analiza aiqbench
This research introduces a novel generalist controller that leverages attention mechanisms and mixture-of-experts architectures to manage diverse dynamical systems with varying orders without architectural changes. By training on hundreds of thousands of demonstrations across linear, nonlinear, stable, and unstable scenarios—from aerospace vehicles to chemical processes—the model achieves performance comparable to traditional system-specific controllers while adapting to unseen disturbances like actuator saturation. This advancement marks a significant step toward scalable, multi-purpose adaptive control policies that eliminate the need for extensive per-system tuning in complex engineering applications.
Generalist AI Control: Towards Multi-purpose Adaptive Algorithms
arXiv:2607.16313v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Robotics (cs.RO); Systems and Control (eess.SY)
arXiv:2607.16313 [cs.AI]
(or arXiv:2607.16313v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.16313 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1016/j.conengprac.2026.106915 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 319 cuvinte
Subiecte conexe
2026 BAIR Graduate Showcase
BAIR Blog · 1 iul. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Game-Theoretic Disempowerment: Loss of Control to Agencyless AI
LessWrong · 27 sept. 2026
AI and Quantum Computing Briefing
livetradingnews.com · 4 aug. 2026