无需重训练即可快速适配新系统的控制方法
Zero-Shot Function Encoder-Based Differentiable Predictive Control
- 用函数编码器神经微分方程建模系统动态
- 在多种参数化系统上实现高精度零样本控制
- 适合需要快速适应的机器人与自动化场景
我们提出一种可微分框架，用于参数化非线性动力系统上的零样本自适应控制。该方法结合基于函数编码器的神经微分方程（FE-NODE）建模系统动态，以及可微分预测控制（DPC）进行离线自监督学习显式控制策略。FE-NODE 能捕捉状态转移中的非线性特性，并实现无需重训练的零样本适配；DPC 则高效学习跨系统参数化的控制策略，避免了经典模型预测控制中常见的昂贵在线优化。我们在多种具有不同参数场景的非线性系统上验证了该方法的效率、准确性和在线适应能力，表明其具备作为通用快速零样本自适应控制工具的潜力。
原文摘要 · Abstract (English)
We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neural ODE (FE-NODE) for modeling system dynamics with a differentiable predictive control (DPC) for offline self-supervised learning of explicit control policies. The FE-NODE captures nonlinear behaviors in state transitions and enables zero-shot adaptation to new systems without retraining, while the DPC efficiently learns control policies across system parameterizations, thus eliminating costly online optimization common in classical model predictive control. We demonstrate the efficiency, accuracy, and online adaptability of the proposed method across a range of nonlinear systems with varying parametric scenarios, highlighting its potential as a general-purpose tool for fast zero-shot adaptive control.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。