# CRISP框架实现宇树G1人形机器人双臂协作在线预测控制

> 原文链接：https://robotics.hellobike.com/papers/2026-11-06-2611-07268-254eb2db
> 频道：papers | 更新日期：2026-11-06 | 标签：auto, arxiv
> 核心摘要：提出CRISP分层控制框架，将人形机器人动力学解耦为子系统并通过完整约束建模交互力。在宇树G1实机验证中，该框架通过NMPC在线优化双臂力矩与地面反作用力，实现了稳定的双臂协同轨迹跟踪与全身协调运动。

# CRISP框架实现宇树G1人形机器人双臂协作在线预测控制

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[CRISP: Constraint-Resolved Interactions between Subsystems for Predictive Whole-Body Cooperation](https://arxiv.org/abs/2611.07268)（arXiv 2611.07268）

## 核心内容

针对人形机器人高维动力学耦合难题，研究提出CRISP分层控制框架，并在宇树G1人形机器人上完成实机验证。该方法将系统分解为躯干单刚体、手臂及下肢浮动基座模型，利用拉格朗日乘子参数化肩部与末端执行器间的交互力。实验表明，非线性模型预测控制（NMPC）可在线求解最优交互力与关节力矩，确保双臂协作轨迹跟踪精度及全身动态稳定性。

技术架构上，CRISP将手臂-躯干刚性连接及双臂闭环运动链建模为完整约束，高层NMPC联合优化子系统状态、臂部力矩、地面反作用力（GRF）及交互力。优化后的臂部力矩直接驱动双臂操作，预设GRF则映射至下肢关节以实现全身协调。该方案在保留独立子系统建模优势的同时维持了动态耦合，数值仿真与硬件测试均证实了在线计算下的力控一致性与运动稳定性。

## 关键看点

- **动力学解耦**：将人形机器人分解为躯干SRB、手臂及下肢浮动基座模型，通过完整约束与拉格朗日乘子参数化肩部和末端交互力
- **在线NMPC优化**：高层控制器联合优化子系统轨迹、臂部力矩、地面反作用力及交互力，支持在线力设计与动态耦合保持
- **全身协调映射**：优化所得臂部力矩直接用于双臂操作，预设地面反作用力映射至下肢关节力矩，实现操作与移动的统一协调
- **G1实机验证**：在宇树G1平台上验证了在线NMPC性能，双臂协同轨迹跟踪稳定，交互力测量值与仿真结果高度一致

## 工程与产业观察

CRISP通过约束解析与子系统解耦，有效降低了人形机器人全身控制的计算维度，使NMPC能在G1等中型平台上实现在线运行。该架构为双臂精密操作与移动底盘的动态耦合提供了可工程化的分层控制范式，对解决具身智能体复杂任务中的实时力位混合控制具有直接参考价值。

## 英文摘要 (Abstract)

This paper presents a layered control framework that recasts high-dimensional system dynamics as a composition of dynamically interconnected subsystems, with dynamic dual-arm manipulation on the humanoid serving as a representative application. The humanoid is decomposed into a single rigid body (SRB) representing the torso and floating-base dynamic models representing the articulated arms and lower-body. The rigid connections between arm and torso and the closed kinematic chain formed between the end-effectors during cooperative manipulation are represented as holonomic constraints. The corresponding Lagrange multipliers parametrize the interaction wrenches transmitted at the shoulders and between the end-effectors. The high-level nonlinear model predictive control (NMPC) jointly optimizes the subsystem state trajectories, arm torques, ground reaction forces (GRFs), and interaction wrenches, enabling online wrench design and optimization while preserving the dynamic coupling among the independently modeled subsystems. The optimized arm torques are applied directly for cooperative dual-arm manipulation, whereas the prescribed GRFs are mapped to lower-body joint torque for whole-body coordination. We validate the proposed framework through numerical simulations and hardware experiments on a G1 humanoid robot. The results demonstrate optimal interaction wrenches consistent with simulated contact measurement, cooperative dual-arm trajectory tracking, and stable whole-body coordination while executing the NMPC in online manner.

作者：Dario Valenzuela, Jeeseop Kim
:::

## 原始参考来源 (Sources)

- [arXiv 2611.07268：CRISP: Constraint-Resolved Interactions between Subsystems for Predictive Whole-Body Cooperation](https://arxiv.org/abs/2611.07268)