Rviz error exit code -11

Software ROS2
1

Hi, I use this command

$ ros2 launch zed_display_rviz2 display_zed_cam.launch.py camera_model:=zed2

Actually it operated well when I turn off my object detection

However, If I turn on object Detection and laucnh this code, After 10~20second,
Process crashed…

I don’t know why this was happend.

please tell me If you need any other file to solve this problem

Environment :

this is my error code…

[ERROR] [rviz2-1]: process has died [pid 27909, exit code -11, cmd '/opt/ros/foxy/lib/rviz2/rviz2 -d /home/ros2/workspace/install/zed_display_rviz2/share/zed_display_rviz2/rviz2/zed2.rviz --ros-args -r __node:=zed2_rviz2 -r __ns:=/zed
2

Hi @Leejh0426
can you please monitor GPU and CPU memory to verify if you are running out of memory when the crash happens?

3

GPU : I use command watch -n 1 nvidia-smi

Screenshot from 2024-04-09 17-43-04
Screenshot from 2024-04-09 17-43-041920×1080 193 KB

CPU: I use command top

Screenshot from 2024-04-09 17-46-42
Screenshot from 2024-04-09 17-46-421373×574 281 KB

that Screenshots are picture just before crashes

4

Please provide more information to try to replicate the issue:

  • common.yaml
  • zed2.yaml
  • object detection configuration
5

common.yaml (15.4 KB)
zed2.yaml (505 Bytes)

I don’t know What is object detection configuration.
You mean this code in common.yaml?

 object_detection:
            od_enabled: True # True to enable Object Detection
            model: 'MULTI_CLASS_BOX_MEDIUM' # 'MULTI_CLASS_BOX_FAST', 'MULTI_CLASS_BOX_MEDIUM', 'MULTI_CLASS_BOX_ACCURATE', 'PERSON_HEAD_BOX_FAST', 'PERSON_HEAD_BOX_ACCURATE'
            allow_reduced_precision_inference: true # Allow inference to run at a lower precision to improve runtime and memory usage
            max_range: 20.0 # [m] Defines a upper depth range for detections
            confidence_threshold: 50.0 # [DYNAMIC] - Minimum value of the detection confidence of an object [0,99]
            prediction_timeout: 0.5 # During this time [sec], the object will have OK state even if it is not detected. Set this parameter to 0 to disable SDK predictions            
            filtering_mode: 1 # '0': NONE - '1': NMS3D - '2': NMS3D_PER_CLASS
            mc_people: false # [DYNAMIC] - Enable/disable the detection of persons for 'MULTI_CLASS_X' models
            mc_vehicle: false # [DYNAMIC] - Enable/disable the detection of vehicles for 'MULTI_CLASS_X' models
            mc_bag: false # [DYNAMIC] - Enable/disable the detection of bags for 'MULTI_CLASS_X' models
            mc_animal: false # [DYNAMIC] - Enable/disable the detection of animals for 'MULTI_CLASS_X' models
            mc_electronics: true # [DYNAMIC] - Enable/disable the detection of electronic devices for 'MULTI_CLASS_X' models
            mc_fruit_vegetable: false # [DYNAMIC] - Enable/disable the detection of fruits and vegetables for 'MULTI_CLASS_X' models
            mc_sport: false # [DYNAMIC] - Enable/disable the detection of sport-related objects for 'MULTI_CLASS_X' models            
            qos_history: 1 # '1': KEEP_LAST - '2': KEEP_ALL
            qos_depth: 1 # Queue size if using KEEP_LAST
            qos_reliability: 1 # '1': RELIABLE - '2': BEST_EFFORT
            qos_durability: 2 # '1': TRANSIENT_LOCAL - '2': VOLATILE
6

Screenshot from 2024-04-09 18-21-12
Screenshot from 2024-04-09 18-21-121920×1080 248 KB

+)this is picture monitor cpu just before crashes

7

There seems to be a memory issue indeed. Can you use the System Monitor application to capture the CPU monitor plot? This would be useful to detect any uncontrolled memory usage growth.

8

As you can see, it turns off in an instant :frowning:

9

+)This is video monitor gpu just before crashes…