GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → roboticsleeds → mujoco-ur5-model

roboticsleeds / mujoco-ur5-model

Licence: GPL-3.0 license
Mujoco Model for UR5-Ridgeback-Robotiq Robot

Programming Languages

python
139335 projects - #7 most used programming language

Labels

roboticsmujocorobotics-simulationmujoco-environments

Projects that are alternatives of or similar to mujoco-ur5-model

Mjrl
Reinforcement learning algorithms for MuJoCo tasks
Stars: ✭ 162 (+636.36%)
Mutual labels:  mujoco
mujoco ros pkgs
ROS integration of Mujoco simulator
Stars: ✭ 57 (+159.09%)
Mutual labels:  mujoco
vnla
Code accompanying the CVPR 2019 paper: https://arxiv.org/abs/1812.04155
Stars: ✭ 60 (+172.73%)
Mutual labels:  robotics-simulation
Pytorch sac
PyTorch implementation of Soft Actor-Critic (SAC)
Stars: ✭ 174 (+690.91%)
Mutual labels:  mujoco
Tianshou
An elegant PyTorch deep reinforcement learning library.
Stars: ✭ 4,109 (+18577.27%)
Mutual labels:  mujoco
jax-rl
JAX implementations of core Deep RL algorithms
Stars: ✭ 61 (+177.27%)
Mutual labels:  mujoco
Pytorch sac ae
PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)
Stars: ✭ 94 (+327.27%)
Mutual labels:  mujoco
URDF-Importer
URDF importer
Stars: ✭ 135 (+513.64%)
Mutual labels:  robotics-simulation
mujoco-benchmark
Provide full reinforcement learning benchmark on mujoco environments, including ddpg, sac, td3, pg, a2c, ppo, library
Stars: ✭ 101 (+359.09%)
Mutual labels:  mujoco
community-projects
Webots projects (PROTO files, controllers, simulation worlds, etc.) contributed by the community.
Stars: ✭ 20 (-9.09%)
Mutual labels:  robotics-simulation
Dm control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Stars: ✭ 2,592 (+11681.82%)
Mutual labels:  mujoco
Pytorch Reinforce
PyTorch Implementation of REINFORCE for both discrete & continuous control
Stars: ✭ 212 (+863.64%)
Mutual labels:  mujoco
ign-rendering
C++ library designed to provide an abstraction for different rendering engines. It offers unified APIs for creating 3D graphics applications.
Stars: ✭ 34 (+54.55%)
Mutual labels:  robotics-simulation
Coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Stars: ✭ 2,085 (+9377.27%)
Mutual labels:  mujoco
ign-sensors
Provides numerous sensor models designed to generate realistic data from simulation environments.
Stars: ✭ 30 (+36.36%)
Mutual labels:  robotics-simulation
Deeprl algorithms
DeepRL algorithms implementation easy for understanding and reading with Pytorch and Tensorflow 2(DQN, REINFORCE, VPG, A2C, TRPO, PPO, DDPG, TD3, SAC)
Stars: ✭ 97 (+340.91%)
Mutual labels:  mujoco
RPN
Code Repository for Regression Planning Networks
Stars: ✭ 58 (+163.64%)
Mutual labels:  robotics-simulation
RigidBodySim.jl
Simulation and visualization of articulated rigid body systems in Julia
Stars: ✭ 63 (+186.36%)
Mutual labels:  robotics-simulation
Pytorch-RL-CPP
A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
Stars: ✭ 73 (+231.82%)
Mutual labels:  mujoco
OpenMAS
OpenMAS is an open source multi-agent simulator based in Matlab for the simulation of decentralized intelligent systems defined by arbitrary behaviours and dynamics.
Stars: ✭ 80 (+263.64%)
Mutual labels:  robotics-simulation
View All Similar Projects ➔

MuJoCo UR5 Model

Model

This is currently a planar robot only with three joints (two slide joints and a hinge joint).

This repository includes:

  • Required STL files to represent the shown robot.
  • MuJoCo XML files to represent the robot in MuJoCo.
  • A Python script that will convert UR5 joint values from degrees to MuJoCo body quaternions. An explanation about the need of this script is available under here.

Developers and Contributors

MuJoCo UR5 Model was developed by the Robot Manipulation Lab in the School of Computing at the University of Leeds.

License

This work is licensed under GNU General Public License v3.0. The full license is available here.

Notes

Description about the robot configuration

Since we meant to use this robot model as a planar robot, we decided to remove the arm joints and just add three joints on Ridgeback (x, y, theta). Therefore, we had to apply some rotations to the bodies themselves to match the joint configuration of the actual robot.

The current model in this repository as defined includes some custom configurations such that the arm is set to the following:

  • Base: -90.0 degrees
  • Shoulder: -175.0 degrees
  • Elbow: -5.0 degrees
  • Wrist1: -180.0 degrees
  • Wrist2: -90.0 degrees
  • Wrist3: -180.0 degrees

If you want to change the configuration of the robot, then we recommend to start from the following original configuration of the arm (which is the home configuration of UR) and apply rotations as needed to the required bodies to match the UR5 joint values shown on the screen. With the following configuration you should just apply the required rotations of each joint from the UR5 screen to the existing quaternions of the configuration below (multiply the current quaternion of the XML with the desired rotation):

<body name="shoulder_link" pos="0.28 0 0.545159" quat="0.681998 0 0 -0.731354">
    <inertial pos="0 0 0" mass="3.7" diaginertia="0.0102675 0.0102675 0.00666" />
    <geom type="mesh" rgba="0.7 0.7 0.7 1" mesh="shoulder" />
    <body name="upper_arm_link" pos="0 0.13585 0" quat="0.707107 0 0.707107 0">
        <inertial pos="0 0 0.28" mass="8.393" diaginertia="0.226891 0.226891 0.0151074" />
        <geom type="mesh" rgba="0.7 0.7 0.7 1" mesh="upperarm" />
        <body name="forearm_link" pos="0 -0.1197 0.425">
            <inertial pos="0 0 0.25" mass="2.275" diaginertia="0.0494433 0.0494433 0.004095" />
            <geom type="mesh" rgba="0.7 0.7 0.7 1" mesh="forearm" />
            <body name="wrist_1_link" pos="0 0 0.39225" quat="0.707107 0 0.707107 0">
                <inertial pos="0 0 0" quat="0.5 0.5 -0.5 0.5" mass="1.219" diaginertia="0.21942 0.111173 0.111173" />
                <geom type="mesh" rgba="0.7 0.7 0.7 1" mesh="wrist1" />
                <body name="wrist_2_link" pos="0 0.093 0">
                    <inertial pos="0 0 0" quat="0.5 0.5 -0.5 0.5" mass="1.219" diaginertia="0.21942 0.111173 0.111173" />
                    <geom type="mesh" rgba="0.7 0.7 0.7 1" mesh="wrist2" />
                    <body name="wrist_3_link" pos="0 0 0.09465">
                        <inertial pos="0 0 0" quat="0.5 0.5 -0.5 0.5"  mass="0.1879" diaginertia="0.033822 0.0171365 0.0171365" />
                        <geom type="mesh" rgba="0.7 0.7 0.7 1" friction="0.8 0.8 0.8" mesh="wrist3" />
                    </body>
                </body>
            </body>
        </body>
    </body>
</body>

However, to make this easier, we wrote a simple Python script under scripts called set_ur5_joints.py that will ask you to provide the joint values in degrees of the robot as shown on the UR5 screen and the xml file you would like to modify and will do the appropriate calculations and convertsions to set the model quaternions correctly.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].