https://github.com/odegnome/sb3_quad
Implementation of Deep Reinforcement Learning for Collision Prevention in Quadrotor - II
https://github.com/odegnome/sb3_quad
autonomous-agents autonomous-robots mujoco python3 quadrotor reinforcement-learning stable-baselines3
Last synced: 2 months ago
JSON representation
Implementation of Deep Reinforcement Learning for Collision Prevention in Quadrotor - II
- Host: GitHub
- URL: https://github.com/odegnome/sb3_quad
- Owner: odegnome
- Created: 2025-01-24T14:53:05.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-24T15:22:28.000Z (over 1 year ago)
- Last Synced: 2025-01-24T16:19:15.935Z (over 1 year ago)
- Topics: autonomous-agents, autonomous-robots, mujoco, python3, quadrotor, reinforcement-learning, stable-baselines3
- Language: Python
- Homepage:
- Size: 308 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Implementation of Deep Reinforcement Learning for Collision Prevention in Quadrotor - II
This is a continuation of my [dissertation project](https://github.com/odegnome/dcode) for building an autonomous quadrotor.
Difference from my original implementation is that this uses [sb3](https://github.com/DLR-RM/stable-baselines3)
algorithm to train and also, yaw axis acceleration is also a consideration in the reward.
The yaw axis reward was necessary because otherwise, the quadrotor was spinning about that
axis uncontrollably.
## Performance after training for 500k time-steps
There is a glitch in the video below due to incorrect use of ffmpeg for converting images to mp4. Please ignore!
https://github.com/user-attachments/assets/e1aca736-3fb0-4e03-85ce-7df2cd698cc4