Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917611509383168 |
|---|---|
| author | Timmerman, Mike Patel, Aryan Reinhart, Tim |
| author_facet | Timmerman, Mike Patel, Aryan Reinhart, Tim |
| contents | The paper presents a technique using reinforcement learning (RL) to adapt the control gains of a quadcopter controller. Specifically, we employed Proximal Policy Optimization (PPO) to train a policy which adapts the gains of a cascaded feedback controller in-flight. The primary goal of this controller is to minimize tracking error while following a specified trajectory. The paper's key objective is to analyze the effectiveness of the adaptive gain policy and compare it to the performance of a static gain control algorithm, where the Integral Squared Error and Integral Time Squared Error are used as metrics. The results show that the adaptive gain scheme achieves over 40$\%$ decrease in tracking error as compared to the static gain controller. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07216 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control Timmerman, Mike Patel, Aryan Reinhart, Tim Systems and Control Machine Learning Robotics The paper presents a technique using reinforcement learning (RL) to adapt the control gains of a quadcopter controller. Specifically, we employed Proximal Policy Optimization (PPO) to train a policy which adapts the gains of a cascaded feedback controller in-flight. The primary goal of this controller is to minimize tracking error while following a specified trajectory. The paper's key objective is to analyze the effectiveness of the adaptive gain policy and compare it to the performance of a static gain control algorithm, where the Integral Squared Error and Integral Time Squared Error are used as metrics. The results show that the adaptive gain scheme achieves over 40$\%$ decrease in tracking error as compared to the static gain controller. |
| title | Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control |
| topic | Systems and Control Machine Learning Robotics |
| url | https://arxiv.org/abs/2403.07216 |