Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

FoundationPose node failed to run #47

Closed
Yeager-101 opened this issue Sep 5, 2024 · 2 comments
Closed

FoundationPose node failed to run #47

Yeager-101 opened this issue Sep 5, 2024 · 2 comments

Comments

@Yeager-101
Copy link

Yeager-101 commented Sep 5, 2024

I have successfully installed foundationPose according to the ISSAC_ROS documentation, and have downloaded and converted the three required model files: refine_trt_engine.plan, score_trt_engine.plan, and sdetr_grasp.plan, and I have modified the foundationPose configuration file for realsense camera startup as follows:

import os

from ament_index_python.packages import get_package_share_directory
import launch
from launch.actions import DeclareLaunchArgument
from launch.conditions import IfCondition
from launch.substitutions import LaunchConfiguration
from launch_ros.actions import ComposableNodeContainer, Node
from launch_ros.descriptions import ComposableNode

# Number of Realsense messages to be dropped in 1 second
HAWK_EXPECT_FREQ = 28
# Expected number of Realsense messages in 1 second
INPUT_IMAGES_DROP_FREQ = 30

RT_DETR_MODEL_INPUT_SIZE = 640  # RT-DETR models expect 640x640 encoded image size
RT_DETR_MODEL_NUM_CHANNELS = 3  # RT-DETR models expect 3 image channels

REALSENSE_IMAGE_WIDTH =  1280
REALSENSE_IMAGE_HEIGHT = 720

VISUALIZATION_DOWNSCALING_FACTOR = 10

REALSENSE_TO_RT_DETR_RATIO = REALSENSE_IMAGE_WIDTH / RT_DETR_MODEL_INPUT_SIZE

REFINE_MODEL_PATH = '/tmp/refine_model.onnx'
REFINE_ENGINE_PATH = '/home/nvidia/Pose/isaac_ros_assets/models/foundationpose/refine_trt_engine.plan'
SCORE_MODEL_PATH = '/tmp/score_model.onnx'
SCORE_ENGINE_PATH = '/home/nvidia/Pose/isaac_ros_assets/models/foundationpose/score_trt_engine.plan'


def generate_launch_description():
    """Generate launch description for testing relevant nodes."""
    rviz_config_path = os.path.join(
        get_package_share_directory('isaac_ros_foundationpose'),
        'rviz', 'foundationpose_realsense.rviz')

    launch_args = [
        DeclareLaunchArgument(
            'hawk_expect_freq',
            default_value=str(HAWK_EXPECT_FREQ),
            description='Number of Realsense messages to be dropped in 1 second'),

        DeclareLaunchArgument(
            'input_images_drop_freq',
            default_value=str(INPUT_IMAGES_DROP_FREQ),
            description='Expected number of Realsense messages in 1 second'),

        DeclareLaunchArgument(
            'mesh_file_path',
            default_value='/home/nvidia/Pose/box/box.obj',
            description='The absolute file path to the mesh file'),

        DeclareLaunchArgument(
            'texture_path',
            default_value='/home/nvidia/Pose/box/baked_mesh_tex0.png',
            description='The absolute file path to the texture map'),

        DeclareLaunchArgument(
            'refine_model_file_path',
            default_value=REFINE_MODEL_PATH,
            description='The absolute file path to the refine model'),

        DeclareLaunchArgument(
            'refine_engine_file_path',
            default_value=REFINE_ENGINE_PATH,
            description='The absolute file path to the refine trt engine'),

        DeclareLaunchArgument(
            'score_model_file_path',
            default_value=SCORE_MODEL_PATH,
            description='The absolute file path to the score model'),

        DeclareLaunchArgument(
            'score_engine_file_path',
            default_value=SCORE_ENGINE_PATH,
            description='The absolute file path to the score trt engine'),

        DeclareLaunchArgument(
            'rt_detr_model_file_path',
            default_value='',
            description='The absolute file path to the RT-DETR ONNX file'),

        DeclareLaunchArgument(
            'rt_detr_engine_file_path',
            # default_value='',
            default_value='/home/nvidia/Pose/isaac_ros_assets/models/synthetica_detr/sdetr_grasp.plan',
            description='The absolute file path to the RT-DETR TensorRT engine file'),

        DeclareLaunchArgument(
            'launch_rviz',
            default_value='False',
            description='Flag to enable Rviz2 launch'),

        DeclareLaunchArgument(
            'container_name',
            default_value='foundationpose',
            # default_value='foundationpose_container',
            description='Name for ComposableNodeContainer'),
    ]

Finally, I started the foundationPose node, ros2 launch isaac_ros_foundationpose isaac_ros_foundationpose_realsense.launch.py, first I made sure I disabled X11 forwarding, my hardware environment is Jetson AGX Orin 32GB, ubuntu22.04 with CUDA12 JetPack6.0, the following error appeared after the node started:

[component_container_mt-1] [INFO] [1725524396.095299005] [drop_node]: Negotiating
[INFO] [launch_ros.actions.load_composable_nodes]: Loaded node '/resize_left_viz' in container '/foundationpose'
[component_container_mt-1] [INFO] [1725524396.841828199] [foundationpose_node]: [NitrosNode] Starting post negotiation setup
[component_container_mt-1] [INFO] [1725524396.841999883] [foundationpose_node]: [NitrosNode] Getting data format negotiation results
[component_container_mt-1] [INFO] [1725524396.842041355] [foundationpose_node]: [NitrosPublisher] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524396.842072204] [foundationpose_node]: [NitrosPublisher] Use only the compatible publisher: topic_name="/output", data_format="nitros_detection3_d_array"
[component_container_mt-1] [INFO] [1725524396.842099981] [foundationpose_node]: [NitrosPublisher] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524396.842120493] [foundationpose_node]: [NitrosPublisher] Use only the compatible publisher: topic_name="/pose_estimation/pose_matrix_output", data_format="nitros_tensor_list_nchw"
[component_container_mt-1] [INFO] [1725524396.842146094] [foundationpose_node]: [NitrosSubscriber] Use the negotiated data format: "nitros_image_rgb8"
[component_container_mt-1] [INFO] [1725524396.842178414] [foundationpose_node]: [NitrosSubscriber] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524396.842199759] [foundationpose_node]: [NitrosSubscriber] Use the compatible subscriber: topic_name="/rgb/camera_info", data_format="nitros_camera_info"
[component_container_mt-1] [INFO] [1725524396.842223503] [foundationpose_node]: [NitrosSubscriber] Use the negotiated data format: "nitros_image_mono8"
[component_container_mt-1] [INFO] [1725524396.842243856] [foundationpose_node]: [NitrosSubscriber] Use the negotiated data format: "nitros_image_32FC1"
[component_container_mt-1] [INFO] [1725524396.842652536] [foundationpose_node]: [NitrosNode] Exporting the final graph based on the negotiation results
[component_container_mt-1] [INFO] [1725524397.096062001] [resize_left_viz]: [NitrosNode] Starting post negotiation setup
[component_container_mt-1] [INFO] [1725524397.096230965] [resize_left_viz]: [NitrosNode] Getting data format negotiation results
[component_container_mt-1] [INFO] [1725524397.096270166] [resize_left_viz]: [NitrosPublisher] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524397.096303126] [resize_left_viz]: [NitrosPublisher] Use only the compatible publisher: topic_name="/rgb/image_rect_color_viz", data_format="nitros_image_rgb8"
[component_container_mt-1] [INFO] [1725524397.096329175] [resize_left_viz]: [NitrosPublisher] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524397.096348535] [resize_left_viz]: [NitrosPublisher] Use only the compatible publisher: topic_name="/rgb/camera_info_viz", data_format="nitros_camera_info"
[component_container_mt-1] [INFO] [1725524397.096373304] [resize_left_viz]: [NitrosSubscriber] Use the negotiated data format: "nitros_image_rgb8"
[component_container_mt-1] [INFO] [1725524397.096397560] [resize_left_viz]: [NitrosSubscriber] Negotiation ended with no results
[component_container_mt-1] [INFO] [1725524397.096417721] [resize_left_viz]: [NitrosSubscriber] Use the compatible subscriber: topic_name="/rgb/camera_info", data_format="nitros_camera_info"
[component_container_mt-1] [INFO] [1725524397.096836258] [resize_left_viz]: [NitrosNode] Exporting the final graph based on the negotiation results
[component_container_mt-1] [INFO] [1725524397.121946293] [resize_left_viz]: [NitrosNode] Wrote the final top level YAML graph to "/tmp/isaac_ros_nitros/graphs/GGZLWRRQKN/GGZLWRRQKN.yaml"
[component_container_mt-1] [INFO] [1725524397.122149562] [resize_left_viz]: [NitrosNode] Loading application
[component_container_mt-1] [INFO] [1725524397.136081473] [resize_left_viz]: [ResizeNode] postLoadGraphCallback().
[component_container_mt-1] [INFO] [1725524397.136513706] [resize_left_viz]: [NitrosNode] Initializing and running GXF graph
[component_container_mt-1] [INFO] [1725524397.152245047] [resize_left_viz]: [NitrosNode] Node was started
[component_container_mt-1] [INFO] [1725524399.044914598] [camera]: Stopping Sensor: Stereo Module
[component_container_mt-1] [INFO] [1725524399.344173027] [camera]: Starting Sensor: Stereo Module
[component_container_mt-1] [INFO] [1725524399.464196847] [camera]: Open profile: stream_type: Depth(0), Format: Z16, Width: 848, Height: 480, FPS: 30
[component_container_mt-1] [INFO] [1725524399.464502870] [camera]: Stopping Sensor: RGB Camera
[component_container_mt-1]  05/09 01:19:59,465 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,476 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,487 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,498 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,509 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,520 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,530 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,541 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,552 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,563 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,574 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1] [INFO] [1725524399.587672420] [camera]: Starting Sensor: RGB Camera
[component_container_mt-1] [INFO] [1725524399.615530386] [camera]: Open profile: stream_type: Color(0), Format: RGB8, Width: 1280, Height: 720, FPS: 30
[component_container_mt-1] [INFO] [1725524399.615742038] [camera]: Stopping Sensor: Motion Module
[component_container_mt-1] [INFO] [1725524399.623044497] [camera]: Starting Sensor: Motion Module
[component_container_mt-1] [INFO] [1725524399.633783412] [camera]: Open profile: stream_type: Accel(0)Format: MOTION_XYZ32F, FPS: 100
[component_container_mt-1] [INFO] [1725524399.633919095] [camera]: Open profile: stream_type: Gyro(0)Format: MOTION_XYZ32F, FPS: 200
[component_container_mt-1] [WARN] [1725524399.636094469] [camera]: 
[component_container_mt-1] [INFO] [1725524399.636563247] [camera]: RealSense Node Is Up!
[component_container_mt-1]  05/09 01:19:59,890 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,900 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,912 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,922 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,933 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1]  05/09 01:19:59,944 WARNING [281472187754720] (messenger-libusb.cpp:42) control_transfer returned error, index: 768, error: Resource temporarily unavailable, number: 11
[component_container_mt-1] [WARN] [1725524400.346289752] [camera]: XXX Hardware Notification:Motion Module force pause,1.72552e+12,Error,Hardware Error
[component_container_mt-1] [WARN] [1725524400.346465724] [camera]: Hardware Notification:Motion Module force pause,1.72552e+12,Error,Hardware Error
[component_container_mt-1] [INFO] [1725524401.815843009] [foundationpose_node]: [NitrosNode] Wrote the final top level YAML graph to "/tmp/isaac_ros_nitros/graphs/EBEFIVHXIA/EBEFIVHXIA.yaml"
[component_container_mt-1] [INFO] [1725524401.815990660] [foundationpose_node]: [NitrosNode] Loading application
[component_container_mt-1] 2024-09-05 01:20:01.832 WARN  gxf/std/yaml_file_loader.cpp@1077: Using unregistered parameter 'dummy_rx' in component ''.
[component_container_mt-1] 2024-09-05 01:20:01.832 WARN  gxf/std/yaml_file_loader.cpp@1077: Using unregistered parameter 'dummy_rx' in component ''.
[component_container_mt-1] 2024-09-05 01:20:01.834 WARN  gxf/std/yaml_file_loader.cpp@1077: Using unregistered parameter 'dev_id' in component 'stream'.
[component_container_mt-1] [INFO] [1725524401.837107395] [foundationpose_node]: [NitrosNode] Initializing and running GXF graph
[component_container_mt-1] 2024-09-05 01:20:01.854 WARN  gxf/std/scheduling_terms.cpp@333: 'min_size' parameter in MultiMessageAvailableSchedulingTerm is deprecated. Use 'min_sum' with SumOfAll sampling mode instead
[component_container_mt-1] 2024-09-05 01:20:01.854 WARN  gxf/std/scheduling_terms.cpp@333: 'min_size' parameter in MultiMessageAvailableSchedulingTerm is deprecated. Use 'min_sum' with SumOfAll sampling mode instead
[component_container_mt-1] 2024-09-05 01:20:01.854 WARN  gxf/std/scheduling_terms.cpp@333: 'min_size' parameter in MultiMessageAvailableSchedulingTerm is deprecated. Use 'min_sum' with SumOfAll sampling mode instead
[component_container_mt-1] 2024-09-05 01:20:01.854 WARN  gxf/std/scheduling_terms.cpp@333: 'min_size' parameter in MultiMessageAvailableSchedulingTerm is deprecated. Use 'min_sum' with SumOfAll sampling mode instead
[component_container_mt-1] 2024-09-05 01:20:01.856 WARN  gxf/std/scheduling_terms.cpp@333: 'min_size' parameter in MultiMessageAvailableSchedulingTerm is deprecated. Use 'min_sum' with SumOfAll sampling mode instead
[component_container_mt-1] [INFO] [1725524401.867930479] [foundationpose_node]: [NitrosNode] Node was started
[component_container_mt-1] [INFO] [1725524401.881938967] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] 2024-09-05 01:20:02.026 WARN  ./gxf/extensions/tensor_rt/tensor_rt_inference.cpp@155: TRT WARNING: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
[component_container_mt-1] [INFO] [1725524402.567335280] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] 2024-09-05 01:20:02.583 WARN  ./gxf/extensions/tensor_rt/tensor_rt_inference.cpp@155: TRT WARNING: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
[component_container_mt-1] [INFO] [1725524403.589012199] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524404.709579357] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524405.816409672] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524406.854557534] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524407.979675575] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524409.090029516] [detection2_d_to_mask]: No detection found with non-zero confidence
[component_container_mt-1] [INFO] [1725524410.214247516] [detection2_d_to_mask]: No detection found with non-zero confidence
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT)
[component_container_mt-1] [INFO] [1725524411.165306050] [rclcpp]: signal_handler(signum=2)
[ERROR] [component_container_mt-1]: process[component_container_mt-1] failed to terminate '5' seconds after receiving 'SIGINT', escalating to 'SIGTERM'
[INFO] [component_container_mt-1]: sending signal 'SIGTERM' to process[component_container_mt-1]
[component_container_mt-1] [INFO] [1725524417.122701960] [rclcpp]: signal_handler(signum=15)
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT) again, ignoring...
[component_container_mt-1] [INFO] [1725524418.262883998] [rclcpp]: signal_handler(signum=2)
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT) again, ignoring...
[component_container_mt-1] [INFO] [1725524418.470428965] [rclcpp]: signal_handler(signum=2)
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT) again, ignoring...
[component_container_mt-1] [INFO] [1725524418.638392462] [rclcpp]: signal_handler(signum=2)
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT) again, ignoring...
[component_container_mt-1] [INFO] [1725524418.782556002] [rclcpp]: signal_handler(signum=2)
^C[WARNING] [launch]: user interrupted with ctrl-c (SIGINT) again, ignoring...
[component_container_mt-1] [INFO] [1725524418.926563315] [rclcpp]: signal_handler(signum=2)
[ERROR] [component_container_mt-1]: process[component_container_mt-1] failed to terminate '10.0' seconds after receiving 'SIGTERM', escalating to 'SIGKILL'
[INFO] [component_container_mt-1]: sending signal 'SIGKILL' to process[component_container_mt-1]
[ERROR] [component_container_mt-1]: process has died [pid 12888, exit code -9, cmd '/opt/ros/humble/lib/rclcpp_components/component_container_mt --ros-args -r __node:=foundationpose -r __ns:=/'].

It keeps looping [component_container_mt-1] [INFO] [1725524410.214247516] [detection2_d_to_mask]: No detection found with non-zero confidence, and I enabled launch_rviz to True in the launch file, but rviz displays image data but no pose information.
Who can help me analyze this problem, I have tried many methods but still failed to solve it, maybe I overlooked some details.Thanks!

@PPZPPZ
Copy link

PPZPPZ commented Oct 25, 2024

Hello, when I recently ran this script, I replaced my own obj file and encountered the same issue as you. Could you please tell me how you resolved it?

@Yeager-101
Copy link
Author

Yeager-101 commented Oct 28, 2024

Hello, when I recently ran this script, I replaced my own obj file and encountered the same issue as you. Could you please tell me how you resolved it?

I think you can debug it as I suggested here before, but I will say that although I seemed to have completed the test in the end, the results showed that it was very slow and resource intensive.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants