Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs
Thanks to their hovering and vertical take-off and landing abilities, quadrotor unmanned aerial vehicles (UAVs) are receiving a great deal of attention. With the diversified development of the functions of UAVs, the requirements for flight performance with higher stability and maneuverability are in...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/15/2686 |
| _version_ | 1797413097185476608 |
|---|---|
| author | Kai Zhao Jia Song Yunlong Hu Xiaowei Xu Yang Liu |
| author_facet | Kai Zhao Jia Song Yunlong Hu Xiaowei Xu Yang Liu |
| author_sort | Kai Zhao |
| collection | DOAJ |
| description | Thanks to their hovering and vertical take-off and landing abilities, quadrotor unmanned aerial vehicles (UAVs) are receiving a great deal of attention. With the diversified development of the functions of UAVs, the requirements for flight performance with higher stability and maneuverability are increasing. Aiming at parameter uncertainty and external disturbance, a deep deterministic policy gradient-based active disturbance rejection controller (DDPG-ADRC) is proposed. The total disturbances can be compensated dynamically by adjusting the controller bandwidth and the estimation of system parameters online. The tradeoff between anti-interference and rapidity can be better realized in this way compared with the traditional ADRC. The process of parameter tuning is demonstrated through the simulation results of tracking step instruction and sine sweep under ideal and disturbance conditions. Further analysis shows the proposed DDPG-ADRC has better performance. |
| first_indexed | 2024-03-09T05:12:37Z |
| format | Article |
| id | doaj.art-0f870800f03749b09160df3b38b94f79 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T05:12:37Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-0f870800f03749b09160df3b38b94f792023-12-03T12:47:59ZengMDPI AGMathematics2227-73902022-07-011015268610.3390/math10152686Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVsKai Zhao0Jia Song1Yunlong Hu2Xiaowei Xu3Yang Liu4School of Astronautics, Beihang University (BUAA), Beijing 100191, ChinaSchool of Astronautics, Beihang University (BUAA), Beijing 100191, ChinaSchool of Astronautics, Beihang University (BUAA), Beijing 100191, ChinaSchool of Astronautics, Beihang University (BUAA), Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing 100191, ChinaThanks to their hovering and vertical take-off and landing abilities, quadrotor unmanned aerial vehicles (UAVs) are receiving a great deal of attention. With the diversified development of the functions of UAVs, the requirements for flight performance with higher stability and maneuverability are increasing. Aiming at parameter uncertainty and external disturbance, a deep deterministic policy gradient-based active disturbance rejection controller (DDPG-ADRC) is proposed. The total disturbances can be compensated dynamically by adjusting the controller bandwidth and the estimation of system parameters online. The tradeoff between anti-interference and rapidity can be better realized in this way compared with the traditional ADRC. The process of parameter tuning is demonstrated through the simulation results of tracking step instruction and sine sweep under ideal and disturbance conditions. Further analysis shows the proposed DDPG-ADRC has better performance.https://www.mdpi.com/2227-7390/10/15/2686reinforcement learningdeep deterministic policy gradientactive disturbance rejection controlquadrotor ummanned aerial vehicle |
| spellingShingle | Kai Zhao Jia Song Yunlong Hu Xiaowei Xu Yang Liu Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs Mathematics reinforcement learning deep deterministic policy gradient active disturbance rejection control quadrotor ummanned aerial vehicle |
| title | Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs |
| title_full | Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs |
| title_fullStr | Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs |
| title_full_unstemmed | Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs |
| title_short | Deep Deterministic Policy Gradient-Based Active Disturbance Rejection Controller for Quad-Rotor UAVs |
| title_sort | deep deterministic policy gradient based active disturbance rejection controller for quad rotor uavs |
| topic | reinforcement learning deep deterministic policy gradient active disturbance rejection control quadrotor ummanned aerial vehicle |
| url | https://www.mdpi.com/2227-7390/10/15/2686 |
| work_keys_str_mv | AT kaizhao deepdeterministicpolicygradientbasedactivedisturbancerejectioncontrollerforquadrotoruavs AT jiasong deepdeterministicpolicygradientbasedactivedisturbancerejectioncontrollerforquadrotoruavs AT yunlonghu deepdeterministicpolicygradientbasedactivedisturbancerejectioncontrollerforquadrotoruavs AT xiaoweixu deepdeterministicpolicygradientbasedactivedisturbancerejectioncontrollerforquadrotoruavs AT yangliu deepdeterministicpolicygradientbasedactivedisturbancerejectioncontrollerforquadrotoruavs |