通用人工智能控制：迈向多用途自适应算法
Generalist AI Control: Towards Multi-purpose Adaptive Algorithms
- University of Hertfordshire（赫特福德大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对传统控制器不能跨系统转换的问题，提出通用控制器。通过带掩码注意力机制等方法，使其能处理不同维度系统。经多系统演示学习跨系统控制策略，仿真显示其性能佳且可推广到未见过的运行条件，迈向通用控制策略。
AI中文摘要：
传统控制器是为特定系统设计的，无法在不同系统阶次和动态特性之间转换。我们提出了一种通用控制器，这是一种基于学习的控制器，能够控制不同阶次和动态特性的系统。该方法引入了一种使用带掩码注意力机制的新颖动态状态空间表示，通过为每个系统分配一个系统标签，使单个经过一次性训练的神经网络能够在不修改架构的情况下处理不同维度的系统。我们从25个不同系统生成了314,630个演示，涵盖稳定、不稳定、最小相位和非最小相位动态特性，包括从自主水下和航空航天飞行器到机械系统和化学过程的线性和非线性系统。该模型通过多尺度时间处理和专家混合架构学习跨系统控制策略。仿真结果表明，所提出的通用控制器在所有测试系统中都能达到与特定系统的LQI控制器相当的性能，包括非最小相位和不稳定动态特性等具有挑战性的情况，同时还能推广到未见过的运行条件，如执行器饱和、噪声、干扰和训练期间未遇到的参考轨迹。这项工作朝着在定义的动态系统家族中实现通用控制策略迈出了重要一步，展示了使用单一学习策略对一系列不同阶次和动态特性的单输入单输出（SISO）系统进行有效控制，而无需特定系统调整。
英文摘要：
Traditional controllers are designed for specific systems and do not transfer across different system orders and dynamics. We present a Generalist Controller, a learning-based controller capable of controlling systems of varying orders and dynamics. The approach introduces a novel dynamic state-space representation using attention mechanisms with masking, enabling a single neural network, trained in one shot, to handle systems with different dimensions without architectural modifications by assigning a system tag to each system. We generated 314,630 demonstrations from 25 diverse systems, including stable, unstable, minimum-phase, and non-minimum-phase dynamics, spanning linear and nonlinear systems from autonomous underwater and aerospace vehicles to mechanical systems and chemical processes. The model learns cross-system control strategies through multi-scale temporal processing and a mixture-of-experts architecture. Simulation results demonstrate that the proposed generalist controller achieves comparable performance to system-specific LQI controllers across all tested systems, including challenging cases such as non-minimum-phase and unstable dynamics, whilst generalising to unseen operating conditions including actuator saturation, noise, disturbance, and reference trajectories not encountered during training. This work represents a significant step towards generalist control policies within a defined family of dynamical systems, demonstrating effective control across a range of single-input single-output (SISO) systems of varying order and dynamics using a single learned policy without system-specific tuning.
