explore Ultralytics Muon optimizer with Newton-Schulz orthogonalization for neural network training. Includes MuSGD hybrid optimizer and momentum-based updates.
+keywords: Muon optimizer, MuSGD, Newton-Schulz iteration, orthogonalization, momentum optimizer, neural network training, PyTorch optimizer, Ultralytics optimization
+---
+
+# Reference for `ultralytics/optim/muon.py`
+
+!!! success "Improvements"
+
+    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/optim/muon.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/optim/muon.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
+
+<br>
+
+## ::: ultralytics.optim.muon.MuSGD
+
+<br><br><hr><br>
+
+## ::: ultralytics.optim.muon.Muon
+
+<br><br><hr><br>
+
+## ::: ultralytics.optim.muon.zeropower_via_newtonschulz5
+
+<br><br><hr><br>
+
+## ::: ultralytics.optim.muon.muon_update
+
+<br><br>