Closed khuechuong closed 1 year ago
Hi @khuechuong this is something related to the RTABmap package, not this example. I suggest you contact RTABmap support: http://official-rtab-map-forum.206.s1.nabble.com/
FYI: Tracking issue here: https://github.com/introlab/rtabmap_ros/issues/874
Preliminary Checks
Description
Basically, I am using a zed mini and using their ROS package. I use ubuntu 20.04, ros noetic, ros1, with a gtx 1080 gpu. I follow the installation instruction: https://www.stereolabs.com/docs/ros/ And I used rtabmap ros. In the beginning, both rtabmapviz and rviz wasn't that good as seen here.
RVIZ with _/zed/zed_node/point_cloud/cloudregistered topic:![Screenshot from 2023-01-20 00-26-16](https://user-images.githubusercontent.com/46792357/213650161-0ede2c4c-b22c-4ac6-964c-871718255ae9.png)
RVIZ without _/zed/zed_node/point_cloud/cloudregistered topic:![Screenshot from 2023-01-20 00-26-38](https://user-images.githubusercontent.com/46792357/213650165-43d7f96c-9b73-4e29-8afb-50cdaf0705bb.png)
So I changed the param _subscribe_scancloud to true and add to rtabmap_ros and rtabmapviz. That really helped rtabmapviz, but rviz still just doesn't have the good quality of mapping like I see in other youtube. The command I ran was _roslaunch zed_rtabmap_example zedrtabmap.launch
zed_rtabmap.launch
<?xml version="1.0"?>
sl_rtabmap.launch.xml
rtabmap.yaml subscribe_depth: true subscribe_rgbd: false subscribe_stereo: false subscribe_stereo: false subscribe_scan: false subscribe_scan_cloud: true subscribe_user_data: false subscribe_odom_info: false
database_path: "~/.ros/rtabmap.db" config_path: "~/.ros/rtabmap.cfg"
frame_id: "base_link" map_frame_id: "map" odom_frame_id: "odom" # odometry from odom msg to have covariance - Remapped by launch file odom_tf_angular_variance: 0.001 # If TF is used to get odometry, this is the default angular variance odom_tf_linear_variance: 0.001 # If TF is used to get odometry, this is the default linear variance tf_delay: 0.02 publish_tf: false # Set to false if fusing different poses (map->odom) with UKF
odom_sensor_sync: true wait_for_transform_duration: 0.2 approx_sync: true
queue_size: 100
scan_normal_k: 0
Grid: 3D: true FlatObstacleDetected: true MapFrameProjection: false GroundIsObstacle: false PreVoxelFiltering: true RayTracing: true FromDepth: true NormalsSegmentation: false CellSize: 0.05 ClusterRadius: 0.1 MinClusterSize: 3 DepthDecimation: 1 DepthRoiRatios: [0.0, 0.0, 0.0, 0.0] FootprintHeight: 2.0 FootprintLength: 0.18 FootprintWidth: 0.18 MaxGroundAngle: 30.0 MinGroundHeight: -0.5 MaxGroundHeight: -0.4 MaxObstacleHeight: 0.1 NoiseFilteringMinNeighbors: 5 NoiseFilteringRadius: 0.1 NormalK: 20 RangeMin: 0.7 RangeMax: 3.0
GridGlobal: Eroded: false # Erode obstacle cells FootprintRadius: 0.18 # Footprint radius (m) used to clear all obstacles under the graph FullUpdate: true # When the graph is changed, the whole map will be reconstructed instead of moving individually each cells of the map. Also, data added to cache won't be released after updating the map. This process is longer but more robust to drift that would erase some parts of the map when it should not MaxNodes: 0 # Maximum nodes assembled in the map starting from the last node (0=unlimited) MinSize: 1.0 # Minimum map size (m) OccupancyThr: 0.55 # Occupancy threshold (value between 0 and 1) ProbClampingMax: 0.971 # Probability clamping maximum (value between 0 and 1) ProbClampingMin: 0.1192 # Probability clamping minimum (value between 0 and 1) ProbHit: 0.7 # Probability of a hit (value between 0.5 and 1) ProbMiss: 0.4 # Probability of a miss (value between 0 and 0.5) UpdateError: 0.01 # Graph changed detection error (m). Update map only if poses in new optimized graph have moved more than this value
Here's a picture of what it looks like:
RVIZ with _/zed/zed_node/point_cloud/cloudregistered topic:![Screenshot from 2023-01-20 00-33-14](https://user-images.githubusercontent.com/46792357/213651440-0693cd8e-e0a3-4086-bfe4-ccd3d45e0ca4.png)
RVIZ with _/zed/zed_node/point_cloud/cloudregistered topic:![Screenshot from 2023-01-20 00-34-05](https://user-images.githubusercontent.com/46792357/213651443-28895626-d955-43d9-8c7d-f0e38118601a.png)
As you can see, in rtabmapviz, the quality improved drastically, but rviz mapping mapping points barely had anything. I don't really understand why. Any thought and help is appreciated. Let me know if you have any questions. Thank you!
Steps to Reproduce
1. 2. 3. ...
Expected Result
RVIZ mapping the same as rtabmpviz
Actual Result
RVIZ maps just a few points and doesn't look anything like rtabmapviz
ZED Camera model
ZED Mini
Environment
Anything else?
No response