[Documentation] [TitleIndex] [WordIndex

  Show EOL distros: 

navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mferguson AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: hydro-devel)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mfergs7 AT gmail DOT com>, Aaron Hoy <ahoy AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: indigo-devel)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mferguson AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: jade-devel)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mfergs7 AT gmail DOT com>, Aaron Hoy <ahoy AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: kinetic-devel)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | robot_pose_ekf | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mfergs7 AT gmail DOT com>, Aaron Hoy <ahoy AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: lunar)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mfergs7 AT gmail DOT com>, Aaron Hoy <ahoy AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: melodic-devel)
navigation: amcl | base_local_planner | carrot_planner | clear_costmap_recovery | costmap_2d | dwa_local_planner | fake_localization | global_planner | map_server | move_base | move_base_msgs | move_slow_and_clear | nav_core | navfn | rotate_recovery | voxel_grid

Package Summary

This package provides an implementation of a 2D costmap that takes in sensor data from the world, builds a 2D or 3D occupancy grid of the data (depending on whether a voxel based implementation is used), and inflates costs in a 2D costmap based on the occupancy grid and a user specified inflation radius. This package also provides support for map_server based initialization of a costmap, rolling window based costmaps, and parameter based subscription to and configuration of sensor topics.

  • Maintainer status: maintained
  • Maintainer: David V. Lu!! <davidvlu AT gmail DOT com>, Michael Ferguson <mfergs7 AT gmail DOT com>, Aaron Hoy <ahoy AT fetchrobotics DOT com>
  • Author: Eitan Marder-Eppstein, David V. Lu!!, Dave Hershberger, contradict@gmail.com
  • License: BSD
  • Source: git https://github.com/ros-planning/navigation.git (branch: noetic-devel)

Overview

costmap_rviz.png Note: In the picture above, the red cells represent obstacles in the costmap, the blue cells represent obstacles inflated by the inscribed radius of the robot, and the red polygon represents the footprint of the robot. For the robot to avoid collision, the footprint of the robot should never intersect a red cell and the center point of the robot should never cross a blue cell.

The costmap_2d package provides a configurable structure that maintains information about where the robot should navigate in the form of an occupancy grid. The costmap uses sensor data and information from the static map to store and update information about obstacles in the world through the costmap_2d::Costmap2DROS object. The costmap_2d::Costmap2DROS object provides a purely two dimensional interface to its users, meaning that queries about obstacles can only be made in columns. For example, a table and a shoe in the same position in the XY plane, but with different Z positions would result in the corresponding cell in the costmap_2d::Costmap2DROS object's costmap having an identical cost value. This is designed to help planning in planar spaces.

As of the Hydro release, the underlying methods used to write data to the costmap is fully configurable. Each bit of functionality exists in a layer. For instance, the static map is one layer, and the obstacles are another layer. By default, the obstacle layer maintains information three dimensionally (see voxel_grid). Maintaining 3D obstacle data allows the layer to deal with marking and clearing more intelligently.

The main interface is costmap_2d::Costmap2DROS which maintains much of the ROS related functionality. It contains a costmap_2d::LayeredCostmap which is used to keep track of each of the layers. Each layer is instantiated in the Costmap2DROS using pluginlib and is added to the LayeredCostmap. The layers themselves may be compiled individually, allowing arbitrary changes to the costmap to be made through the C++ interface. The costmap_2d::Costmap2D class implements the basic data structure for storing and accessing the two dimensional costmap.

The details about how the Costmap updates the occupancy grid are described below, along with links to separate pages describing how the individual layers work.

Marking and Clearing

The costmap automatically subscribes to sensors topics over ROS and updates itself accordingly. Each sensor is used to either mark (insert obstacle information into the costmap), clear (remove obstacle information from the costmap), or both. A marking operation is just an index into an array to change the cost of a cell. A clearing operation, however, consists of raytracing through a grid from the origin of the sensor outwards for each observation reported. If a three dimensional structure is used to store obstacle information, obstacle information from each column is projected down into two dimensions when put into the costmap.

Occupied, Free, and Unknown Space

While each cell in the costmap can have one of 255 different cost values (see the inflation section), the underlying structure that it uses is capable of representing only three. Specifically, each cell in this structure can be either free, occupied, or unknown. Each status has a special cost value assigned to it upon projection into the costmap. Columns that have a certain number of occupied cells (see mark_threshold parameter) are assigned a costmap_2d::LETHAL_OBSTACLE cost, columns that have a certain number of unknown cells (see unknown_threshold parameter) are assigned a costmap_2d::NO_INFORMATION cost, and other columns are assigned a costmap_2d::FREE_SPACE cost.

Map Updates

The costmap performs map update cycles at the rate specified by the update_frequency parameter. Each cycle, sensor data comes in, marking and clearing operations are perfomed in the underlying occupancy structure of the costmap, and this structure is projected into the costmap where the appropriate cost values are assigned as described above. After this, each obstacle inflation is performed on each cell with a costmap_2d::LETHAL_OBSTACLE cost. This consists of propagating cost values outwards from each occupied cell out to a user-specified inflation radius. The details of this inflation process are outlined below.

tf

In order to insert data from sensor sources into the costmap, the costmap_2d::Costmap2DROS object makes extensive use of tf. Specifically, it assumes that all transforms between the coordinate frames specified by the global_frame parameter, the robot_base_frame parameter, and sensor sources are connected and up-to-date. The transform_tolerance parameter sets the maximum amount of latency allowed between these transforms. If the tf tree is not updated at this expected rate, the navigation stack stops the robot.

Inflation

costmapspec.png

Inflation is the process of propagating cost values out from occupied cells that decrease with distance. For this purpose, we define 5 specific symbols for costmap values as they relate to a robot.

The rationale behind these definitions is that we leave it up to planner implementations to care or not about the exact footprint, yet give them enough information that they can incur the cost of tracing out the footprint only in situations where the orientation actually matters.

Map Types

There are two main ways to initialize a costmap_2d::Costmap2DROS object. The first is to seed it with a user-generated static map (see the map_server package for documentation on building a map). In this case, the costmap is initialized to match the width, height, and obstacle information provided by the static map. This configuration is normally used in conjunction with a localization system, like amcl, that allows the robot to register obstacles in the map frame and update its costmap from sensor data as it drives through its environment.

The second way to initialize a costmap_2d::Costmap2DROS object is to give it a width and height and to set the rolling_window parameter to be true. The rolling_window parameter keeps the robot in the center of the costmap as it moves throughout the world, dropping obstacle information from the map as the robot moves too far from a given area. This type of configuration is most often used in an odometric coordinate frame where the robot only cares about obstacles within a local area.

Component API

Pre-hydro only <<Include: execution failed [No module named neo_cgi] (see also the log)>>

New in ROS hydro <>


2020-09-19 12:39