Skip to content

quadrotor environment based on openai gym api.

Notifications You must be signed in to change notification settings

jc-bao/gym-quad

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 

Repository files navigation

gym-quad

Description

This is a gym environment for quadrotor control. It is based on the PyBullet physics engine.

The environment is a 3D quadrotor with 4 rotors. The rotors are controlled by a 4D action space. The observation space is a 3D position and 3D velocity. The reward is the negative distance to a target position.

The main feature is that the quadrotor is hanging an object by a free joint. The object can be moved by the quadrotor. The object can also be moved by an external force.

Visualization Multi Quad Plot
tmp multi-quad image
Bi-level PID Controller Limitation: sensitive to object mass, large control error.

Installation

pip install -e .

Usage

cd gym_quad
python quad_bullet.py

TODO

  • Dual drone environment apply force
  • Soft rope for single drone (multi-link or spring)
  • More drones pulling a object (3 or more. )

About

quadrotor environment based on openai gym api.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages