Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor
Inaccurate system parameters and unpredicted external disturbances affect the performance of non-linear controllers. In this paper, a new adaptive control algorithm under the reinforcement framework is proposed to stabilize a quadrotor helicopter. Based on a command-filtered non-linear control algor...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2016-02-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Online Access: | https://doi.org/10.5772/62128 |
| _version_ | 1818191014168363008 |
|---|---|
| author | Wenjie Lou Xiao Guo |
| author_facet | Wenjie Lou Xiao Guo |
| author_sort | Wenjie Lou |
| collection | DOAJ |
| description | Inaccurate system parameters and unpredicted external disturbances affect the performance of non-linear controllers. In this paper, a new adaptive control algorithm under the reinforcement framework is proposed to stabilize a quadrotor helicopter. Based on a command-filtered non-linear control algorithm, adaptive elements are added and learned by policy-search methods. To predict the inaccurate system parameters, a new kernel-based regression learning method is provided. In addition, Policy learning by Weighting Exploration with the Returns (PoWER) and Return Weighted Regression (RWR) are utilized to learn the appropriate parameters for adaptive elements in order to cancel the effect of external disturbance. Furthermore, numerical simulations under several conditions are performed, and the ability of adaptive trajectory-tracking control with reinforcement learning are demonstrated. |
| first_indexed | 2024-12-12T00:07:52Z |
| format | Article |
| id | doaj.art-2af2d6ca51a24338bc69f3412ffa8e39 |
| institution | Directory Open Access Journal |
| issn | 1729-8814 |
| language | English |
| last_indexed | 2024-12-12T00:07:52Z |
| publishDate | 2016-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-2af2d6ca51a24338bc69f3412ffa8e392022-12-22T00:45:04ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142016-02-011310.5772/6212810.5772_62128Adaptive Trajectory Tracking Control using Reinforcement Learning for QuadrotorWenjie Lou0Xiao Guo1 School of Aeronautic Science and Engineering, Beihang University, Beijing, China School of Automation Science and Electrical Engineering, Beihang University, Beijing, ChinaInaccurate system parameters and unpredicted external disturbances affect the performance of non-linear controllers. In this paper, a new adaptive control algorithm under the reinforcement framework is proposed to stabilize a quadrotor helicopter. Based on a command-filtered non-linear control algorithm, adaptive elements are added and learned by policy-search methods. To predict the inaccurate system parameters, a new kernel-based regression learning method is provided. In addition, Policy learning by Weighting Exploration with the Returns (PoWER) and Return Weighted Regression (RWR) are utilized to learn the appropriate parameters for adaptive elements in order to cancel the effect of external disturbance. Furthermore, numerical simulations under several conditions are performed, and the ability of adaptive trajectory-tracking control with reinforcement learning are demonstrated.https://doi.org/10.5772/62128 |
| spellingShingle | Wenjie Lou Xiao Guo Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor International Journal of Advanced Robotic Systems |
| title | Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor |
| title_full | Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor |
| title_fullStr | Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor |
| title_full_unstemmed | Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor |
| title_short | Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor |
| title_sort | adaptive trajectory tracking control using reinforcement learning for quadrotor |
| url | https://doi.org/10.5772/62128 |
| work_keys_str_mv | AT wenjielou adaptivetrajectorytrackingcontrolusingreinforcementlearningforquadrotor AT xiaoguo adaptivetrajectorytrackingcontrolusingreinforcementlearningforquadrotor |