For the costmap_2d that is in move_base you can use these parameters to limit minimum and maximum heights of point cloud data that is considered for obstacles.<div><br></div><div>From <a href="http://www.ros.org/wiki/costmap_2d#Sensor_management_parameters">http://www.ros.org/wiki/costmap_2d#Sensor_management_parameters</a>:</div>

<i>~&lt;name&gt;/&lt;source_name&gt;/max_obstacle_height (double, default: 2.0)<br><br>The maximum height in meters of a sensor reading considered valid. This is usually set to be slightly higher than the height of the robot. Setting this parameter to a value greater than the global max_obstacle_heightparameter has no effect. Setting this parameter to a value less than the global max_obstacle_height will filter out points from this sensor above that height.<br>

<br>~&lt;name&gt;/&lt;source_name&gt;/min_obstacle_height (double, default: 0.0)<br><br>The minimum height in meters of a sensor reading considered valid. This is usually set to be at ground height, but can be set higher or lower based on the noise model of your sensor.</i><div>

<i><br></i></div><div><i><span class="Apple-style-span" style="font-style: normal;">Hope that helps,</span><br></i><div><br></div><div><br clear="all">~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>William Woodall<br>Graduate Software Engineering<br>

Auburn University<br><a href="mailto:w@auburn.edu" target="_blank">w@auburn.edu</a><br><a href="mailto:wjwwood@gmail.com" target="_blank">wjwwood@gmail.com</a><br>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>
<br><br><div class="gmail_quote">On Tue, Feb 1, 2011 at 6:44 AM, Marja <span dir="ltr">&lt;<a href="mailto:zurigune0002@yahoo.es">zurigune0002@yahoo.es</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">

<br>
First of all, I apologize if this question has been answered before.<br>
<br>
We have in mind to work with a laser pointing downwards, so the obstacles<br>
lying in the floor in front of the robot could be detected. If I am not<br>
wrong, ROS works with a 2D map, more precisely with a 2D projection of a 3D<br>
cloud of points. When performing local planning, the new discovered<br>
obstacles are added to the map.<br>
<br>
My question is: how does ROS consider the floor when it is not detected<br>
exactly (maybe with some tolerance?) where it is supossed to be? My guess is<br>
that it is considered an obstacle and then a laser readings filtering would<br>
be necessary and the detection of obstacles of small height not<br>
straightforward. Am I right?<br>
<br>
I would be very grateful for any suggestion from people working in this<br>
area.<br>
<br>
Cheers!<br>
<br>
Maria<br>
<font color="#888888">--<br>
View this message in context: <a href="http://ros-users.122217.n3.nabble.com/Floor-detected-as-an-obstacle-tp2397002p2397002.html" target="_blank">http://ros-users.122217.n3.nabble.com/Floor-detected-as-an-obstacle-tp2397002p2397002.html</a><br>


Sent from the ROS-Users mailing list archive at Nabble.com.<br>
_______________________________________________<br>
ros-users mailing list<br>
<a href="mailto:ros-users@code.ros.org">ros-users@code.ros.org</a><br>
<a href="https://code.ros.org/mailman/listinfo/ros-users" target="_blank">https://code.ros.org/mailman/listinfo/ros-users</a><br>
</font></blockquote></div><br></div></div>