This package is intended to be a migration package of mir_robot using ros1 to ros humble. It is currently still under heavy development - to be used with caution! The following packages have been migrated to humble:
- mir_description
- mir_driver
- mir_gazebo
- mir_msgs
- mir_navigation
This repo contains a ROS driver and ROS configuration files (URDF description, Gazebo launch files, move_base config, bringup launch files, message and action descriptions) for the MiR robots. This is a community project created by us (DFKI, the German Research Center for Artificial Intelligence) to use the MiR Robots with ROS. We are not affiliated with Mobile Industrial Robots. If you find a bug or missing feature in this software, please report it on the issue tracker.
mir_actions: Action definitions for the MiR robotmir_description: URDF description of the MiR robotmir_dwb_critics: Plugins for the dwb_local_planner used in Gazebomir_driver: A reverse ROS bridge for the MiR robotmir_gazebo: Simulation specific launch and configuration files for the MiR robotmir_msgs: Message definitions for the MiR robotmir_navigation: move_base launch and configuration files
If you haven't already installed ROS2 on your PC, you need to add the ROS2 apt repository. This step is necessary for either binary or source install.
For a source install, run the commands below instead of the command from the "binary install" section.
# create a ros2 workspace
mkdir -p ~/ros2_ws/src
cd ~/ros2_ws/
# clone mir_robot into the ros2 workspace
git clone -b humble-devel https://github.com/ATh0ft/mir_robot src/mir_robot
# use vcs to fetch linked repos
vcs import < src/mir_robot/ros2.repos src --recursive
# use rosdep to install all dependencies (including ROS itself)
sudo apt update
sudo apt install -y python3-rosdep
rosdep update --rosdistro=humble
rosdep install --from-paths src --ignore-src -r -y --rosdistro humble
# build all packages in the workspace
source /opt/ros/humble/setup.bash
cd ~/ros2_ws
colcon buildYou must source the workspace in each terminal you want to work in:
source ~/ros2_ws/install/setup.bashAlternatively you can add the following line to the end of your ~/.bashrc, and then
close and reopen all terminals:
echo "source ~/ros2_ws/install/setup.bash" >> ~/.bashrc### gazebo
ros2 launch mir_gazebo mir_gazebo_launch.py world:=maze rviz_config_file:=$(ros2 pkg prefix mir_navigation)/share/mir_navigation/rviz/mir_nav.rviz
### localization (existing map)
ros2 launch mir_navigation amcl.py use_sim_time:=true map:=$(ros2 pkg prefix mir_navigation)/share/mir_navigation/maps/maze.yaml
### navigation
ros2 launch mir_navigation navigation.py use_sim_time:=true-
HEADLESS MODE: To run the simulation without the gazebo graphical interface (performance improvement) add to the gazebo launch command:
gui:=false
Initialize the position with "2D Pose Estimate". You should see sensor inputs and costmap by now. Now, you can use the "2D Goal Pose" tool in RViz to set a navigation goal for move_base
### gazebo:
ros2 launch mir_gazebo mir_gazebo_launch.py world:=maze
### mapping (slam_toolbox)
ros2 launch mir_navigation mapping.py use_sim_time:=true slam_params_file:=$(ros2 pkg prefix mir_navigation)/share/mir_navigation/config/mir_mapping_async_sim.yaml
### navigation (optional)
ros2 launch mir_navigation navigation.py use_sim_time:=true- switch on MiR base
- connect to MiR_R??? wifi (password "mirex4you"), for example from your Android phone/tablet
- disable other network connections (mobile data / LAN / etc.)
- open mir.com (192.168.12.20) in Chrome (!)
- log in (admin/mir4you)
The internal robot PC's is not synchronized (for example via NTP), so it tends
to get out of sync quickly (about 1 second per day!). This causes TF transforms
timing out etc. and can be seen using tf_monitor (the "Max Delay" is about
3.3 seconds in the following example, but should be less than 0.1 seconds):
Since MiR is running a roscore (ROS1), the following tf_monitor can be excecuted after sourcing ROS1 (i.e. noetic) first:
source /opt/ros/noetic/setup.bash
export ROS_MASTER_URI=http://192.168.12.20:11311$ rosrun tf tf_monitor
Frames:
Frame: /back_laser_link published by unknown_publisher Average Delay: 3.22686 Max Delay: 3.34766
Frame: /base_footprint published by unknown_publisher Average Delay: 3.34273 Max Delay: 3.38062
Frame: /base_link published by unknown_publisher Average Delay: 3.22751 Max Delay: 3.34844
[...]
All Broadcasters:
Node: unknown_publisher 418.344 Hz, Average Delay: 0.827575 Max Delay: 3.35237
Node: unknown_publisher(static) 465.362 Hz, Average Delay: 0 Max Delay: 0If you don't have a ROS1 distro installed, you'll need to run the mir_driver first and execute the following once a connection is established:
ros2 run tf2_ros tf2_monitor- In the Mir dashboard (mir.com in the Mir-Wifi), go to "Service" -> "Configuration" -> "System settings" -> "Time settings" -> "Set device time on robot" Use load from device to sync with the system time!
From the package mir_restapi a node called mir_restapi_server can be run, which can execute a time sync REST API call from the driver's host machine to the Mir's host.
-
Launch the node with the API key and mir hostname's IP address
ros2 run mir_restapi mir_restapi_server --ros-args -p mir_hostname:='MIR_IP_ADDR' -p mir_restapi_auth:='YOUR_API_KEY' -
Call the time sync service from terminal by invoking
ros2 service call /mir_100_sync_time std_srvs/Trigger
Keep in mind, that the time sync causes the mir_bridge to freeze. Therefore online time syncs are not recommended.
- go to "Service" -> "Configuration" -> "Launch menu", start "Planner"; this starts
move_baseandamclon the robot
- go to "Manual", press yellow button (LEDs change from yellow to blue); now the robot can be teleoperated
If the robot's localization is lost:
- go to "Service" -> "Command view" -> "Set start position" and click + drag to current position of robot in the map
- click "Adjust"
ros2 launch mir_driver mir_launch.py- The driver automatically launches rviz to visualize the topics and sensor messages. To disable use
rviz_enabled:=falseas a launch argument - The driver automatically launches a seperate teleop window to manually move the robot using your keyboard. To disable use
teleop_enabled:=falseas a launch argument
### driver:
ros2 launch mir_driver mir_launch.py
### mapping (slam_toolbox)
ros2 launch mir_navigation mapping.py use_sim_time:=false slam_params_file:=$(ros2 pkg prefix mir_navigation)/share/mir_navigation/config/mir_mapping_async.yaml
### navigation (optional)
ros2 launch mir_navigation navigation.py use_sim_time:=false### combined launch file:
ros2 launch mir_navigation mir_mapping_launch.py### driver:
ros2 launch mir_driver mir_launch.py
### localization (amcl)
ros2 launch mir_navigation amcl.py use_sim_time:=false map:={path to existing map}
### navigation
ros2 launch mir_navigation navigation.py use_sim_time:=false### combined launch file:
ros2 launch mir_navigation mir_nav_launch.py map:={path to /name of existing map}As mentioned before, you can launch the differnet modules seperately or use the combined launch commands below:
In Simulation run:
ros2 launch mir_navigation mir_mapping_sim_launch.py
On MiR run:
ros2 launch mir_navigation mir_mapping_launch.py
Both commands launch the simulation / driver and SLAM node.
To save the created map, use the rviz plugin "Save Map" and "Serialize Map". From time to time segmentation faults or timeouts occur, so make sure your map is saved before shutting down the connection.
The given launch commands will create a fresh new map of the environment. If you like to adapt an existing map (must be serialized!) you can deserialize it using the rviz slam_toolbox plugin.
| Select map to deserialize | and continue mapping |
|---|---|
-
NAVIGATION: Navigation is disabled per default. If you like to teleoperate the robot using nav2 add:
navigation_enabled:=true
| Mapping.. | ..using nav2 |
|---|---|
As mentioned before, you can launch the differnet modules seperately or use the combined launch commands below:
In Simulation run:
ros2 launch mir_navigation mir_nav_sim_launch.py
On MiR run:
ros2 launch mir_navigation mir_nav_launch.py map:={path to existing map}
Both commands launch the simulation / driver and localization (amcl) using an existing map.
-
MAP: In Simulation the map defaults to the maze map. On the real robot a map should be passed via the
mapargumentmap:= {path_to_map_yaml} world:={world_file} # simulation only: add respective world
Once the simulation / driver is running and rviz is started, you need to set the initial pose on the map. This doesnt have to be accurate, just a reference and amcl will do the refinement. To refine, move the robot around a little using the teleop window and the scan will eventually match the map.
| Initialize Pose | Drifted pose | Refined pose |
|---|---|---|
When using a namespace for your robot, add the --ros-args -p namespace:=my_namespace to the launch files.
The driver, description and gazebo packages work out of the box.
However, to use the navigation stack the corresponding config.yaml files need to be adapted to match the renamed topic.
The navigation cmd_vel topic is automatically remapped by adding the namespace in the navigation.py launch file.