add chinese

python/mujoco/sysid/README.md

@@ -1,73 +1,55 @@
-# System Identification Toolbox
+# 系统辨识工具箱（System Identification Toolbox）
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.png)](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/python/mujoco/sysid/sysid.ipynb)
 
-Given a MuJoCo model and recorded sensor data, find parameters
-that make simulation match reality. By default, the library uses
-nonlinear least-squares with box constraints to minimize the difference
-between measured and simulated (predicted) outputs. Residuals
-can be modified by static or optimized parameters, such as
-weights and time-delays.
+给定 MuJoCo 模型和采集到的传感器数据，寻找能够使仿真结果与真实物理系统相吻合的模型参数。默认情况下，该库使用带有边界约束（box constraints）的非线性最小二乘法来最小化测量输出与仿真（预测）输出之间的差异。残差可以通过静态或待优化的参数（例如权重和时间延迟）进行调整。
 
-The optimizer uses Gauss-Newton with finite-difference Jacobians. Each
-parameter perturbation requires an independent simulation rollout. All
-of them execute in a single batched call to `mujoco.rollout`, parallelized
-across threads.
+优化器采用基于有限差分雅可比矩阵的高斯-牛顿法（Gauss-Newton）。每次参数摄动都需要一次独立的仿真 rollout（推演）。所有 rollout 均在对 `mujoco.rollout` 的单次批处理调用中跨多线程并行执行。
 
-## Pipeline
+## 工作流程（Pipeline）
 
-**You provide:**
-- One or more `ModelSequences` each bundling a single `MjSpec` with one or
-  more sequences of measured data. All will be optimized jointly.
-- A `ParameterDict` defining differentiable `Parameter`s with bounds.
-- Callbacks to apply `Parameter`s to an `MjSpec` (individually or jointly)
-- (optional) Functions (`build_model`, `custom_rollout`, `modify_residual`)
-  that override the default residual function behavior.
+**用户提供：**
+- 一个或多个 `ModelSequences`，每个序列将单个 `MjSpec` 与一个或多个测量数据序列打包在一起。所有序列将被联合优化。
+- 一个 `ParameterDict`，用于定义带有上下界的可微参数 `Parameter`。
+- 用于将 `Parameter` 应用到 `MjSpec` 上的回调函数（可单独或联合应用）。
+- （可选）用于覆盖默认残差函数行为的自定义函数（`build_model`、`custom_rollout`、`modify_residual`）。
 
-**The framework:**
-- Composes user code into a residual function (`build_residual_fn`).
-- Optimizes parameters via batched parallel rollouts (`optimize`).
-- Saves results and generates an HTML report (`save_results`, `default_report`).
+**框架执行：**
+- 将用户代码组合为残差函数（`build_residual_fn`）。
+- 通过批量并行 rollout 优化参数（`optimize`）。
+- 保存结果并生成交互式 HTML 报告（`save_results`、`default_report`）。
 
-## What Can You Identify?
+## 可以辨识哪些参数？
 
-You can optimize any parameter that differentiably modifies the final
-residuals. Common use cases include:
+您可以优化任何能够以可微方式修改最终残差的参数。常见用例包括：
 
-**Physics parameters** settable on `MjSpec`. Most parameters in MjSpec
-can be easily set directly by user-provided callbacks:
+在 `MjSpec` 上可设置的**物理参数**。MjSpec 中的大多数参数可以通过用户提供的回调函数直接轻松设置：
 
-| Target | Approach |
+| 辨识目标 | 对应方法 |
 |---|---|
-| Contact sliding friction | `spec.pair("cp").friction[0] = p.value[0]` |
-| Joint damping | `spec.joint("j1").damping = p.value[0]` |
+| 接触滑动摩擦力 | `spec.pair("cp").friction[0] = p.value[0]` |
+| 关节阻尼 | `spec.joint("j1").damping = p.value[0]` |
 
-Convenience functions are provided for common system identification
-parameterizations that cannot be trivially applied to an MjSpec:
+对于无法直接简单应用到 MjSpec 的常见系统辨识参数化方式，该库提供了便捷函数：
 
-| Target | Approach |
+| 辨识目标 | 对应方法 |
 |---|---|
-| Body mass | `body_inertia_param(..., InertiaType.Mass)` |
-| Body mass + center of mass | `body_inertia_param(..., InertiaType.MassIpos)` |
-| Full inertia (10-D) | `body_inertia_param(..., InertiaType.Pseudo)` |
-| Actuator P/D gains | `apply_pdgain(spec, "act1", p.value)` |
+| 刚体质量 | `body_inertia_param(..., InertiaType.Mass)` |
+| 刚体质量 + 质心位置 | `body_inertia_param(..., InertiaType.MassIpos)` |
+| 完整惯量（10 维） | `body_inertia_param(..., InertiaType.Pseudo)` |
+| 执行器 P/D 增益 | `apply_pdgain(spec, "act1", p.value)` |
 
-Full inertia uses the pseudo-inertia Cholesky parameterization
-([Rucker & Wensing 2022](https://ieeexplore.ieee.org/document/9690029)),
-guaranteeing physical consistency without singularities.
+完整惯量采用伪惯量 Cholesky 参数化（Pseudo-inertia Cholesky Parameterization，[Rucker & Wensing 2022](https://ieeexplore.ieee.org/document/9690029)），保证物理一致性且不存在奇异点。
 
-**Measurement parameters** such as sensor delays, gains, and biases are
-properties of the measurement system, not the physics model. The library
-provides utilities for applying these corrections to the residual after
-rollout. They are functionally complete but their API is not yet final.
+诸如传感器延迟、增益和偏差等**测量参数**属于测量系统的属性，而非物理模型本身的属性。该库提供了在 rollout 之后将这些校正应用于残差的实用工具。这些功能已完备，但其 API 尚未最终定型。
 
-## Example
+## 示例
 
 ```python
 import mujoco
 from mujoco import sysid
 
-# 1. Load model and define parameters.
+# 1. 加载模型并定义待辨识参数。
 spec = mujoco.MjSpec.from_file("robot.xml")
 model = spec.compile()
 
@@ -79,18 +61,17 @@ params.add(sysid.Parameter(
     "link1_mass", nominal=2.0, min_value=0.5, max_value=5.0,
     modifier=set_link1_mass))
 
-# 2. Load and package measured data.
-# arrays assumed to be in MuJoCo order, otherwise pass names argument
+# 2. 加载并封装实测数据。
+# 数组默认采用 MuJoCo 顺序，否则请传入 names 参数
 control = sysid.TimeSeries.from_control_names(times, ctrl_array, model)
 measureddata = sysid.TimeSeries.from_names(times, measurement_array, model)
 initial_state = sysid.create_initial_state(model, qpos_0, qvel_0)
 ms = sysid.ModelSequences("robot", spec, "traj_1", initial_state, control, measureddata)
 
-# 3. Build residual, optimize, save.
+# 3. 构建残差函数、执行优化并保存结果。
 residual_fn = sysid.build_residual_fn(models_sequences=[ms])
 opt_params, opt_result = sysid.optimize(initial_params=params, residual_fn=residual_fn)
 sysid.save_results("results/", [ms], params, opt_params, opt_result, residual_fn)
 ```
 
-`default_report` generates an interactive HTML report with videos, measurement comparisons,
-parameter tables, and confidence intervals.
+`default_report` 可生成包含视频、测量对比图、参数表格以及置信区间的交互式 HTML 报告。

python/mujoco/usd/README.md

@@ -1,3 +1,3 @@
-# USD exporter module
+# USD 导出器模块
 
-Please see [documentation](https://mujoco.readthedocs.io/en/stable/python.html) for details.
+详情请参阅[官方文档](https://mujoco.readthedocs.io/en/stable/python.html)。