Skip to main content

A package of reinforcement learning environments for flight control using the JSBSim flight dynamics model.

Project description

JSBGym

Python: 3.7+ PyPI Version PyPI downloads Code style: black

Note: This library will only work with Windows.

JSBGym provides reinforcement learning environments for the control of fixed-wing aircraft using the JSBSim flight dynamics model. The package's environments implement the Farama-Foundation's Gymnasium interface allowing environments to be created and interacted with.

Example

Pretrained models can be found here

Setup

Firstly, install JSBSim. Make sure that it is installed in C:/JSBSim

If you would like to render the environment with FlightGear, install it from here. Make sure the FlightGear bin directory is in PATH (Usually C:\Program Files\FlightGear 2020.3\bin)and there is a system variable called FG_ROOT with the FG data folder as it's value (Usually C:\Program Files\FlightGear 2020.3\data). If you have installed the aircraft to a different location, add the folder to the FG_AIRCRAFT system variable. 3D visualisation requires installation of the FlightGear simulator. Confirm it is runnable from terminal with:

fgfs --version

Open the console and install jsbgym:

pip install jsbgym

Getting Started

import jsbgym
import gymnasium as gym

env = gym.make(ENV_ID)
env.reset()
observation, reward, terminated, truncated, info = env.step(action)

Environments

Environment ID strings are constructed as follows:

f"{aircraft}-{task}-{shaping}-{flightgear}-v0"

Aircraft

The environment can be configured to use one of seven aircraft:

  • Cessna172P Cessna 172P Skyhawk (Default FlightGear Aircraft)
  • PA28 Piper PA-28-161 Warrior II
  • J3 Piper J-3 Cub
  • F15 McDonnell Douglas F-15C Eagle (F-15C in FlightGear)
  • F16 General Dynamics F-16CJ Block 52
  • OV10 North American OV-10A USAFE Bronco
  • A320 Airbus A320 (A320 Familiy in Flightgear)
  • B747 Boeing 747-400
  • MD11 McDonnell Douglas MD-11

All aircraft except the Cessna 172P requires the aircraft to be downloaded via the launcher using the default FlightGear Hangar.

Task

JSBGym implements two tasks for controlling the altitude and heading of aircraft:

  • HeadingControlTask aircraft must fly in a straight line, maintaining its initial altitude and direction of travel (heading)
  • TurnHeadingControlTask aircraft must turn to face a random target heading while maintaining their initial altitude

Shaping

The environment can use three different shaping types:

  • Shaping.STANDARD
  • Shaping.EXTRA
  • Shaping.EXTRA_SEQUENTIAL

FlightGear

If using FlightGear as a render mode, use FG, if not, use NoFG

Environment ID

To fly a Cessna on the Heading Control task withoug using FlightGear,

env = gym.make("Cessna172P-HeadingControlTask-Shaping.STANDARD-NoFG-v0")

Visualisation

2D

A basic plot of agent actions and current state information can be using human render mode by calling env.render() after specifying the render mode in gym.make().

env = gym.make("Cessna172P-HeadingControlTask-Shaping.STANDARD-NoFG-v0", render_mode="human")
env.reset()
env.render()

3D

Visualising with FlightGear requires the Gymnasium environment to be created with a FlightGear-enabled environment ID by specifying the render_mode in gym.make() and changing the value after {shaping} to FG. Using this render mode while training is strongly discouraged due to an error occuring midway through the training (Could not connect to socket for output!).

env = gym.make("Cessna172P-HeadingControlTask-Shaping.STANDARD-FG-v0", render_mode="flightgear")
env.reset()
env.render()

State and Action Space

JSBGym's environments have a continuous state and action space. The state is a 17-tuple:

(name='position/h-sl-ft', description='altitude above mean sea level [ft]', min=-1400, max=85000)
(name='attitude/pitch-rad', description='pitch [rad]', min=-1.5707963267948966, max=1.5707963267948966)
(name='attitude/roll-rad', description='roll [rad]', min=-3.141592653589793, max=3.141592653589793)
(name='velocities/u-fps', description='body frame x-axis velocity [ft/s]', min=-2200, max=2200)
(name='velocities/v-fps', description='body frame y-axis velocity [ft/s]', min=-2200, max=2200)
(name='velocities/w-fps', description='body frame z-axis velocity [ft/s]', min=-2200, max=2200)
(name='velocities/p-rad_sec', description='roll rate [rad/s]', min=-6.283185307179586, max=6.283185307179586)
(name='velocities/q-rad_sec', description='pitch rate [rad/s]', min=-6.283185307179586, max=6.283185307179586)
(name='velocities/r-rad_sec', description='yaw rate [rad/s]', min=-6.283185307179586, max=6.283185307179586)
(name='fcs/left-aileron-pos-norm', description='left aileron position, normalised', min=-1, max=1)
(name='fcs/right-aileron-pos-norm', description='right aileron position, normalised', min=-1, max=1)
(name='fcs/elevator-pos-norm', description='elevator position, normalised', min=-1, max=1)
(name='fcs/rudder-pos-norm', description='rudder position, normalised', min=-1, max=1)
(name='error/altitude-error-ft', description='error to desired altitude [ft]', min=-1400, max=85000)
(name='aero/beta-deg', description='sideslip [deg]', min=-180, max=180)
(name='error/track-error-deg', description='error to desired track [deg]', min=-180, max=180)
(name='info/steps_left', description='steps remaining in episode', min=0, max=300)

Actions are 3-tuples of floats in the range [-1,+1] describing commands to move the aircraft's control surfaces (ailerons, elevator, rudder):

(name='fcs/aileron-cmd-norm', description='aileron commanded position, normalised', min=-1.0, max=1.0)
(name='fcs/elevator-cmd-norm', description='elevator commanded position, normalised', min=-1.0, max=1.0)
(name='fcs/rudder-cmd-norm', description='rudder commanded position, normalised', min=-1.0, max=1.0)

Known Issues

  • A320 has and error when rendering with flightgear.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jsbgym-0.1.10.tar.gz (46.3 kB view details)

Uploaded Source

Built Distribution

jsbgym-0.1.10-py3-none-any.whl (52.3 kB view details)

Uploaded Python 3

File details

Details for the file jsbgym-0.1.10.tar.gz.

File metadata

  • Download URL: jsbgym-0.1.10.tar.gz
  • Upload date:
  • Size: 46.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for jsbgym-0.1.10.tar.gz
Algorithm Hash digest
SHA256 db0d016ed930dd2f89ae1226a69e87a44bb74beebfd5298ca82f6b55bc798243
MD5 3ae62031f2cb7c8236a5fb8374d162cf
BLAKE2b-256 6fb449de9b9d12047b761d237195c2c2d735d3c87a3ca7ed0847d1ead2739f63

See more details on using hashes here.

File details

Details for the file jsbgym-0.1.10-py3-none-any.whl.

File metadata

  • Download URL: jsbgym-0.1.10-py3-none-any.whl
  • Upload date:
  • Size: 52.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for jsbgym-0.1.10-py3-none-any.whl
Algorithm Hash digest
SHA256 97d9468e0e7f5e2243db2f60f786988d88f78ddc0b3c7016b0b42032fb007d5f
MD5 673160eec0a7f4cb5fa94617ab72e9b7
BLAKE2b-256 11b745d179dc8558c225bc4a5bac974c253c5cbc6fae00d4e949a86ccea1fa5b

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page