Adaptive Flight Control Law Based on Neural Networks and Dynamic Inversion for Unmanned Aerial Vehicle

Author(s):  
Yang Ning ◽  
Wu Liao-ni ◽  
Lin Qi
2021 ◽  
Vol 6 (2) ◽  
pp. 2044-2051
Author(s):  
Danial Sufiyan ◽  
Luke Soe Thura Win ◽  
Shane Kyi Hla Win ◽  
Gim Song Soh ◽  
Shaohui Foong

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4115 ◽  
Author(s):  
Yuxia Li ◽  
Bo Peng ◽  
Lei He ◽  
Kunlong Fan ◽  
Zhenxu Li ◽  
...  

Roads are vital components of infrastructure, the extraction of which has become a topic of significant interest in the field of remote sensing. Because deep learning has been a popular method in image processing and information extraction, researchers have paid more attention to extracting road using neural networks. This article proposes the improvement of neural networks to extract roads from Unmanned Aerial Vehicle (UAV) remote sensing images. D-Linknet was first considered for its high performance; however, the huge scale of the net reduced computational efficiency. With a focus on the low computational efficiency problem of the popular D-LinkNet, this article made some improvements: (1) Replace the initial block with a stem block. (2) Rebuild the entire network based on ResNet units with a new structure, allowing for the construction of an improved neural network D-Linknetplus. (3) Add a 1 × 1 convolution layer before DBlock to reduce the input feature maps, reducing parameters and improving computational efficiency. Add another 1 × 1 convolution layer after DBlock to recover the required number of output channels. Accordingly, another improved neural network B-D-LinknetPlus was built. Comparisons were performed between the neural nets, and the verification were made with the Massachusetts Roads Dataset. The results show improved neural networks are helpful in reducing the network size and developing the precision needed for road extraction.


2020 ◽  
Vol 10 (4) ◽  
pp. 1300 ◽  
Author(s):  
Xin Zhao ◽  
Zhou Zhou ◽  
Xiaoping Zhu ◽  
An Guo

This paper describes our work on a small, hand-launched, solar-powered unmanned aerial vehicle (UAV) suitable for low temperatures and high altitudes, which has the perpetual flight potential for conservation missions for rare animals in the plateau area in winter. Firstly, the conceptual design method of a small, solar-powered UAV based on energy balance is proposed, which is suitable for flight in high-altitude and low-temperature area. The solar irradiance model, which can reflect the geographical location and time, was used. Based on the low-temperature discharge test of the battery, a battery weight model considering the influence of low temperature on the battery performance was proposed. Secondly, this paper introduces the detailed design of solar UAV for plateau area, including layout design, structure design, load, and avionics. To increase the proportion of solar cells covered, the ailerons were removed and a rudder was used to control both roll and yaw. Then, the dynamics model of an aileron-free layout UAV was developed, and the differences in maneuverability and stability of aileron-free UAV in plateau and plain areas were analyzed. The control law and trajectory tracking control law were designed for the aileron-free UAV. Finally, the flight test was conducted in Qiangtang, Tibet, at an altitude of 4500 m, China’s first solar-powered UAV to take off and land above 4500 m on the plateau in winter (−30 °C). The test data showed the success of the scheme, validated the conceptual design method and the success of the control system for aileron-free UAV, and analyzed the feasibility of perpetual flight carrying different loads according to the flight energy consumption data.


Sign in / Sign up

Export Citation Format

Share Document