Document nonlinear least-squares tutorial.

PiperOrigin-RevId: 615496587
Change-Id: I97975a4dc99a599afd1eb6964d0ca0cf3d9fcc0e

README.md

@@ -50,12 +50,13 @@ your machine.
 If you are a Python user, you might want to start with our tutorial notebooks
 running on Google Colab:
 
- - The first tutorial focuses on the basics of MuJoCo:
+ - The **introductory tutorial** teaches MuJoCo basics:
    [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/tutorial.ipynb)
- - For a more advanced example, see the LQR tutorial which creates an LQR
-   controller to balance a humanoid on one leg using MuJoCo's dynamics
-   derivatives: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/LQR.ipynb)
- - The MJX tutorial provides usage examples of
+ - The **LQR** tutorial synthesizes a linear-quadratic controller, balancing a humanoid on one leg:
+   [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/LQR.ipynb)
+ - The **least-squares** tutorial explains how to use the Python-based nonlinear least-squares solver:
+   [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/least-squares.ipynb)
+ - The **MJX** tutorial provides usage examples of
    [MuJoCo XLA](https://mujoco.readthedocs.io/en/stable/mjx.html), a branch of MuJoCo written in
    JAX:
    [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/mjx/tutorial.ipynb)

doc/XMLreference.rst

@@ -1262,7 +1262,8 @@ The full list of processing steps applied by the compiler to each mesh is as fol
    the desired vertices and faces have already been generated and do not apply removal or re-indexing;
 #. If vertex normals are not provided, generate normals automatically, using a weighted average of the surrounding face
    normals. If sharp edges are encountered, the renderer uses the face normals to preserve the visual information about
-   the edge, unless :ref:`smoothnormal` is true. Note that normals cannot be provided with STL meshes;
+   the edge, unless :ref:`smoothnormal<asset-mesh-smoothnormal>` is true.
+   Note that normals cannot be provided with STL meshes;
 #. Scale, translate and rotate the vertices and normals, re-normalize the normals in case of scaling;
 #. Construct the convex hull if specified;
 #. Find the centroid of all triangle faces, and construct the union-of-pyramids representation. Triangles whose area is

doc/changelog.rst

@@ -49,6 +49,12 @@ Python bindings
 ^^^^^^^^^^^^^^^
 11. Fixed incorrect data types in the bindings for the ``geom``, ``vert``, ``elem``, and ``flex`` array members
     of the ``mjContact`` struct, and all array members of the ``mjrContext`` struct.
+12. Added the ``mujoco.minimize`` Python module for nonlinear least-squares, designed for System Identification (sysID).
+    The sysID tutorial is work in progress, but a pedagogical colab notebook with examples, including Inverse
+    Kinematics, is available here: |ls_colab|
+
+.. |ls_colab| image:: https://colab.research.google.com/assets/colab-badge.svg
+              :target: https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/least_squares.ipynb
 
 
 Version 3.1.2 (February 05, 2024)