Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910869866151936 |
|---|---|
| author | Liu, Yu Tang Vale, Afonso Ahmad, Aamir Ventura, Rodrigo Basiri, Meysam |
| author_facet | Liu, Yu Tang Vale, Afonso Ahmad, Aamir Ventura, Rodrigo Basiri, Meysam |
| contents | Quadcopter attitude control involves two tasks: smooth attitude tracking and aggressive stabilization from arbitrary states. Although both can be formulated as tracking problems, their distinct state spaces and control strategies complicate a unified reward function. We propose a multitask deep reinforcement learning framework that leverages parallel simulation with IsaacGym and a Graph Convolutional Network (GCN) policy to address both tasks effectively. Our multitask Soft Actor-Critic (SAC) approach achieves faster, more reliable learning and higher sample efficiency than single-task methods. We validate its real-world applicability by deploying the learned policy - a compact two-layer network with 24 neurons per layer - on a Pixhawk flight controller, achieving 400 Hz control without extra computational resources. We provide our code at https://github.com/robot-perception-group/GraphMTSAC\_UAV/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy Liu, Yu Tang Vale, Afonso Ahmad, Aamir Ventura, Rodrigo Basiri, Meysam Robotics Quadcopter attitude control involves two tasks: smooth attitude tracking and aggressive stabilization from arbitrary states. Although both can be formulated as tracking problems, their distinct state spaces and control strategies complicate a unified reward function. We propose a multitask deep reinforcement learning framework that leverages parallel simulation with IsaacGym and a Graph Convolutional Network (GCN) policy to address both tasks effectively. Our multitask Soft Actor-Critic (SAC) approach achieves faster, more reliable learning and higher sample efficiency than single-task methods. We validate its real-world applicability by deploying the learned policy - a compact two-layer network with 24 neurons per layer - on a Pixhawk flight controller, achieving 400 Hz control without extra computational resources. We provide our code at https://github.com/robot-perception-group/GraphMTSAC\_UAV/. |
| title | Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.08259 |