arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.07173cs.LGcs.SYeess.SY
收藏

在上下文中学习非线性系统:从合成数据到现实世界的运动控制

Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control

Tong Jian, Tianyu Dai, Tao Yu

AI总结:

本文提出基于变压器模型的上下文学习方法,用于现实世界中的运动控制,通过少量示例实现对非线性系统的高效泛化,优于传统控制方法。

摘要:

大型语言模型(LLMs)已显示出强大的上下文学习(ICL)能力,但尚未扩展到信号处理系统。受其设计启发,我们首次提出了一种基于变压器模型的ICL方法,适用于运动前馈控制,这是一个关键任务,在此任务中传统PI方法和基于物理的方法在处理非线性和复杂负载条件时存在困难。我们提出了一种基于变压器的模型架构,将信号表示与系统行为分离,从而实现少量样本微调和单样本ICL。在大量合成线性和非线性系统数据上预训练后,模型仅通过少量示例即可泛化到未见过的实际电机动态。在实验中,我们的方法在多种电机负载配置上泛化,将未调优的示例转换为准确的前馈预测,并优于PI控制器和基于物理的前馈基线。这些结果表明,ICL可以连接合成预训练和现实世界的适应性,为物理系统的数据高效控制开辟了新方向。

英文摘要:

LLMs have shown strong in-context learning (ICL) abilities, but have not yet been extended to signal processing systems. Inspired by their design, we have proposed for the first time ICL using transformer models applicable to motor feedforward control, a critical task where classical PI and physics-based methods struggle with nonlinearities and complex load conditions. We propose a transformer based model architecture that separates signal representation from system behavior, enabling both few-shot finetuning and one-shot ICL. Pretrained on a large corpus of synthetic linear and nonlinear systems, the model learns to generalize to unseen system dynamics of real-world motors only with a handful of examples. In experiments, our approach generalizes across multiple motor load configurations, transforms untuned examples into accurate feedforward predictions, and outperforms PI controllers and physics-based feedforward baselines. These results demonstrate that ICL can bridge synthetic pretraining and real-world adaptability, opening new directions for data efficient control of physical systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑