NeFut Logo NeFut
Admin Login

[CS.AI] Generalist AI Control: Towards Multi-purpose Adaptive Algorithms

Published at: 2026-07-21 22:00 Last updated: 2026-07-22 01:01
#algorithm #AI #Machine Learning

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.

Original Source: https://arxiv.org/abs/2607.16313

[h] Back to Home