kinova jaco2 和realsense d435i手眼标定

1 环境配置

1.1 visip

sudo apt-get install ros-melodic-visp

cd ~/catkin_ws/src
git clone  https://github.com/lagadic/vision_visp.git
cd ..
catkin_make --pkg visp_hand2eye_calibration

1.2 aruco_ros

cd ~/catkin_ws/src
git clone  https://github.com/pal-robotics/aruco_ros
cd ..
catkin_make

1.3 easy_handeye

https://github.com/IFL-CAMP/easy_handeye

cd ~/catkin_ws/src
git clone https://github.com/IFL-CAMP/easy_handeye
cd ..  
rosdep install -iyr --from-paths src
catkin_make

1.4 moveit

sudo apt-get install ros-melodic-moveit
sudo apt-get install ros-melodic-trac-ik

2 验证

# 相机
roslaunch realsense2_camera rs_camera.launch
# 机械臂
roslaunch kinova_bringup kinova_robot.launch kinova_robotType:=j2n6s300
# moveit
roslaunch j2n6s300_moveit_config j2n6s300_demo.launch

3 标定过程

3.1 launch文件

在~/catkin_ws/src/easy_handeye/easy_handeye/launch文件夹下新建kinova_realsense.launch

文件内容：

<launch>
    <arg name="namespace_prefix" default="kinova_d435i_handeyecalibration" />
 
    <arg name="marker_size" value="0.1" />
    <arg name="marker_id" value="582" />
 
    <include file="$(find realsense2_camera)/launch/rs_camera.launch" >
    </include>
 
    <!-- start ArUco -->
    <node name="aruco_tracker" pkg="aruco_ros" type="single">
        <remap from="/camera_info" to="/camera/color/camera_info" />
        <remap from="/image" to="/camera/color/image_raw" />
        <param name="image_is_rectified" value="true"/>
        <param name="marker_size"        value="$(arg marker_size)"/>
        <param name="marker_id"          value="$(arg marker_id)"/>
        <param name="reference_frame"    value="camera_link"/>
        <param name="camera_frame"       value="camera_depth_optical_frame"/>
        <!--<param name="camera_frame"       value="_color_optical_frame"/>-->
        <param name="marker_frame"       value="camera_marker" />
 
    </node>
 
    <!-- start the robot -->
    <include file="$(find kinova_bringup)/launch/kinova_robot.launch">
    </include>
    <include file="$(find j2n6s300_moveit_config)/launch/j2n6s300_demo.launch">
    </include>

    <node name="joint_state_publisher" pkg="joint_state_publisher" type="joint_state_publisher">

    </node>
 
    <!-- start easy_handeye -->
    <include file="$(find easy_handeye)/launch/calibrate.launch" >
        <arg name="namespace_prefix" value="$(arg namespace_prefix)" />
        <arg name="eye_on_hand" value="false" />
 
        <arg name="tracking_base_frame" value="camera_link" />
        <arg name="tracking_marker_frame" value="camera_marker" />
        <arg name="robot_base_frame" value="j2n6s300_link_base" />
        <arg name="robot_effector_frame" value="j2n6s300_link_6" />
        <!--disable automatic robot movement-->
        <arg name="freehand_robot_movement" value="false" />
        
        <arg name="robot_velocity_scaling" value="0.5" />
        <arg name="robot_acceleration_scaling" value="0.2" />
    </include>
 
</launch>

3.2 准备aruco码

https://chev.me/arucogen/

Dictionary: Original ArUco

Marker ID:582

Marker size:100

# 注：Marker ID 必须为~/catkin_ws/src/aruco_ros/aruco_ros/etc文件夹中存在的ID，且Dictionary必须为Original ArUco，生成pdf后，原尺寸打印

3.3 标定

（1） 将calibrate.launch文件中的第十三行move_group的default value改为arm

（2）运行kinova_realsense.launch，只能得到两个rviz图形界面,且报错原因不固定，一直在变，应该是python解释器版本冲突问题导致cv2导入出问题：

先

python -m pip install opencv-contrib-python

再运行launch，如果没解决：

# 打开文件 ~/catkin_ws/src/easy_handeye/easy_handeye/src/easy_handeye/handeye_calibration_backend_opencv.py
# 将
import cv2
# 改为
import sys
sys.path.remove('/opt/ros/kinetic/lib/python2.7/dist-packages')
import cv2
sys.path.append('/opt/ros/kinetic/lib/python2.7/dist-packages')

（3）调不出image-view窗口：

# 另开窗口，运行：
rqt_image_view
# 话题选择/aruco_tracker/result

（4）eye on base:将aruco码固定在机械臂末端执行器上

（5）Cannot calibrate from current position：手动调整机械臂位置，调整一次，采样一次，采样17次后，点击compute，得到外参

参考链接

https://blog.csdn.net/miss_future/article/details/111826016
https://blog.csdn.net/weixin_45393946/article/details/103580657