Learning-based quadrotor tracking control using Recursive Gaussian Processes
Abstract
Abstract High-performance trajectory tracking for Unmanned Aerial Vehicles is one of the main interests of the aerospace and control community, since classical model-based controllers are susceptible to performance degradation in the presence of unmodeled effects (e.g., wind disturbances) or unmodeled dynamics (e.g., aerodynamic effects). In this context, many researchers resort to learning-based controllers, where classical controllers are integrated with machine learning techniques, improving model accuracy and tracking performance. However, the application of these controllers is currently limited to simulations or offline implementations, due to the computational limitations of UAVs. Moreover, formal stability guarantees for these controllers remain an open challenge. In this paper, a controller is proposed in which a Recursive Gaussian Process, a Bayesian model integrated with a sparsity technique that reduces the computational complexity of the algorithm, compensates online for the nonlinear dynamics left uncanceled by a Feedback Linearization controller, with a novel Kalman-filter-based tuning algorithm specifically designed for this purpose. The entire RGP pipeline is implemented directly onboard the drone and validated for single-axis horizontal position control through an experimental campaign on a real quadrotor (the ANT-X Lab drone). Tested on various types of sinusoidal reference signals, both repetitive and non-repetitive, in an indoor environment, the proposed…
Read the paper
Related studies
- eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses
- Online Survival Analysis Software to Assess the Prognostic Value of Biomarkers Using Transcriptomic Data in Non-Small-Cell Lung Cancer
- OptiType: precision HLA typing from next-generation sequencing data
- Nicotinic Cholinergic System and COVID-19: In Silico Identification of an Interaction between SARS-CoV-2 and Nicotinic Receptors with Potential Therapeutic Targeting Implications
- Saccharomyces cerevisiae cells have three Omega class glutathione S-transferases acting as 1-Cys thiol transferases
- Hemolysis at low blood flow rates: in-vitro and in-silico evaluation of a centrifugal blood pump
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.