基于原语信息的采样型模型预测控制用于多指灵巧操作

中文摘要 AI 辅助

我们提出了一种基于原语信息的采样型模型预测控制（MPC）框架，用于多指灵巧操作。采样型MPC避免了通过复杂接触动力学求梯度的需求，但直接在高维关节空间中进行探索效率低下，且使性能强烈依赖于采样分布。我们的框架利用编码协调手指运动的低维操作原语来偏置采样，同时优化关节级残差以适应当前手-物体配置。任务相关的滚动约束在前向仿真过程中拒绝不可行轨迹，从而提高了采样预算的有效利用。我们在物理Allegro手上使用同步的MuJoCo数字孪生评估了该方法。消融实验表明，原语和残差对于可靠的连续手中旋转都是必需的；仅增加采样预算无法恢复这种协调性，而滚动约束显著提高了成功率。从单个物体提取的原语在物体尺寸变化和模型失配情况下仍然有效，该框架还支持抓取、物体重新定向以及协调的手臂-手-到达-抓取-搬运，使用的原语可从仿真训练的策略和人类手部运动数据中提取。

英文摘要

We present a primitive-informed sampling-based model predictive control (MPC) framework for multi-fingered dexterous manipulation. Sampling-based MPC evaluates candidate control trajectories through forward simulation without requiring gradients through complex contact dynamics. However, directly sampling these trajectories in the high-dimensional joint space of a dexterous hand is inefficient and makes performance strongly dependent on the sampling distribution. Our framework biases sampling using low-dimensional manipulation primitives that encode coordinated finger motions, while simultaneously optimizing joint-level residuals to adapt these motions to the current hand-object configuration. Task-related rollout constraints reject infeasible trajectories during forward simulation, improving the effective use of the sampling budget. We evaluate the approach on a 16 DoF Allegro hand using a synchronized MuJoCo digital twin. Ablations show that both the primitive and residual are necessary for reliable continuous in-hand rotation, that increasing the sampling budget alone does not recover this coordination, and that rollout constraints substantially improve success rate. A primitive extracted for one object size transfers to other sizes and remains effective under model mismatch. The framework further supports grasping, object reorientation, and coordinated arm-hand manipulation, using primitives extracted from both a simulation-trained policy and human hand-motion data.

发表机构

• Honda Research Institute USA（本田美国研究院）
• Georgia Institute of Technology（佐治亚理工学院）
• Skild AI

机构由 AI 辅助整理，请以论文原文为准。