analiza aiqbench
This research introduces Continual Uncertainty Learning (CUL), a framework that decomposes complex control problems into sequential tasks to efficiently handle multiple, heterogeneous uncertainties in nonlinear systems. By combining curriculum-based learning with anti-forgetting regularization and model-based baselines, the method significantly improves sample efficiency while preserving performance across diverse operating conditions. The approach is validated on an active vibration controller for automotive powertrains, demonstrating robustness against structural nonlinearities and dynamic variations.
Continual Uncertainty Learning for Robust Control of Nonlinear Systems with Multiple Heterogeneous Uncertainties
arXiv:2602.17174v3 Announce Type: replace-cross Abstract: Robust control of mechanical systems with multiple uncertainties remains a fundamental challenge, particularly when nonlinear dynamics and operating-condition variations are intricately intertwined. Although deep reinforcement learning combined with domain randomization has shown promise in mitigating the sim-to-real gap, simultaneously handling all the sources of uncertainty often leads to sub-optimal policies and poor learning efficiency. This study proposes continual uncertainty learning (CUL), a curriculum-based continual learning framework for robust control of nonlinear systems on which multiple heterogeneous uncertainties are simultaneously superimposed. The core idea is to decompose the original control problem into a sequence of continual learning tasks by extending the system into a set of plants whose uncertainties are progressively expanded and diversified, so that the strategy for handling each uncertainty is acquired sequentially. Within this curriculum, the policy is updated across the plant sets under a memory-efficient anti-forgetting regularization, which preserves the strategies acquired for earlier uncertainties. In parallel, a model-based controller that guarantees a shared baseline performance across all the plant sets is embedded in the learning process, so that the agent learns only the residual compensation for each uncertainty, thereby substantially enhancing sample efficiency. The proposed framework is applied to the design of an active vibration controller for automotive powertrains as a practical industrial application. Comparative validation demonstrates that the resulting controller remains robust against structural nonlinearities and dynamic variations over a wide range of plant conditions while improving the control performance.
Abstract:Robust control of mechanical systems with multiple uncertainties remains a fundamental challenge, particularly when nonlinear dynamics and operating-condition variations are intricately intertwined. Although deep reinforcement learning combined with domain randomization has shown promise in mitigating the sim-to-real gap, simultaneously handling all the sources of uncertainty often leads to sub-optimal policies and poor learning efficiency. This study proposes continual uncertainty learning (CUL), a curriculum-based continual learning framework for robust control of nonlinear systems on which multiple heterogeneous uncertainties are simultaneously superimposed. The core idea is to decompose the original control problem into a sequence of continual learning tasks by extending the system into a set of plants whose uncertainties are progressively expanded and diversified, so that the strategy for handling each uncertainty is acquired sequentially. Within this curriculum, the policy is updated across the plant sets under a memory-efficient anti-forgetting regularization, which preserves the strategies acquired for earlier uncertainties. In parallel, a model-based controller that guarantees a shared baseline performance across all the plant sets is embedded in the learning process, so that the agent learns only the residual compensation for each uncertainty, thereby substantially enhancing sample efficiency. The proposed framework is applied to the design of an active vibration controller for automotive powertrains as a practical industrial application. Comparative validation demonstrates that the resulting controller remains robust against structural nonlinearities and dynamic variations over a wide range of plant conditions while improving the control performance.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
arXiv:2602.17174 [cs.LG]
(or arXiv:2602.17174v3 [cs.LG] for this version)
From: Heisei Yonezawa Dr. [view email] [v1] Thu, 19 Feb 2026 08:39:42 UTC (1,853 KB) [v2] Tue, 10 Mar 2026 11:26:16 UTC (1,858 KB) [v3] Sun, 23 Aug 2026 16:29:34 UTC (1,998 KB)
Text integral sub licența deschisă a publicației · 286 cuvinte
Subiecte conexe
SACK: Safe Active Continual Koopman Learning for Uncertain Systems with Contractive Guarantees
arXiv · 6 aug. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Continual learning might make your blocking monitors nearly useless
AI Alignment Forum · 24 sept. 2026