Juan Ignacio Ubeira
Juan Ignacio Ubeira
As the current map is empty, it makes no sense to adjust the global costmap and planner. #119 tunes the navstack giving priority to the local costmap and planner, so...
Ideally, the robot should be able to enter a mode where the map is built using `tango_ros_node` functionality. The user should be able to teleoperate the robot while the app...
Investigate how `tango_ros_node` is creating occupancy grids. Use that functionality together with the map node (#121) to publish a map created by Tango.
Create a node that can publish an actual map instead of an empty one.
Right now we are using localization mode 1. Check if we can suppress the `map` to `odom` static publisher and use ADF frame as `map` instead using the correct localization...
The local costmap isn't cleaned quite well yet. E.g. in this case, the laser can see through the obstacles, but they are not cleared in the local costmap.  Recovery...
Some applications in [rosjava/android](https://github.com/rosjava/android_apps) are available to visualize the robot in a map and send goal poses. map_nav is a good candidate, but it is outdated, and depends on packages...
Should we index the package? That would improve the documentation a bit: http://wiki.ros.org/rosdistro/Tutorials/Indexing%20Your%20ROS%20Repository%20for%20Documentation%20Generation
Tango odometry is more accurate than wheel odometry. Some research has to be done to figure if it is worth doing fusion with both odometries, correcting wheel odometry with Tango...
To test the navigation stack on Linux, the starting point will be an operational navigation stack running with data coming from a simulator (such as Stage or Gazebo). Then, the...