Unified Meta-Representation and Feedback Calibration for General Disturbance Estimation

2026-01-06

arXiv.org

AI Summary

This work addresses the degradation in control accuracy caused by unknown, time-varying, unstructured disturbances in modern robotic systems by proposing a general disturbance estimation framework based on meta-learning and state-feedback calibration. The approach extracts features from observations within a finite-time window to construct a unified meta-representation that requires no prior structural assumptions, and integrates an online state-feedback mechanism to calibrate learning residuals, enabling accurate estimation of diverse rapidly varying disturbances. Theoretical analysis establishes the synchronous convergence of online learning error and disturbance estimation error. Experimental validation on a quadrotor platform demonstrates the method’s effectiveness and robustness in handling unstructured disturbances and distribution shifts.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Precise control in modern robotic applications is always an open issue due to unknown time-varying disturbances. Existing meta-learning-based approaches require a shared representation of environmental structures, which lack flexibility for realistic non-structural disturbances. Besides, representation error and the distribution shifts can lead to heavy degradation in prediction accuracy. This work presents a generalizable disturbance estimation framework that builds on meta-learning and feedback-calibrated online adaptation. By extracting features from a finite time window of past observations, a unified representation that effectively captures general non-structural disturbances can be learned without predefined structural assumptions. The online adaptation process is subsequently calibrated by a state-feedback mechanism to attenuate the learning residual originating from the representation and generalizability limitations. Theoretical analysis shows that simultaneous convergence of both the online learning error and the disturbance estimation error can be achieved. Through the unified meta-representation, our framework effectively estimates multiple rapidly changing disturbances, as demonstrated by quadrotor flight experiments. See the project page for video, supplementary material and code: https://nonstructural-metalearn.github.io.

Problem

• disturbance estimation
• non-structural disturbances
• meta-learning
• representation error
• distribution shift

Innovation

• unified meta-representation
• feedback calibration
• non-structural disturbance estimation
• online adaptation
• meta-learning