arrow
返回

Neural Enhanced Control for Quadrotor Linear Behavior Fitting

delete2022-06-21
delete2
delete
OA
AI
E
Estéban Carvalho *
P
Pierre Susbielle
A
Ahmad Hably
J
Jilles Dibangoye
N
Nicolas Marchand
DOI:10.1109/ICUAS54217.2022.9836058delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Designing an efficient autopilot for quadrotor can be a very long and tedious process. This comes from the complex nonlinear dynamics that rule the flying robot behavior as battery discharge, blade flapping, gyroscopic effect, frictions, etc. In this paper we propose to use a traditional cascaded control architecture enhanced with Deep Neural Network (DNN). The idea is to easily setup a control algorithm using linear cascaded laws and then correct unmodelled dynamics and approximations made during the linear control design with the DNN. The tuning process is reduced to choice of proportional and derivative gains of each control loop. The approach is tested in the ROS/Gazebo simulation environment and experimentally in a motion capture room. Results confirm that the methodology significantly improves the performance of linear approaches on nonlinear quadrotor system.
Keyword:
TRACKING

期刊

I
International Conference on Unmanned Aircraft Systems
IF:
0
论文数:
48
被引数:
0

机构

I
institut national polytechnique de grenoble
学者数:
6.7K
论文数: 5.2K
被引数: 1
C
communaute universite grenoble alpes
学者数:
3.5W
论文数: 2.7W
被引数: 29
引用论文

引用论文

Pharmacokinetics of subcutaneous recombinant human granulocyte colony- stimulating factor in children
err1992-06-01
err0
errOAAI
errN Stute; VM Santana; JH Rodman; MJ Schell; JN Ihle; WE Evans
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
Saccades as Related to Reading Disorders
err1974-05-01
err0
PREAI
errDonald C. Griffin; Howard N. Walton; Vera Ives
err分享
err收藏
err分享
err收藏
学者 查看更多内容