Learning-based method for controlling unmanned aerial vehicle to complete trajectory tracking under wind disturbance

A trajectory tracking and unmanned aerial vehicle technology, applied in three-dimensional position/channel control, mechanical equipment, combustion engine, etc., can solve problems such as inability to achieve results, poor trajectory tracking accuracy, etc., to maintain fidelity, ensure real-time, The effect of improving efficiency

Pending Publication Date: 2022-04-15
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

He considers the most stringent constraints, a strategy that maintains good constraints but performs relatively poorly in trajectory tracking accuracy due to its conservative nature
Recent methods use the confidence theor

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Learning-based method for controlling unmanned aerial vehicle to complete trajectory tracking under wind disturbance
  • Learning-based method for controlling unmanned aerial vehicle to complete trajectory tracking under wind disturbance
  • Learning-based method for controlling unmanned aerial vehicle to complete trajectory tracking under wind disturbance

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0070] Example 1:

[0071] Such as figure 1 As shown, a method based on learning-based control drones complete trajectory tracking under the wind, including the following steps:

[0072] Step 1. Enter the reference trajectory and the drone state, based on the priori model predictive control, optimize the corrected reference trajectory and the reference control amount.

[0073] Enter the reference track x, d, enter the current state X of the drone; consider a nonlinear affine model

[0074] Convert the drone system into this form; linearize it to obtain a linear model, and establish a model predictive control on this basis, that is, at each sampling time t k = T 0 + K × D t , T 0 For the current time, k is the number of predictive steps, DT is the control interval, solve a limited time domain optimal control problem, as follows:

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] U 1 (t) ∈U

[0081] in For prediction, the target function J is as follows:

[0082]

...

Example Embodiment

[0128] Example 2

[0129] This embodiment provides an electronic device comprising: a memory, a processor, and a computer program stored on a memory and can perform the computer program on the processor, the processor performs the computer program, and implements the learning-based learning according to Example 1. Controling the method of completing trajectory tracking under the wind.

Example Embodiment

[0130] Example 3

[0131] This embodiment provides a computer readable storage medium, which stores a computer program, which is executed by the processor, and the learning-based control drone according to Embodiment 1 is implemented under the wind. Tracking method.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of unmanned aerial vehicle control, in particular to a learning-based method for controlling an unmanned aerial vehicle to complete trajectory tracking under wind disturbance. A Gaussian process model is directly used for compensating wind disturbance, so that the tracking precision is improved; and on the other hand, when the stability and safety constraints are ensured, the Gaussian process prediction error upper bound is utilized to ensure the construction of a high-probability constraint guarantee, and the fidelity of the model can be maintained. And errors are not considered in model prediction control, so that the initiative is maximized, and the tracking precision is further improved. In addition, the complexity of the algorithm is optimized from the structure of the algorithm and model updating, the efficiency of the algorithm is improved, and the real-time performance of the control algorithm is ensured.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle control, and more specifically, relates to a learning-based method for controlling an unmanned aerial vehicle to complete trajectory tracking under wind disturbance. Background technique [0002] UAVs are widely used in many fields to solve complex tasks, including agricultural irrigation, disaster relief, police and military, etc. In many scenarios, drones need to track trajectories accurately in order to complete their tasks. Inaccurate tracking may prevent the mission from being completed or even lead to serious accidents. Therefore, accurate tracking performance is a basic requirement for UAV tracking tasks. Additionally, safety is of paramount importance for dynamic control systems. Violation of safety constraints will not only cause harm to the drone itself, but also to humans in many scenarios. Due to inaccurate tracking caused by wind disturbance, the drone will deviate...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G05D1/10
CPCY02T10/40
Inventor 吴挚旋成慧
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap