Abstract
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.
Blogger's Review: This paper showcases the robust potential of the generalist controller to achieve efficient control across diverse systems, marking a significant advancement in control theory. The key to this technology lies in its flexibility and adaptability, capable of addressing varying dynamic characteristics and external disturbances, promising substantial practical applications.