Adaptive Multimodal Servoing Control for Unmanned Aerial Manipulator Perching
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Dear Editor, This letter presents an adaptive control framework for unmanned aerial manipulator (UAM) perching, integrating image segmentation-based tracking with multimodal nonlinear model predictive control (NMPC). A hybrid control strategy with depth derivative prediction and pitch feedforward compensation effectively resolves control parameter conflicts between pole grasping and suction-based perching on planar surfaces. An autonomous switching mechanism, leveraging detection confidence, spatial fusion, and pixel-level feature enhancement, ensures accurate target pose estimation under dynamic occlusions. Moreover, a multimodal NMPC framework with phased weight adaptation optimizes energy efficiency, trajectory tracking precision, and contact compliance across distinct flight phases.
Fields of Study & Subjects
Aerospace Engineering and Control Systems
Adaptive Control of Nonlinear Systems
Robot Manipulation and Learning
Publication details
- Journal / source
- IEEE/CAA Journal of Automatica Sinica
- Volume
- 13
- Issue
- 3
- Pages
- 731–733
- Publication date
- 1 March 2026
- Language
- EN