|
|
| Line 6: |
Line 6: |
| | ===Why we use it=== | | ===Why we use it=== |
| | description | | description |
| − |
| |
| − | *Zed
| |
| − | **the camera and software that comes with it. We are using the first Zed camera.
| |
| − | **https://www.stereolabs.com/docs/getting-started/
| |
| − |
| |
| − | *Depth image
| |
| − | **An image that has various distances information. Zed already can create the depth image. Because Zed has two cameras, it can calculate the distance information knowing the distance between its own two cameras.
| |
| − |
| |
| − | (We may eventually get a LIDAR that will allow us to skip these steps and directly have a laser scan)
| |
| − |
| |
| − | *Laserscan
| |
| − | **Uses the depth image to determine the shape of the objects. We plan to use the ROS package depthimage_to_laserscan to get this
| |
| − | **http://wiki.ros.org/depthimage_to_laserscan
| |
| − |
| |
| − | *Occupancy Grid
| |
| − | **The data from the laserscan is transformed into an occupancy grid, which is essentially an array of data. We are planning on using the ROS package rtabmap for this step. We could also use gmapping, but rtabmap has better documentation. For rtabmap, we plan on using the published topics grid_map.From the ROS website, grid_map creates an occupancy grid generated with laser scans. It uses parameters with prefixes map_ and grid_. We will give this to the navigation team.
| |
| − | **http://wiki.ros.org/rtabmap_ros
| |
| − |
| |
| − | ===Example SLAM projects===
| |
| − | *SLAM Robot
| |
| − | **https://kahilyprojects.com/slam-robot/
| |
| − | *Turtlebot
| |
| − | **https://github.com/turtlebot/turtlebot/blob/melodic/turtlebot_bringup/launch/3dsensor.launch
| |
