Multiple agents on a single machine

This scenario describes simulating multiple agent dynamics and imagery on a single machine with Python API. Multiple vehicles can be added to the vehicle_model block of FligthGogglesClient.yaml. Check Python Parameters for the detailed instructions about writing a configuration file.

This is the example configuration of multiple agents:

YAML

state:
    sceneFilename: "Stata_GroundFloor"
    camWidth: 640
    camHeight: 480
    camFOV: 70.0
    camDepthScale: 0.20

renderer:
    0:
        inputPort: "10253"
        outputPort: "10254"

camera_model:
    0:
        ID: cam0
        channels: 3
        renderer: 0
        freq: 30
        outputShaderType: -1
        hasCollisionCheck: False
    1:
        ID: cam1
        channels: 3
        renderer: 0
        freq: 30
        outputShaderType: -1
        hasCollisionCheck: False

vehicle_model:
    uav1:
        type: "uav"
        initialPose: [-6.5, -18.5, -2.0, 1.0, 0, 0, 0]
        imu_freq: 200
        cameraInfo:
            cam0:
                relativePose: [0.2, 0, 0, 1, 0, 0, 0]
    car1:
        type: "car"
        initialPose: [-6.5, -18.5, -0.2, 1.0, 0, 0, 0]
        imu_freq: 200
        cameraInfo:
            cam1:
                relativePose: [0, 0, 0, 1, 0, 0, 0]
    uav2:
        type: "uav"
        initialPose: [-6.5, -12.5, -2.0, 1.0, 0, 0, 0]
        imu_freq: 200

Note that the vehicle model can be executed without any attached camera or object.

This is the sample code for multiple agents simulation:

PY

import numpy as np
from IPython.display import HTML, display
from flightgoggles.env import flightgoggles_env

if __name__ == "__main__":
    env = flightgoggles_env()
    for i in range(200):
        env.proceed_motor_speed("uav1", np.ones(4)*1133.0, 0.01)
        env.proceed("car1", 1., 1., 0.01)
        env.proceed_motor_speed("uav2", np.ones(4)*1133.0, 0.01)

    ani_set = env.plot_state_video()
    if "cam0" in ani_set.keys():
        display(HTML(ani_set["cam0"].to_html5_video()))
    if "cam1" in ani_set.keys():
        display(HTML(ani_set["cam1"].to_html5_video()))
    env.close()

Fig 1. The result of the example code (cam 0)

Fig 2. The result of the example code (cam 1)