论文/arXiv 2610.04609·25 天前

在类人机器人移动操作的上下文参数学习中利用分层控制器结构

针对分层控制跨层参数耦合难调问题，提出上下文贝叶斯优化，并在变质量物理推箱的类人移动操作中验证。

AI 整理

• 本体 SDK 与控制

原文链接：Exploiting Hierarchical Controller Structure in Contextual Parameter Learning for Humanoid Loco-Manipulation（arXiv 2610.04609 · 发布日期：2026-10-03）

Exploiting Hierarchical Controller Structure in Contextual Parameter Learning for Humanoid Loco-Manipulation

针对分层控制跨层参数耦合难调问题，提出上下文贝叶斯优化，并在变质量物理推箱的类人移动操作中验证。

核心要点

• 分层控制需协调规划、全身运动与底层控制，独立调参可能忽略跨层交互。
• 框架联合学习层级参数，保留任务表现、实现质量和控制代价的分量观测。
• 用相关多输出高斯过程建模各性能分量，并解析评估其聚合闭环目标。
• 在联合调节质心预测控制器和全身控制器时，训练与适应的平均经验遗憾最低。

验证范围与局限：验证范围为类人机器人移动操作中的物理推箱任务，并考虑不同箱体质量。

英文摘要 (Abstract)

Hierarchical control architectures are widely used to decompose complex control problems into interacting control levels and are particularly important in robotics, where planning, whole-body motion, and lower-level control must be coordinated across different levels of abstraction and time scales. Their overall closed-loop performance, however, depends strongly on parameters distributed across the hierarchy, such that tuning controllers on different levels independently may neglect relevant cross-layer interactions. We propose a contextual Bayesian optimization framework for joint parameter learning in hierarchical control systems. Rather than modeling closed-loop performance only as a scalar black-box function, we retain separate observations of task performance, realization quality, and control effort. A correlated multi-output Gaussian process models these performance components, while their known aggregation into the overall closed-loop objective is evaluated analytically. The formulation exploits three complementary consequences of hierarchical control: informative performance quantities exposed by the hierarchy, coupling between parameters of different controller levels, and variations of these relations with operating conditions. We evaluate the approach for humanoid loco-manipulation, jointly tuning a centroidal predictive controller and a whole-body controller for physical box pushing under varying box mass. The proposed method achieves the lowest mean empirical regret during both training and adaptation among the considered baselines.

作者：Sebastian Hirt, Lukas Theiner, Jan Peters, Rolf Findeisen

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.04609：Exploiting Hierarchical Controller Structure in Contextual Parameter Learning for Humanoid Loco-Manipulation访问 2026-10-21