Skip to main content

A simulator of ADAM (Autonomous Domestic Ambidextrous Manipulator), a mobile robot manipulator consisting of a base with two Degrees of Freedom (DoF) and two Universal Robots UR3 of 6 DoF each.

Project description

ADAM simulator

ADAM (Autonomous Domestic Ambidextrous Manipulator) is a mobile robot manipulator consisting of a base with two Degrees of Freedom (DoF) and two Universal Robots UR3 of 6 DoF each.

The simulation was built using MuJoCo, a free and open source physics engine designed from the ground up for the purpose of model-based optimization, and in particular optimization through contacts.

Installation

Follow the next steps for installing the simulation on your device.

Requierements:

  • Ubuntu
  • Python 3.10.0 or higher

Install miniconda (highly-recommended)

It is highly recommended to install all the dependencies on a new virtual environment. For more information check the conda documentation for installation and environment management. For creating the environment use the following commands on the terminal.

conda create -n adam python==3.10.8
conda activate adam

Install from pip

The ADAM simulator is available as a pip package. For installing it just use:

pip install adam-sim

Install from source

Firstly, clone the repository in your system.

git clone https://github.com/vistormu/adam_simulator.git

Then, enter the directory and install the required dependencies

cd adam_simulator
pip install -r requirements.txt

API Reference

Visit TMP

Minimal Working Examples

Basic Usage

In this example, ADAM moves the left and right wrist_2 continuously.

from adam import Simulation
from adam.entities import Configuration, Data


def main():
    sim: Simulation = Simulation()
    initial_data: Data = sim.load_scene()

    left_configuration: Configuration = initial_data.configuration.left_manipulator
    right_configuration: Configuration = initial_data.configuration.right_manipulator

    for _ in range(100):
        left_configuration += Configuration(0.0, 0.0, 0.0, 0.0, 0.1, 0.0)
        right_configuration -= Configuration(0.0, 0.0, 0.0, 0.0, 0.1, 0.0)

        sim.render()
        data: Data = sim.step(left_configuration, right_configuration)

    sim.close()


if __name__ == '__main__':
    main()

ConfigurationsManager example

In this example, the test configurations are loaded to the left manipulator.

from adam import Simulation, ConfigurationsManager
from adam.entities import Configuration, Data


def main():
    sim: Simulation = Simulation()
    initial_data: Data = sim.load_scene()

    configuration_list: list[Configuration] = ConfigurationsManager.load('test')

    for configuration in configuration_list:
        sim.render()

        data: Data = sim.step(configuration, initial_data.configuration.right_manipulator)

    sim.close()


if __name__ == '__main__':
    main()

MapMaker example

In this example, various bodies are created and then added to the scene

from adam import Simulation, MapMaker
from adam.entities import Data, Cube, Box, Capsule, Cylinder, Sphere


def main():
    directory_path: str = 'tests/assets/'
    filename: str = 'obstacles.xml'

    map_maker: MapMaker = MapMaker(directory_path+filename)

    # Cube 1
    cube_1: Cube = Cube('cube_1')
    cube_1.set_geometry(size=0.5, position=(0.5, 0.0, 0.0))
    cube_1.set_dynamics(mass=1.0)
    cube_1.set_appearance('#2f2f2f')

    # Cube 2
    cube_2: Cube = Cube('cube_2')
    cube_2.set_geometry(size=0.5, position=(1.0, 0.0, 0.0))
    cube_2.set_dynamics(mass=1.0)
    cube_2.set_appearance(color='#b64545', alpha=0.5)

    # Cube 3
    cube_3: Cube = Cube('cube_3')
    cube_3.set_geometry(size=0.5, position=(1.0, 0.0, 0.5))
    cube_3.set_appearance('#c4c476')

    # Cube 4
    cube_4: Cube = Cube('cube_4')
    cube_4.set_geometry(size=0.5, position=(0.5, 0.0, 0.5))

    # Box
    box: Box = Box('box')
    box.set_geometry(size=(0.2, 0.2, 0.5), position=(1.0, 0.0, 1.0))
    box.set_appearance(color=(0.2, 0.2, 0.2), alpha=0.2)

    # Capsule
    capsule: Capsule = Capsule('capsule')
    capsule.set_geometry(size=(0.2, 0.5), position=(0.5, -0.5, 0.0))

    # Cylinder
    cylinder: Cylinder = Cylinder('cylinder')
    cylinder.set_geometry(size=(0.2, 0.5), position=(1.0, -0.5, 0.0))

    # Sphere
    sphere: Sphere = Sphere('sphere')
    sphere.set_geometry(size=0.25, position=(0.5, -1.0, 0.0))

    map_maker.add_bodies([cube_1, cube_2, cube_3, cube_4, box, capsule, cylinder, sphere])
    map_maker.make()

    Simulation.export_scene(directory_path)
    map_maker.add_to(directory_path + 'scene.xml')

    sim: Simulation = Simulation()
    initial_data: Data = sim.load_scene('tests/assets/scene.xml')

    sim.extend_collisions({77: 'table'})

    for _ in range(1000):
        sim.step(initial_data.configuration.left_manipulator, initial_data.configuration.right_manipulator)
        sim.render()


if __name__ == '__main__':
    main()

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

adam_sim-0.3.0.tar.gz (8.6 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

adam_sim-0.3.0-py3-none-any.whl (8.6 MB view details)

Uploaded Python 3

File details

Details for the file adam_sim-0.3.0.tar.gz.

File metadata

  • Download URL: adam_sim-0.3.0.tar.gz
  • Upload date:
  • Size: 8.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.8

File hashes

Hashes for adam_sim-0.3.0.tar.gz
Algorithm Hash digest
SHA256 def64654371ba386850cfb7032baca6bad2de95b63634fd3d008c7256efab671
MD5 ad63aefff88990ed539ac4b67df31c14
BLAKE2b-256 7da5fd5dfc6adc9ad4f50008b3ba63961fbc5efd52d7ef040f209625f90033b0

See more details on using hashes here.

File details

Details for the file adam_sim-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: adam_sim-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 8.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.8

File hashes

Hashes for adam_sim-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3cd6becdc24ba55579fb6a31d6f203397ca54f55ecc90d155da78ae37839820f
MD5 7988515c85978075fa96a77b6aa335a7
BLAKE2b-256 3ed05447259d8c976d87f1cb9c0db309f49330d9ebbb08eb23ee403e84490223

See more details on using hashes here.

Supported by

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