Neural Feedforward and Residual Disturbance Observation for Multi-UAV Formation Tracking: A Simulation Study Under Aerodynamic Model Mismatch

Close-proximity quadrotor formations require disturbance compensation, but learned feedforward can have observer-dependent value. We examined a retrained neural force prior with zero ambient-wind inputs through complementary-filter analysis and a complete prior-observer-robust factorial. Five training seeds used grouped synthetic data, while independent tuning and 50 paired evaluation seeds separated component increments from tuned-method comparisons. Each comparison regime contained 5400 entries across six scenarios, with complete-period, gust/recovery, and peak error assessed jointly. The neural prior reduced period error by 0.13–0.98 mm in five complete matched families, but slightly increased peaks in three. Failed executions prevented complete-family inference for combined stress. Public two-vehicle records supplied a separate source-platform load-shape check with held-out recordings.

Authors

Institutions

Publication Details

Journal
Drones
Published
2026-11-19
DOI
https://doi.org/10.3390/drones10110868
Primary Topic
Adaptive Control of Nonlinear Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Neural Feedforward and Residual Disturbance Observation for Multi-UAV Formation Tracking: A Simulation Study Under Aerodynamic Model Mismatch

Xiaoguang Xu, Haibo Zhou, Qinqiang Sun, Yang Yang
Drones
Adaptive Control of Nonlinear Systems
article

Neural Feedforward and Residual Disturbance Observation for Multi-UAV Formation Tracking: A Simulation Study Under Aerodynamic Model Mismatch

Xiaoguang Xu, Haibo Zhou, Qinqiang Sun, Yang Yang
article en

Abstract

Close-proximity quadrotor formations require disturbance compensation, but learned feedforward can have observer-dependent value. We examined a retrained neural force prior with zero ambient-wind inputs through complementary-filter analysis and a complete prior-observer-robust factorial. Five training seeds used grouped synthetic data, while independent tuning and 50 paired evaluation seeds separated component increments from tuned-method comparisons. Each comparison regime contained 5400 entries across six scenarios, with complete-period, gust/recovery, and peak error assessed jointly. The neural prior reduced period error by 0.13–0.98 mm in five complete matched families, but slightly increased peaks in three. Failed executions prevented complete-family inference for combined stress. Public two-vehicle records supplied a separate source-platform load-shape check with held-out recordings.

DronesVol. 10(11)
Changchun University of Science and Technology (CN)
Adaptive Control of Nonlinear Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon