Robust and Efficient MuJoCo-based Model Predictive Control via Web of Affine Spaces Derivatives

📄 arXiv: 2512.21109 📥 PDF

作者: Chen Liang, Daniel Rakita

分类: cs.RO

发布日期: 2026-07-20

💡 一句话要点

提出WASP导数以提升MuJoCo模型预测控制的效率与鲁棒性

🎯 匹配领域: 支柱一：机器人控制 (Robot Control)

关键词: 模型预测控制 MuJoCo 仿射空间 导数计算 机器人控制 高效算法 实时决策

📋 核心要点

  1. 现有的MJPC库依赖有限差分法计算导数，导致在高自由度系统中计算成本高，影响实时性。
  2. 本文提出使用WASP导数替代有限差分法，利用先前导数计算的信息加速新导数的计算。
  3. 实验表明，WASP导数在MJPC中实现了高达2倍的速度提升，并在效率和可靠性上优于随机采样规划器。

📝 摘要（中文）

MuJoCo是一种广泛应用于机器人领域的高效物理模拟器，常通过模型预测控制（MPC）实现实时控制策略的优化。现有的开源库MJPC依赖有限差分法（FD）计算导数，导致在高自由度系统或复杂场景中计算成本高昂。本文提出在MJPC中使用仿射空间网络（WASP）导数作为FD的替代方案，WASP通过重用先前导数计算的信息，加速并稳定新导数的计算。实验结果表明，WASP导数在MJPC中表现出色，能够实现高达2倍的速度提升，并在效率和可靠性上超越MJPC的随机采样规划器。为支持后续研究，本文发布了集成WASP导数的MJPC开源实现。

🔬 方法详解

问题定义：本文旨在解决MuJoCo模拟器中有限差分法计算导数的高成本问题，尤其是在高自由度系统和复杂场景下的实时控制需求。

核心思路：通过引入WASP导数，利用仿射空间的网络结构，重用先前的导数计算信息，从而加速新导数的计算过程，适应MPC的迭代更新需求。

技术框架：整体架构包括WASP导数计算模块与MJPC控制策略模块，WASP模块负责高效计算导数，MJPC模块则利用这些导数进行实时控制决策。

关键创新：WASP导数的引入是本文的核心创新，与传统的有限差分法相比，WASP通过信息重用显著提高了导数计算的效率和稳定性。

关键设计：WASP导数的计算过程涉及多个参数设置和优化策略，具体细节包括导数近似的精确度控制和计算过程中的信息重用机制。通过这些设计，WASP能够在多种任务中实现高效的导数计算。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，WASP导数在MJPC中的应用实现了高达2倍的速度提升，相比于有限差分法，WASP在效率和可靠性上均表现优越，尤其在复杂任务中展现出更强的稳定性和适应性。

🎯 应用场景

该研究的潜在应用领域包括机器人控制、自动驾驶、以及任何需要实时决策的动态系统。通过提升MPC的效率和鲁棒性，WASP导数的应用可以显著改善复杂环境下的控制策略，推动智能系统的实际应用和发展。

📄 摘要（原文）

MuJoCo is a powerful and efficient physics simulator widely used in robotics. One common way it is applied in practice is through Model Predictive Control (MPC), which uses repeated rollouts of the simulator to optimize future actions and generate responsive control policies in real time. To make this process more accessible, the open source library MuJoCo MPC (MJPC) provides ready-to-use MPC algorithms and implementations built directly on top of the MuJoCo simulator. However, MJPC relies on finite differencing (FD) to compute derivatives through the underlying MuJoCo simulator, which is often a key bottleneck that can make it prohibitively costly for time-sensitive tasks, especially in high-DOF systems or complex scenes. In this paper, we introduce the use of Web of Affine Spaces (WASP) derivatives within MJPC as a drop-in replacement for FD. WASP is a recently developed approach for efficiently computing sequences of accurate derivative approximations. By reusing information from prior, related derivative calculations, WASP accelerates and stabilizes the computation of new derivatives, making it especially well suited for MPC's iterative, fine-grained updates over time. We evaluate WASP across a diverse suite of MJPC tasks spanning multiple robot embodiments. Our results suggest that WASP derivatives are particularly effective in MJPC: it integrates seamlessly across tasks, delivers consistently robust performance, and achieves up to a 2$\mathsf{x}$ speedup compared to an FD backend when used with derivative-based planners, such as iLQG. In addition, WASP-based MPC outperforms MJPC's stochastic sampling-based planners on our evaluation tasks, offering both greater efficiency and reliability. To support adoption and future research, we release an open-source implementation of MJPC with WASP derivatives fully integrated.