Ask Your Question

Athria's profile - activity

2016-09-22 08:53:58 -0600 received badge  Nice Question (source)
2016-04-01 06:11:35 -0600 received badge  Taxonomist
2016-01-04 09:40:27 -0600 received badge  Nice Question (source)
2015-10-12 01:27:55 -0600 received badge  Famous Question (source)
2015-10-12 01:26:32 -0600 commented answer Pose going up and constant "Visual Odometry got Lost!" message

Sorry Sai, I missed your comment, I did not manage to get good results in the end. I ended up working with a different monocular camera.

2015-10-06 05:57:17 -0600 marked best answer Camera calibration parameters not appropriate for SVO package

Hello, I have been trying to use the SVO package using Ubuntu 12.04 and ROS Hydro, but I ran into trouble with the calibration file. In the SVO calibration guidelines says that the camera_calibration package can be used to obtain a calibration file that works with SVO, but the format of the calibration file expected by the SVO looks like this:

cam_model: Pinhole cam_width: 752

cam_height: 480 cam_fx: 414.536145

cam_fy: 414.284429 cam_cx: 348.804988

cam_cy: 240.076451 cam_d0: -0.283076

cam_d1: 0.066674 cam_d2: 0.000896

cam_d3: 0.000778

And the one obtained with the camera_calibration, after convertir to yaml using the camera_calibration_parsers looks like this:

image_width: 1024 image_height: 768 camera_name: narrow_stereo camera_matrix: rows: 3 cols: 3
data: [1114.338842, 0, 488.044082, 0, 1483.616573, 384.580052, 0, 0, 1] distortion_model: plumb_bob distortion_coefficients: rows: 1
cols: 5 data: [0.089323, -0.327338, -0.003856, -0.002099, 0] rectification_matrix: rows: 3
cols: 3 data: [1, 0, 0, 0, 1, 0, 0, 0, 1] projection_matrix: rows: 3
cols: 4 data: [1117.866699, 0, 485.532623, 0, 0, 1492.567993, 382.458084, 0, 0, 0, 1, 0]

I do not see how to make SVO work with the calibration file I'm getting and I have also not found a way to convert said file to the format that works.

I found another forum question where a person with my same problem got to the conclusion that the camera_calibration file didn't work with SVO and that the ATAN format file from ethzasl_ptam had to be used instead. But when I try to implement the ptam package I get a missing header error that I haven't been able to solve either (it's this error, but the solutions found in that thread haven't worked for me neither in Hydro nor in Groovy). Which is why I need to make the camera_calibration file work.

Thank you very much in advance for any ideas or suggestions.

2015-07-22 06:47:55 -0600 commented answer Fovis_ros using freenect_launch has depth image format error

I looked a bit more into it. With a fresh install of both Fovis and the freenect_launch in Indigo (14.04.2) the Kinect works well, using the same launch file but with the respective <include file="$(find freenect_launch)/launch/freenect.launch">

2015-07-22 05:57:04 -0600 commented answer Fovis_ros using freenect_launch has depth image format error

Sorry I could not answer before, I read about some problems with the openni_launch and the Kinect in Indigo, but in Hydro it works just fine with the simple launch file. I am glad you could make it work.

2015-07-20 10:43:32 -0600 received badge  Famous Question (source)
2015-07-14 06:13:26 -0600 received badge  Teacher (source)
2015-07-14 04:50:20 -0600 commented answer Fovis_ros using freenect_launch has depth image format error

Too bad about openni, are you by any chance working from a virtual machine? I had a similar issue with one. I haven't used freenect, but if it publishes the required image and depth topics you might be able to use them by just changing the remaps and the upper include from the working launch file

2015-07-13 08:51:55 -0600 answered a question Fovis_ros using freenect_launch has depth image format error

Hello, I was indeed having your same problem and it was because of the launch file I was using, which was this one. I still don't know why it didn't work, but adding the oppeni_launch include to the example launch file that Miguel Massot linked above fixed my problem, I don't think it should be any different in your case because you use Indigo. My current, working, launch file is this one:

<launch>
   <include file="$(find openni_launch)/launch/openni.launch">
  </include>


  <arg name="camera" default="camera" />
  <node pkg="nodelet" type="nodelet" args="manager" name="nodelet_manager" />
  <node pkg="nodelet" type="nodelet" name="convert_openni_fovis" 
        args="load depth_image_proc/convert_metric nodelet_manager">
    <remap from="image_raw" to="$(arg camera)/depth_registered/sw_registered/image_rect_raw"/>
    <remap from="image" to="$(arg camera)/depth_registered/image_rect"/>
  </node>

  <node pkg="fovis_ros" type="fovis_mono_depth_odometer" name="kinect_odometer" >
    <remap from="/camera/rgb/image_rect" to="$(arg camera)/rgb/image_rect_mono" />
    <remap from="/camera/rgb/camera_info" to="$(arg camera)/rgb/camera_info" />
    <remap from="/camera/depth_registered/camera_info" to="$(arg camera)/depth_registered/sw_registered/camera_info" />
    <remap from="/camera/depth_registered/image_rect" to="$(arg camera)/depth_registered/image_rect" />
    <param name="approximate_sync" type="bool" value="True" />
    <param name="publish_tf" type="bool" value="False" />
  </node>

</launch>

Hope it helps.

2015-07-09 07:43:04 -0600 received badge  Notable Question (source)
2015-07-07 16:11:28 -0600 received badge  Famous Question (source)
2015-06-17 12:22:29 -0600 received badge  Famous Question (source)
2015-05-28 08:46:02 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

And thank you for pointing out the control flaw, I will rethink how I'm using the tf measurements to account for deceleration.

2015-05-28 08:44:11 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

I am plotting the output of the /odom topic (that is published when I run the turtlebot_gazebo for the simulation and minimal.launch for the real robot), I thought that topic was giving me the combined odometry of IMU and wheels.

2015-05-28 08:33:44 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

robot_pose_ekf is being called on the turtlebot_bringup/package.xml as run_depend, but the odom_combined->base_footprint frame is not being published, the only one that appears is odom->base_footprint. I assumed that the odom-base_footprint was coming from the ekf since I don't have other odometry

2015-05-28 03:21:24 -0600 received badge  Notable Question (source)
2015-05-27 16:37:09 -0600 received badge  Popular Question (source)
2015-05-27 11:30:14 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

Sorry, I didn't read the last comment before. I thought the turtlebot's own odometry might be good enough since there are examples of people using the odom tf sucessfully to move in predefined trajectories, so maybe there's something wrong with my hardware instead of my code?

2015-05-27 11:23:16 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

and I tought the the cumulative error from the velocity would affect the real turtlebot but not the simulation. I did expect an improvement when using the tf because I don't depend on time or on the acurracy of the speed anymore and the odometry seems to work better than what the tf code shows

2015-05-27 11:17:34 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

Since I can compare the trajectory without odometry, with imu+wheel odometry and with the VOs. I thought the clock and loop errors wouldn't affect that much, since they didn't affect the turtlesim but maybe it got worse on gazebo because it is much heavier,

2015-05-27 11:12:33 -0600 commented answer Turtlebot not moving according to input (in simulation and reality)

Hello, thank you very much for the answer. My main goal is to test how the libfovis and viso2 visual odometry packages respond to different lightning conditions and environments, but for that I wanted a repeatable test so I thought the turtlebot was the best choice

2015-05-27 10:08:14 -0600 asked a question Turtlebot not moving according to input (in simulation and reality)

Hello, I'm using a Turtlebot with Kobuki base and running Ros Hydro on Ubuntu 12.04.

I need the Turtlebot to move in the shape of a square and guiding myself by this codes: albany , turtlebot motion and turtlebot tutorials, I put together a code that only sends the appropriate cmd_vel messages to make the robot move at a certain speed for a chosen time and another one that uses tf information from odom->base_footprint to make the robot move a chosen distance at a certain speed.

I was first testing the codes on turtlesim and they seemed to work well, but when I tested them on the gazebo turtlebot simulator and on the real turtlebot this was the outcome (obtained from the /odom topic on rviz):

Gazebo Simulation - From the code that doesn't use tf: Gazebo Simulation - From the code that doesn't use tf

Gazebo Simulation - From the code that uses the odom->base_footprint tf: Gazebo Simulation - From the code that uses the odom->base_footprint tf:

Real Turtlebot - From the code that doesn't use tf: Real Turtlebot - From the code that doesn't use tf

Real Turtlebot - From the code that uses the odom->base_footprint tf: Real Turtlebot - From the code that uses the odom->base_footprint tf

From what I've read the odom->base_footprint tf uses the wheel odometry and IMU data and the kobuki base already comes with a calibrated gyro, so I don't think the problem is in the odometry tf. Also, the movement of the turtlebot with the code that doesn't use the tf looks similar to the one the /odom topic shows.

The result from the real turtlebot is terrible, but I was surprised that even in the simulation the code doesn't work well. I don't really know how to improve this results, because I expected that the way to improve the first code was to use the one that implements the tf and that one is the one that works the worst.

Am I misusing the tfs or am I missing something particular about the turtlebot with the messages I'm sending? at least in the first code it looks as if the robot doesn't move as much as the speed would indicate but the tf should be indifferent to that. I read the similar questions in the FAQs but none of them help me solve this.

Thank you very much in advance and sorry for the rviz plots, I didn't find another way to get the trajectory of the robot.


The two codes are below:


Code that only sends the appropriate cmd_vel messages to make the robot move at a certain speed for a chosen time:

#!/usr/bin/env python
# http://library.isr.ist.utl.pt/docs/roswiki/rospy%282f%29Overview%282f%29Time.html
""" Example code of how to move a robot around the shape of a square. """

import roslib
import rospy
import math
import time
from geometry_msgs.msg import Twist


class square:  """ This example is in the form of a class. """

def __init__(self):
    """ This is the constructor of our class. """
    # register this function to be called on shutdown
    rospy.on_shutdown(self.cleanup)

    # publish to cmd_vel
    self.p = rospy.Publisher('cmd_vel', Twist)
#twist ...
(more)
2015-05-27 05:19:34 -0600 commented answer Trouble building fovis_ros on Hydro

I think when I was doing git clone it was downloading the indigo versions (I am really new with github) and that's why it wasn't working. I hope it helps

2015-05-27 05:18:54 -0600 commented answer Trouble building fovis_ros on Hydro

Hello Sai, I don't know if it will help you but this is exactly what worked for me in the end: I deleted what I had from fovis, then I downloaded (manually, not by git clone) the two folders (libfovis and fovis) from the hydro branch in github to the catkin/src/ folder and then it compiled well.

2015-05-26 23:41:41 -0600 received badge  Famous Question (source)
2015-05-26 23:37:20 -0600 marked best answer Trouble building fovis_ros on Hydro

Hello, I'm running Ubuntu 12.04 with ROS Hydro and wanted to test fovis_ros with a Kinect, but I'm having trouble building the package.

Following the advice given in this question I executed the following commands :

git clone https://github.com/srv/fovis.git

git clone https://github.com/srv/libfovis.git

So I had the fovis and libfovis folders inside catkin_ws/src.

Then I tried building with catkin_make and got the following messages at the end:

...
[ 98%] Built target fovis_ros_generate_messages
/home/ire/catkin_ws/src/fovis/fovis_ros/src/visualization.cpp:3:40: fatal error: libfovis/visual_odometry.hpp: No such file or directory
compilation terminated.
make[2]: * [fovis/fovis_ros/CMakeFiles/visualization.dir/src/visualization.cpp.o] Error 1
make[1]:
[fovis/fovis_ros/CMakeFiles/visualization.dir/all] Error 2
make: *
* [all] Error 2
Invoking "make" failed

I verified and the "visual_odometry.hpp" file is inside the libfovis/libfovis folder, like the rest of the files used by fovis_ros that don't seem to present an issue.

I tried building the libfovis library first, which gave no trouble and then adding fovis_ros but I got the exact same error. I also followed the advice from issue #11 but the problem remained.

Here is the complete log in case it's more useful.

Thank you in advance.

2015-05-25 14:38:24 -0600 marked best answer Pose going up and constant "Visual Odometry got Lost!" message

Hello, I'm using the viso2_ros' stereo node with Ubuntu 12.04 and ROS Hydro. My setup consists of two webcams attached to a steady surface at a distance of 17.3 cm from each other and calibrated with the stereo camera_calibration.

I am viewing in Rviz the Pose and Point_cloud published by the node and after a few seconds of running, the Pose starts shooting up:

the pose vector goes up from the point where the pink arrow is at

I also get a the "Visual Odometry got Lost!" message frequently. I checked the ~info topic and this was the outcome:

Messages published by the ~info topic

I read the FAQs for the package and I tried to apply the solutions given to people with similar issues. So I reset the odometer by calling the stereo_odometer/reset_pose service and changed the match_disp_tolerance parameter.

Reseting the odometer didn't work because the pose went back down to the grid but after a few seconds it was going up again.

I increased the match_disp_tolerance parameter from 5 (the value that it had by default) to 20 and then to 100. For some reason the number of "Visual Odometry got Lost!" messages increased with the parameter, and I think it worked the best with the original value.

changing match_disp_tolerance to 20

I thought the problem might be that the number of inliers was too low, but even if i changed the background drastically the number of inliers didn't remain high for long (sometimes I get a lot of inliers but after a few seconds, without moving the camera, they decrease to less than 10, then they go up again and so on). This is the image I was viewing for the messages on some of the screenshots above:

background

And this is the launch file I'm using:

<!-- Arguments -->
<arg name="camera" default="/stereo" /> <!-- The namespace where images are published -->


<!-- Run the camera -->
    <group ns="stereo" >
        <node pkg="uvc_camera" type="uvc_stereo_node" name="uvc_stereo_node">
            <param name="left/device" type="string" value="/dev/video1" />
            <param name="right/device" type="string" value="/dev/video2" />
    </node>
</group>

<!-- Run the ROS package stereo_image_proc -->
<group ns="$(arg camera)" >
    <node pkg="stereo_image_proc" type="stereo_image_proc" name="stereo_image_proc">
    </node>
</group>

<!-- Publish transforms -->

<node pkg="tf" type="static_transform_publisher" name="camera_broadcaster" args="0 0 0 0 0 0 1 base_link camera 100" />


<!-- Run the viso2_ros package -->

<node pkg="viso2_ros" type="stereo_odometer" name="stereo_odometer" output="screen">
    <remap from="stereo" to="$(arg camera)"/>
    <remap from="image" to="image_rect"/>
    <param name="match_disp_tolerance" type="int" value=“20” />  <!-- Set to 5 by default -->
</node>

<!-- Run Rviz -->   
<node pkg="rviz" type="rviz" name="rviz">
</node>

Since I was getting the "Visual Odometry got Lost!" message constantly, I decided to test the odometry of the stereo camera without the robot, that's why I publish the tf with arguments 0 0 0 0 0 0 1 base_link camera 100. I still have some trouble grasping the tfs so I didn't want to add any mistake with them to my current problem.

I'm not sure if I'm doing something wrong or if my cameras are not good enough to use the package ... (more)

2015-05-19 12:50:46 -0600 received badge  Notable Question (source)
2015-05-19 12:50:46 -0600 received badge  Popular Question (source)
2015-05-16 09:27:01 -0600 marked best answer Building cob_people_detection package on Hydro

Hello, I'm currently running Ros Hydro on Ubuntu 12.04 and I want to use a Kinect for face recognition.

I found the cob_people_detection package and downloaded cob_people_perception-hydro_dev to my catkin_ws/src/ folder, but when I try to build it with catkin_make I get errors concerning several configuration files, like this ones:

CMake Error at /opt/ros/hydro/share/catkin/cmake/catkinConfig.cmake:75 (find_package): Could not find a configuration file for package cob_image_flip.

CMake Error at /opt/ros/hydro/share/catkin/cmake/catkinConfig.cmake:75 (find_package): Could not find a configuration file for package cob_perception_msgs.

Here is the complete log.

I tried deleting the devel and build folders, and then building, but I get the same error. I don't have a similar problem with any of the other packages I'm using, so I'm not sure if I'm missing something here.

Thank you in advance,

2015-05-16 09:26:58 -0600 commented answer Building cob_people_detection package on Hydro

Thank you very much, with the first suggestion the compilation errors remained, but ignoring the packages you mentioned in the second one it compiled without errors. Thank you again.

2015-05-15 08:41:54 -0600 received badge  Notable Question (source)
2015-05-11 07:39:04 -0600 commented answer Building cob_people_detection package on Hydro

other packages to see if it made any difference (I once had an issue with two conflicting packages), but it didn't help. Today I downloaded the common and perception packages once more and compiled several times, but it's still the same error. I tried deleting the devel and build folders too (2/2)

2015-05-11 07:36:58 -0600 commented answer Building cob_people_detection package on Hydro

Hello, sorry but it is still trowing errors when I tried to build ( https://gist.github.com/Athria/c575b2... ), first I downloaded again both packages from github and tried with catkin_make and catkin_make -j1, since none of them worked and I couldn't fix the error I tried deleting (1/2)

2015-05-08 04:40:27 -0600 commented answer Building cob_people_detection package on Hydro

I also tried installing the indigo_dev like suggested, but it threw errors as well. I think I have all the dependencies for the openni2_tracker and I couldn't find anything about additional dependencies for the libnite2, but from the errors I think I might be missing something there. Thank you again