wh200720041 / mms_slam

Wang Han [homepage]              

• :🌱: currently working in Huawei Singapore (Todmind Program).
• 🎓 received Ph.D. in Nanyang Technological University.
• 🔨 specialize in computer vision and robotics.

mms_slam's Issues

RUNNING SCRIPT: How do we get this to run on system python on Ubuntu 20.04 without messing with system python ?

I am a bit confused on how to get this repo up and running Ubuntu 20.04. I am having a ton problems with the fact that this repo is built with python 3.7 and default system python is 3.8. A lot of mmdet requirements need it to be python3.7. The Shebang in solo_node.py is requiring mmdet to be installed with default system python which is 3.8. I am curious how you all go around this isuse ?

So far I've gotten mmdet 2.0.0 to install in solo conda enviroment and updated the shebang in solo_node.py to point to conda python enviroment. However I am unable to get alfred_py to install in this enviroment and this causing a wheel error.

• Are we supposed to downgrade the system python to 3.7?
• If not how execatly does the solo_node.py script find the mmdet install ?

any paper

is a reference paper of the program？ I want to get the link to better understand the work. Thanks!

What is the transformation matrix here?

        Eigen::Isometry3d pose_trans = Eigen::Isometry3d::Identity();
        pose_trans.translation() = Eigen::Vector3d(0.001, 0.014, -0.007);
        Eigen::Quaterniond quaternion_temp(1.00,-0.012, -0.001, -0.003); 
        pose_trans.linear() = quaternion_temp.toRotationMatrix();;
        pcl::PointCloud<pcl::PointXYZRGB>::Ptr transformed_pc(new pcl::PointCloud<pcl::PointXYZRGB>());

missing 1 required positional argument: 'bias'

I encounter a problem while running the command " roslaunch mms_slam mms_slam_mapping.launch"

ImportError: libcudart.so.10.1: cannot open shared object file: No such file or directory

Is the cuda version used in this project cuda11 (refer to readme for condo install pytorch=1.7.1 torchvision=0.8.2 torchaudio=0.7.2 cudatoolkit=11.0- c pytorch), but I encountered an error while running roslaunch:
Traceback (most recent call last):
File "/home/ht/Project/mms_slam/src/mms_slam/src/solo_node.py", line 11, in
from mmdet.apis import init_detector, inference_detector, show_result_ins, show_result
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/apis/init.py", line 1, in
from .inference import (async_inference_detector, inference_detector,
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/apis/inference.py", line 11, in
from mmdet.core import get_classes
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/core/init.py", line 6, in
from .post_processing import * # noqa: F401, F403
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/core/post_processing/init.py", line 1, in
from .bbox_nms import multiclass_nms, multiclass_nms_idx
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/core/post_processing/bbox_nms.py", line 3, in
from mmdet.ops.nms import nms_wrapper
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/ops/init.py", line 2, in
from .conv import build_conv_layer
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/ops/conv.py", line 4, in
from .dcn import DeformConvPack, ModulatedDeformConvPack
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/ops/dcn/init.py", line 1, in
from .deform_conv import (DeformConv, DeformConvPack, ModulatedDeformConv,
File "/home/ht/Project/mms_slam/src/mms_slam/dependency/mmdet/mmdet/ops/dcn/deform_conv.py", line 12, in
from . import deform_conv_ext
ImportError: libcudart.so.10.1: cannot open shared object file: No such file or directory
[solo_node-3] process has died [pid 43752, exit code 1, cmd /home/ht/Project/mms_slam/src/mms_slam/src/solo_node.py ~input:=/camera/color/image_raw __name:=solo_node __log:=/home/ht/.ros/log/f9bda8ea-65e6-11ee-b78f-a5d328de9705/solo_node-3.log].
log file: /home/ht/.ros/log/f9bda8ea-65e6-11ee-b78f-a5d328de9705/solo_node-3*.log

rviz

When running the launch file mentioned above, I got an error. How can I find this problem? Fixed Frame error Unknown frame world
Segmentation result: image displays No Image received

any solid-state lidar?

I see there is only depth camera, code have no lidar. Can you tell me how can I deal with lidar?

unaligned points

unaligned points appear when running code with the camera. Modified parameters in the code are still unaligned points. Isn't this parameter set internally for the camera?

Runing errors

First, thank you very much for seeing such an excellent work, I have built your code in my ubuntu 18.04 & 20.04 desktop, but I get the same error like this:

then, I check the log file in ros, i find the mms_slam_odom_estimation_node-6-stdout.log is an empty file, and there are some errors in master.log, can u give me some experiences to solve these problem.:help:

[rosmaster.threadpool][ERROR] 2021-10-26 15:12:20,152: Traceback (most recent call last):
  File "/opt/ros/melodic/lib/python2.7/dist-packages/rosmaster/threadpool.py", line 218, in run
    result = cmd(*args)
  File "/opt/ros/melodic/lib/python2.7/dist-packages/rosmaster/master_api.py", line 210, in publisher_update_task
    ret = xmlrpcapi(api).publisherUpdate('/master', topic, pub_uris)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1243, in __call__
    return self.__send(self.__name, args)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1602, in __request
    verbose=self.__verbose
  File "/usr/lib/python2.7/xmlrpclib.py", line 1283, in request
    return self.single_request(host, handler, request_body, verbose)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1316, in single_request
    return self.parse_response(response)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1493, in parse_response
    return u.close()
  File "/usr/lib/python2.7/xmlrpclib.py", line 800, in close
    raise Fault(**self._stack[0])
Fault: <Fault -1: 'publisherUpdate: unknown method name'>

[rosmaster.threadpool][ERROR] 2021-10-26 15:12:20,305: Traceback (most recent call last):
  File "/opt/ros/melodic/lib/python2.7/dist-packages/rosmaster/threadpool.py", line 218, in run
    result = cmd(*args)
  File "/opt/ros/melodic/lib/python2.7/dist-packages/rosmaster/master_api.py", line 210, in publisher_update_task
    ret = xmlrpcapi(api).publisherUpdate('/master', topic, pub_uris)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1243, in __call__
    return self.__send(self.__name, args)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1602, in __request
    verbose=self.__verbose
  File "/usr/lib/python2.7/xmlrpclib.py", line 1283, in request
    return self.single_request(host, handler, request_body, verbose)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1311, in single_request
    self.send_content(h, request_body)
  File "/usr/lib/python2.7/xmlrpclib.py", line 1459, in send_content
    connection.endheaders(request_body)
  File "/usr/lib/python2.7/httplib.py", line 1095, in endheaders
    self._send_output(message_body)
  File "/usr/lib/python2.7/httplib.py", line 898, in _send_output
    self.send(msg)
  File "/usr/lib/python2.7/httplib.py", line 860, in send
    self.connect()
  File "/usr/lib/python2.7/httplib.py", line 837, in connect
    self.timeout, self.source_address)
  File "/usr/lib/python2.7/socket.py", line 575, in create_connection
    raise err
error: [Errno 22] Invalid argument

I also upload my master.log file.
master.log
Thanks very much!!