analiza aiqbench
This research presents a hybrid modeling framework that merges physics-based Prediction Error Methods with Gaussian Processes to address nonlinear dynamics and uncertainty in quadcopter control. By separating known physical structures from unmodeled residuals, the approach achieves LSTM-level prediction accuracy while providing calibrated uncertainty estimates crucial for safe autonomous operation. The work advances system identification by bridging interpretability with data-driven flexibility specifically for aerial robotics applications.
A Hybrid PEM-GP Framework for Uncertainty-Aware System Identification of Quadcopters
arXiv:2608.30433v1 Announce Type: new Abstract: Accurate dynamic models play a central role in achieving reliable control of quadcopters. Classical system identification methods remain widely used, mainly because of their interpretability. However, they often fail to capture important nonlinear effects, especially in small-scale aerial platforms where such effects become more pronounced. Data-driven approaches offer a different perspective. They can represent complex nonlinear dynamics more effectively, but this comes at the cost of reduced interpretability and the absence of well-calibrated uncertainty estimates. In this work, we propose a framework that combines physics-based modeling with data-driven learning, while explicitly accounting for uncertainty. A physics-based model is first identified using the Prediction Error Method (PEM), which captures the main structure of the system. The remaining dynamics are then modeled using a Gaussian Process (GP), allowing the residual behavior to be learned directly from data. This separation makes it possible to distinguish between known physical effects and unmodeled dynamics. The proposed framework is validated on a Duckiedrone-like experimental setup. The results show that the PEM-GP model achieves prediction accuracy comparable to that of a Long Short-Term Memory (LSTM) network, while additionally providing calibrated uncertainty estimates. This combination improves model reliability and supports uncertainty-aware decision-making.
Abstract:Accurate dynamic models play a central role in achieving reliable control of quadcopters. Classical system identification methods remain widely used, mainly because of their interpretability. However, they often fail to capture important nonlinear effects, especially in small-scale aerial platforms where such effects become more pronounced. Data-driven approaches offer a different perspective. They can represent complex nonlinear dynamics more effectively, but this comes at the cost of reduced interpretability and the absence of well-calibrated uncertainty estimates. In this work, we propose a framework that combines physics-based modeling with data-driven learning, while explicitly accounting for uncertainty. A physics-based model is first identified using the Prediction Error Method (PEM), which captures the main structure of the system. The remaining dynamics are then modeled using a Gaussian Process (GP), allowing the residual behavior to be learned directly from data. This separation makes it possible to distinguish between known physical effects and unmodeled dynamics. The proposed framework is validated on a Duckiedrone-like experimental setup. The results show that the PEM-GP model achieves prediction accuracy comparable to that of a Long Short-Term Memory (LSTM) network, while additionally providing calibrated uncertainty estimates. This combination improves model reliability and supports uncertainty-aware decision-making.
19 pages, 7 figures. Published in International Journal of Control, Automation, and Systems, Vol. 24, No. 8, pp. 2047-2057, 2026
Robotics (cs.RO)
arXiv:2608.30433 [cs.RO]
(or arXiv:2608.30433v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.30433 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
International Journal of Control, Automation, and Systems, Vol. 24, No. 8, pp. 2047-2057, 2026
https://doi.org/10.1007/s12555-026-00123-5 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 · 331 cuvinte
Subiecte conexe
PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems
arXiv · 22 sept. 2026
A Multi-Agent System for IPMSM Design Optimization via an FEA-AI Hybrid Approach
arXiv · 9 iun. 2026
In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
arXiv · 12 oct. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026