代码拉取完成，页面将自动刷新
This package wraps the hand-eye calibration routine from the ViSP library
(contained in the visp_hand2eye_calibration package) to provide a simple
camera pose estimation solution. Input is expected as transformations published in tf.
Additionally, a method for saving and publishing the resulting calibration is provided. Computing and using a calibration can be achieved by including/starting a single launch file respectively.
The rqt_easy_handeye package (also in this repository) provides a GUI to sample the data, compute and save the
calibration.
Another GUI for automatically moving the robot during the calibration procedure is included in the same package. This script uses MoveIt! to rotate and translate the end effector around the starting position. Its usage is optional, as you can also move the robot by hand in teaching mode (if the robot's ROS driver supports reading the robot position in said mode).
You can try out this software in a simulator, through the
easy_handeye_demo package. This package also serves as an
example for integrating easy_handeye into your own launch scripts.
If you are unfamiliar with Tsai's hand-eye calibration [1], it can be used in two ways:
A relevant example of an eye-on-base calibration is finding the position of an RGBD camera with respect to a robot for object collision avoidance, e.g. with MoveIt!: an example launch file is provided to perform this common task between an Universal Robot and a Kinect through aruco. eye-on-hand can be used for vision-guided tasks.
The (arguably) best part is, that you do not have to care about the placement of the auxiliary marker (the one on the table in the eye-in-hand case, or on the robot in the eye-on-base case). The algorithm will "erase" that transformation out, and only return the transformation you are interested in.
| eye-on-base | eye-on-hand |
|---|---|
 |
 |
cd ~/catkin_ws/src # replace with path to your workspace
git clone https://github.com/IFL-CAMP/easy_handeye
cd .. # now we are inside ~/catkin_ws
rosdep install -iyr --from-paths src
catkin build
Two launch files, one for computing and one for publishing the calibration respectively, are provided to be included in your own. The default arguments should be overridden to specify the correct tf reference frames, and to avoid conflicts when using multiple calibrations at once.
The suggested integration is:
handeye_calibrate.launch file, which includes the robot's and tracking system's launch files, as well as
easy_handeye's calibrate.launch as illustrated below in the next section "Calibration"easy_handeye's publish.launch
as illustrated below in the section "Publishing"For both use cases, you can either launch the calibrate.launch
launch file, or you can include it in another launchfile as shown below. Either
way, the launch file will bring up the visp_hand2eye_calibration solver, along with an
integration script. By default, the integration script will interactively ask you
to accept or discard each sample. At the end, the parameters will be saved in a yaml file.
<launch>
<!-- (start your robot's MoveIt! stack, e.g. include its moveit_planning_execution.launch) -->
<!-- (start your tracking system's ROS driver) -->
<include file="$(find easy_handeye)/launch/calibrate.launch">
<arg name="eye_on_hand" value="true"/>
<!-- you can choose any identifier, as long as you use the same for publishing the calibration -->
<arg name="namespace" value="my_eih_calib"/>
<!-- fill in the following parameters according to your robot's published tf frames -->
<arg name="robot_base_frame" value="/base_link"/>
<arg name="robot_effector_frame" value="/ee_link"/>
<!-- fill in the following parameters according to your tracking system's published tf frames -->
<arg name="tracking_base_frame" value="/optical_origin"/>
<arg name="tracking_marker_frame" value="/optical_target"/>
</include>
</launch>
<launch>
<!-- (start your robot's MoveIt! stack, e.g. include its moveit_planning_execution.launch) -->
<!-- (start your tracking system's ROS driver) -->
<include file="$(find easy_handeye)/launch/calibrate.launch">
<arg name="eye_on_hand" value="false"/>
<arg name="namespace" value="my_eob_calib"/>
<!-- fill in the following parameters according to your robot's published tf frames -->
<arg name="robot_base_frame" value="/base_link"/>
<arg name="robot_effector_frame" value="/ee_link"/>
<!-- fill in the following parameters according to your tracking system's published tf frames -->
<arg name="tracking_base_frame" value="/optical_origin"/>
<arg name="tracking_marker_frame" value="/optical_target"/>
</include>
</launch>
A GUI for automatic robot movement is provided by the rqt_easy_handeye package. Please refer to its documentation.
The following tips are given in [1], paragraph 1.3.2.
The publish.launch starts a node that publishes the transformation found during calibration in tf.
The parameters are automatically loaded from the yaml file, according to the specified namespace.
For convenience, you can include this file within your own launch script. You can include this file multiple times to
publish many calibrations simultaneously; the following example publishes one eye-on-base and one eye-in-hand calibration:
<launch>
<!-- (start your robot's MoveIt! stack, e.g. include its moveit_planning_execution.launch) -->
<!-- (start your tracking system's ROS driver) -->
<include file="$(find easy_handeye)/launch/publish.launch">
<arg name="namespace" value="my_eob_calib"/> <!-- use the same namespace that you used during calibration! -->
</include>
<include file="$(find easy_handeye)/launch/publish.launch">
<arg name="namespace" value="my_eih_calib"/> <!-- use the same namespace that you used during calibration! -->
</include>
</launch>
You can have any number of calibrations at once (provided you specify distinct namespaces).
If you perform again any calibration, you do not need to do anything: the next time you start the system,
the publisher will automatically fetch the latest information. You can also manually restart the publisher
nodes (e.g. with rqt_launch), if you don't want to shut down the whole system.
Please check the troubleshooting
This is a perfect example of an eye-on-base calibration. You can take a look at this example launch file written for an UR5 and a Kinect via aruco_ros.
You can pass the argument freehand_robot_movement:=true to calibrate.launch.
You can just override the namespace argument of calibrate.launch to be always different, such that they will never collide. Using the same namespace as argument to multiple inclusions of publish.launch will allow you to publish each calibration in tf.
You could perform the eye-on-base calibration against the same tracking system, and concatenate the results.
You could perform the eye-on-base calibration against the same robot, and concatenate the results. This will work also if the tracking systems are completely different and do not use the same markers.
[1] Tsai, Roger Y., and Reimar K. Lenz. "A new technique for fully autonomous and efficient 3D robotics hand/eye calibration." Robotics and Automation, IEEE Transactions on 5.3 (1989): 345-358.
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。