|
1 2 3 4 5 6 7 |
#include <sensor_msgs/point_cloud_conversion.h> sensor_msgs::PointCloud2 point_cloud2; sensor_msgs::PointCloud point_cloud; sensor_msgs::convertPointCloudToPointCloud2(point_cloud, point_cloud2); sensor_msgs::convertPointCloud2ToPointCloud(point_cloud2, point_cloud); |
Converting sensor_msgs::PCLPointCloud2 to sensor_msgs::PointCloud and reverse Read More »
First, install the necessary package:
|
1 |
sudo apt-get install ros-indigo-joy |
make sure your joystick is working:
|
1 |
sudo jstest /dev/input/js0 |
also, make sure your controller has correct permissions:
|
1 |
ls -l /dev/input/js0 |
The permission on the last column must be rw, if it “–” like this:
|
1 |
crw-rw-r--+ 1 root root 13, 0 May 18 12:12 /dev/input/js0 |
then correct the permission:
|
1 |
sudo chmod a+rw /dev/input/js0 |
run the Joy node and roscore:
|
1 2 3 |
roscore rosparam set joy_node/dev "/dev/input/js0" rosrun joy joy_node |
The joystick data are being published under
Controlling your robot with joystick and reading data from it Read More »
Real-time object recognition and 6DOF pose estimation with PCL pointcloud and ROS. This approach is based on normal coherence
Real time object recognition and 6DOF pose estimation with PCL pointcloud and ROS Read More »
Here is an example of obtaining occupancy grid from sensory data of turtlebot robot. 1.First you need to install all dependencies for gazebo and turtlebot and octomap server:
|
1 |
sudo apt-get install ros-kinetic-gmapping ros-kinetic-turtlebot-gazebo ros-kinetic-turtlebot-simulator ros-kinetic-turtlebot-teleop |
2. Launch gazebo in a simulated environment:
|
1 |
roslaunch turtlebot_gazebo turtlebot_world.launch |
3.Launch RVIZ to view the published data
|
1 |
roslaunch turtlebot_rviz_launchers view_robot.launch |
3.Move your robot via keyboard:
|
1 |
roslaunch turtlebot_teleop keyboard_teleop.launch |
to learn how to move the robot with
Making occupancy grid map in ROS from gazebo with Octomap Read More »
Rapidly-exploring random trees (RRT) and their variant are a very power solution for solving motion planning problem in robotics, but they suffer from finding an optimise solution and the generated path is usually jerky with redundant movements. Sample based-optimisation-based planners benefit the robustness of RRT and the possibility of imposing a cost function. Here in this work, I
Sample based-optimisation-based planner with signed distance fields cost map Read More »
Limited-Memory CMA-ES (LM-CMA-ES) is a variation of CMA-ES which has been tailored for large-scale optimisation with limited memory. As a warm up here, I have used this algorithm to solve the min point of the following function: $$ z= -( 4 \times e^{- ( (x-4)^2 +(y-4)^2 ) }+ 2 \times e^{- ( (x-2)^2 +(y-2)^2 ) } )$$ The function
Solving of optimisation problem with evolutionary algorithm (LM-CMA-ES) Read More »
In many applications, you need to track an object. One simple method is color based tracking. I have developed a simple tool for that with OpenCV. All you have to do is just to adjust the High and Low values of HSV slider in the left window till you filter the image and you only see your
Colour based object Tracking with OpenCV Read More »
In this tutorial, I will show you how to estimate optical flow based on Lucas–Kanade method. This project has the following scripts: Optical_flow_estimation, myFlow, myWarp, computeColor, flowToColor. The myFlow does the main job, it gets two images and a window length (patch length) and a threshold for accepting the optical flow. In the following, you see the myFlow. You can uncomment figure function calls
Lucas–Kanade method optical flow with MATLAB Read More »
It quite often happens that you need to send a CMake parameter to your catkin project, for instance, you need to build your code for debugging mode. The correct syntax is:
|
1 |
catkin_make -DCMAKE_BUILD_TYPE="Release" |
another example:
|
1 |
catkin_make -DCMAKE_VERBOSE_MAKEFILE=ON |
read more: http://wiki.ros.org/catkin/Tutorials/using_a_workspace
Send CMake param to catkin Read More »
