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 → jr-robotics → robo-gym-robot-servers

jr-robotics / robo-gym-robot-servers

Licence: MIT license
Repository containing Robot Servers ROS packages

Programming Languages

python
139335 projects - #7 most used programming language
Dockerfile
14818 projects
CMake
9771 projects
shell
77523 projects

Labels

roboticsopenai-gymreinforcement-learning-environmentsrobo-gym

Projects that are alternatives of or similar to robo-gym-robot-servers

modelicagym
Modelica models integration with Open AI Gym
Stars: ✭ 53 (+112%)
Mutual labels:  openai-gym, reinforcement-learning-environments
bark-ml
Gym environments and agents for autonomous driving.
Stars: ✭ 68 (+172%)
Mutual labels:  openai-gym, reinforcement-learning-environments
gym-cartpole-swingup
A simple, continuous-control environment for OpenAI Gym
Stars: ✭ 20 (-20%)
Mutual labels:  openai-gym, reinforcement-learning-environments
gym-hybrid
Collection of OpenAI parametrized action-space environments.
Stars: ✭ 26 (+4%)
Mutual labels:  openai-gym, reinforcement-learning-environments
realant
RealAnt robot platform for low-cost, real-world reinforcement learning
Stars: ✭ 40 (+60%)
Mutual labels:  reinforcement-learning-environments
Ns3 Gym
ns3-gym - The Playground for Reinforcement Learning in Networking Research
Stars: ✭ 221 (+784%)
Mutual labels:  openai-gym
Deep Reinforcement Learning Gym
Deep reinforcement learning model implementation in Tensorflow + OpenAI gym
Stars: ✭ 200 (+700%)
Mutual labels:  openai-gym
Tensorflow Rl
Implementations of deep RL papers and random experimentation
Stars: ✭ 176 (+604%)
Mutual labels:  openai-gym
a3c-super-mario-pytorch
Reinforcement Learning for Super Mario Bros using A3C on GPU
Stars: ✭ 35 (+40%)
Mutual labels:  openai-gym
deep-rl-docker
Docker image with OpenAI Gym, Baselines, MuJoCo and Roboschool, utilizing TensorFlow and JupyterLab.
Stars: ✭ 44 (+76%)
Mutual labels:  openai-gym
rlberry
An easy-to-use reinforcement learning library for research and education.
Stars: ✭ 124 (+396%)
Mutual labels:  reinforcement-learning-environments
A3c continuous
A continuous action space version of A3C LSTM in pytorch plus A3G design
Stars: ✭ 223 (+792%)
Mutual labels:  openai-gym
RLGC
An open-source platform for applying Reinforcement Learning for Grid Control (RLGC)
Stars: ✭ 85 (+240%)
Mutual labels:  openai-gym
Gymfc
A universal flight control tuning framework
Stars: ✭ 210 (+740%)
Mutual labels:  openai-gym
ddp-gym
Differential Dynamic Programming controller operating in OpenAI Gym environment.
Stars: ✭ 70 (+180%)
Mutual labels:  openai-gym
Hands On Intelligent Agents With Openai Gym
Code for Hands On Intelligent Agents with OpenAI Gym book to get started and learn to build deep reinforcement learning agents using PyTorch
Stars: ✭ 189 (+656%)
Mutual labels:  openai-gym
yarll
Combining deep learning and reinforcement learning.
Stars: ✭ 84 (+236%)
Mutual labels:  openai-gym
Deep-Reinforcement-Learning-With-Python
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
Stars: ✭ 222 (+788%)
Mutual labels:  openai-gym
awesome-isaac-gym
A curated list of awesome NVIDIA Issac Gym frameworks, papers, software, and resources
Stars: ✭ 373 (+1392%)
Mutual labels:  openai-gym
multi car racing
An OpenAI Gym environment for multi-agent car racing based on Gym's original car racing environment.
Stars: ✭ 58 (+132%)
Mutual labels:  reinforcement-learning-environments
View All Similar Projects ➔

robo-gym-robot-servers

Repository containing Robot Servers ROS packages for the robo-gym toolkit.

The robo-gym-robot-servers provide an interface to the Gazebo simulations and to the real robots.

Supported Systems

Recommended System Setup: Ubuntu 20.04 - ROS Noetic - Python [>3.7]

The packages have been tested for ROS Noetic and Melodic. We will try to maintain compatibility with ROS Melodic for as long as possible, nevertheless our main efforts will be based on ROS Noetic.

Robots currently implemented

  • MiR100
  • Universal Robots: UR3, UR3e, UR5, UR5e, UR10, UR10e, UR16

WARNING for ROS Kinetic users

The compatibility of the Universal Robots environments with ROS Kinetic has been maintained until version v0.1.8 included. After this version we integrated a refactored version of the universal_robot repository which is not compatible with ROS Kinetic. To use the UR environments on ROS kinetic you need to use v0.1.8 of the robo-gym package and v.0.1.8 of the robo-gym-robot-servers. See #16 for more details.

Installation

Ubuntu 20.04 - ROS Noetic - Python [>3.7]

  1. Setup your computer to accept software from packages.ros.org
sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list' && sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654
  1. Install the required packages
sudo apt-get update && sudo apt-get install apt-utils build-essential psmisc vim-gtk git swig sudo libcppunit-dev python3-catkin-tools python3-rosdep python3-pip python3-rospkg python3-future python3-osrf-pycommon
  1. Open a new terminal and set the environment variables. Use the same terminal for all the installation steps.
# Set robo-gym ROS workspace folder
export ROBOGYM_WS=~/robogym_ws 
# Set ROS distribution
export ROS_DISTRO=noetic
  1. Create a workspace folder in the home folder of your PC and clone this repository
mkdir -p $ROBOGYM_WS/src && cd $ROBOGYM_WS/src && git clone https://github.com/jr-robotics/robo-gym-robot-servers.git
  1. Clone required packages, build the workspace and install required python modules
git clone -b $ROS_DISTRO https://github.com/jr-robotics/mir_robot.git
git clone -b $ROS_DISTRO https://github.com/jr-robotics/universal_robot.git
git clone -b v0.7.1-dev https://github.com/jr-robotics/franka_ros_interface
git clone https://github.com/jr-robotics/franka_panda_description
git clone -b ${ROS_DISTRO}-devel https://github.com/jr-robotics/panda_simulator
git clone https://github.com/orocos/orocos_kinematics_dynamics
cd orocos_kinematics_dynamics && git checkout b35c424e77ebc5b7e6f1c5e5c34f8a4666fbf5bc
cd $ROBOGYM_WS
sudo apt-get update
sudo rosdep init
rosdep update
rosdep install --from-paths src -i -y --rosdistro $ROS_DISTRO
catkin init
source /opt/ros/$ROS_DISTRO/setup.bash
catkin build
pip3 install robo-gym-server-modules scipy numpy
pip3 install --upgrade protobuf
  1. Add the sourcing of ROS and the ROS workspace to your .bashrc file:
printf "source /opt/ros/$ROS_DISTRO/setup.bash\nsource $ROBOGYM_WS/devel/setup.bash" >> ~/.bashrc

Ubuntu 18.04 - ROS Melodic - Python 2

Click to expand

  1. Setup your computer to accept software from packages.ros.org
sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list' && sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654
  1. Install the required packages
sudo apt-get update && sudo apt-get install apt-utils build-essential psmisc vim-gtk git swig sudo libcppunit-dev python-catkin-tools python-rosdep python-pip python-rospkg python-future
  1. Open a new terminal and set the environment variables. Use the same terminal for all the installation steps.
# Set robo-gym ROS workspace folder
export ROBOGYM_WS=~/robogym_ws 
# Set ROS distribution
export ROS_DISTRO=melodic
  1. Create a workspace folder in the home folder of your PC and clone this repository
mkdir -p $ROBOGYM_WS/src && cd $ROBOGYM_WS/src && git clone https://github.com/jr-robotics/robo-gym-robot-servers.git
  1. Clone required packages, build the workspace and install required python modules
git clone -b $ROS_DISTRO https://github.com/jr-robotics/mir_robot.git
git clone -b $ROS_DISTRO https://github.com/jr-robotics/universal_robot.git
git clone -b v0.7.1-dev https://github.com/jr-robotics/franka_ros_interface
git clone https://github.com/jr-robotics/franka_panda_description
git clone -b ${ROS_DISTRO}-devel https://github.com/jr-robotics/panda_simulator
git clone https://github.com/orocos/orocos_kinematics_dynamics
cd orocos_kinematics_dynamics && git checkout b35c424e77ebc5b7e6f1c5e5c34f8a4666fbf5bc
cd $ROBOGYM_WS
sudo apt-get update
sudo rosdep init
rosdep update
rosdep install --from-paths src -i -y --rosdistro $ROS_DISTRO
catkin init
source /opt/ros/$ROS_DISTRO/setup.bash
catkin build
pip install --upgrade pip
pip install robo-gym-server-modules scipy numpy
  1. Add the sourcing of ROS and the ROS workspace to your .bashrc file:
printf "source /opt/ros/$ROS_DISTRO/setup.bash\nsource $ROBOGYM_WS/devel/setup.bash" >> ~/.bashrc

How to use

MiR100

Simulated Robot

Simulated Robot Servers are handled by the Server Manager. If you want to manually start a Simulated Robot Server use:

roslaunch mir100_robot_server sim_robot_server.launch gui:=true

Real Robot

  • Connect to the robot's network

In a terminal window:

  • Set ROS Master IP: export ROS_MASTER_URI=http://192.168.12.20:11311
  • Launch MiR100 Robot Server roslaunch mir100_robot_server real_robot_server.launch gui:=true

Universal Robots

Simulated Robot

Simulated Robot Servers are handled by the Server Manager. If you want to manually start a Simulated Robot Server use:

roslaunch ur_robot_server ur_robot_server.launch ur_model:=ur10  gui:=true

Real Robot Server

Install UR ROS Driver

To control the UR Robots we use the new UR ROS Driver. At the current status the UR ROS Driver and the Universal_robot package use two different robot descriptions, for this reason it is needed to setup the UR ROS Driver in a separate workspace to avoid conflicts between the two packages.

# Source ROS 
source /opt/ros/$ROS_DISTRO/setup.bash

# Create a new folder for the workspace
mkdir -p ~/urdriver_ws/src
cd ~/urdriver_ws
catkin init

# Clone the necessary packages
cd ~/urdriver_ws/src
git clone https://github.com/jr-robotics/Universal_Robots_ROS_Driver.git
git clone -b calibration_devel https://github.com/fmauch/universal_robot.git

# Install dependencies
cd ~/urdriver_ws
sudo apt update -qq
rosdep update
rosdep install --from-paths src --ignore-src -y

# Build the workspace
catkin build

For additional instructions on how to setup the driver on the robot follow the README of the UR ROS Driver.

How to use

NOTE: The following instructions and command lines have been written for the UR 10 but they apply to all the supported UR robots, for instance for using the UR 5 Robot Server it is sufficient to replace ur10 with ur5 in all the following command lines.

  • Connect to the robot's network

In a terminal window start the UR ROS driver:

# Source ROS 
source /opt/ros/$ROS_DISTRO/setup.bash

# source the UR ROS Driver workspace
source ~/urdriver_ws/devel/setup.bash

# start the Driver (replace with the IP of your robot)
roslaunch ur_robot_driver ur10_bringup.launch robot_ip:=192.168.12.70

In another terminal window start the Robot Server

# Source ROS 
source /opt/ros/$ROS_DISTRO/setup.bash

# source robo-gym workspace
source ~/robogym_ws/devel/setup.bash

# start the Robot Server
roslaunch ur_robot_server ur_robot_server.launch ur_model:=ur10 real_robot:=true gui:=true max_torque_scale_factor:=0.5 max_velocity_scale_factor:=0.5 speed_scaling:=0.5

Troubleshooting

The Robot Server uses the standard ROS logging system, you can find the latest log of the Robot Server at: .ros/log/latest/robot_server-*.log

Examples

See example_robot_server for a basic implementation of a Robot Server reduced to its minimum form. The example implements a Robot Server for the robot MiR100 with basic functionality and it is meant as a good place to start from to implement a Robot Server for your own robot.

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].