[ndt_matching] gpu version died
Required information:
- Operating system and version:
- Ubuntu 18.04
- Autoware installation type:
- Autoware version or commit hash
- master
- output of git rev-parse HEAD: 63d8bc77 (of core_perception)
- ROS distribution and version:
- rosdistro: melodic
- rosversion: 1.14.3
- ROS installation type:
- from binaries, http://wiki.ros.org/melodic/Installation/Ubuntu
Description of the bug
the ndt_matching with pcl_generic method works fine, but pcl_anh_gpu method always crashed when started
Steps to reproduce the bug
- in simulation tab, select bag file (demo data provided by autoware), press start and pause
- in setup tab, press tf and vehicle model
- in map tab select and press point cloud (demo data provided by autoware) select and press vector map (demo data provided by autoware) select and press tf (demo data provided by autoware)
- in simulation tab, press pause again to resume, in rviz, verify that the pcd map and vector map are loaded correctly
- in sensing tab, click voxel_grid_filter with default parameters
- in computing tab, click nmea2tfpose with default parameters select pcl_anh_gpu method and click ndt_matching
- in simulation tab, press pause to resume
- then ndt_matching died
Expected behavior
localize correctly
Actual behavior
ndt_matching died with error message: Error: out of memory /home/leon/autoware.ai/src/autoware/core_perception/ndt_gpu/src/VoxelGrid.cu 181 terminate called after throwing an instance of 'boost::exception_detail::clone_impl<boost::exception_detail::error_info_injectorboost::lock_error >' what(): boost: mutex lock failed in pthread_mutex_lock: Invalid argument [ndt_matching-1] process has died [pid 8436, exit code -6, cmd /home/leon/autoware.ai/install/lidar_localizer/lib/lidar_localizer/ndt_matching __name:=ndt_matching __log:=/home/leon/.ros/log/a41e9918-b072-11e9-96f6-9cb6d01138d9/ndt_matching-1.log]. log file: /home/leon/.ros/log/a41e9918-b072-11e9-96f6-9cb6d01138d9/ndt_matching-1*.log
Screenshots
Additional information
- nvidia graphic card: gtx980m
- driver version: 410
- CUDA version: 10.0
- CUDNN version: 7.6.1.34
I tried the Docker version followed the steps by https://gitlab.com/autowarefoundation/autoware.ai/autoware/wikis/Docker,
and run with command ./run.sh -ros-distro melodic
, this error also occurred.