Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control
This work addresses data-efficient control of physical systems, offering a novel approach for motor control under nonlinearities and complex loads, though it is incremental in extending in-context learning to a new domain.
The paper tackles the problem of applying in-context learning to signal processing for motor feedforward control, where it outperforms PI controllers and physics-based baselines by generalizing from synthetic data to real-world motors with few examples.
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.