koide3

Hi @GLKode, I think the cause is the confliction of the nodelet manager names. hdl_graph_slam uses the same nodelet manager name as the one used in velodyne_driver so that they...

@improve100 , If you did it with a ROS bag, could you try to slow down the playback speed? I guess the CPU power was not enough, and the SLAM...

@improve100 , OK, your PC is definitely powerful enough for this package. Could you upload your launch file so that I can check some parameters?

@improve100 , About the scan matching problem, maybe ndt_resolution is too small for outdoor. Larger resolutions (2m ~ 5m) are better for such environments. I'm not sure what is the...

To use the IMU feature, you need to install [ethzasl_sensor_fusion](http://wiki.ros.org/ethzasl_sensor_fusion). As it's apt package is no longer available for ROS noetic, you would need to build it by yourself.

Hi @ZOUJIASHUAI , Haha, thanks for your appreciation. So far, this package does not support multiple LIDAR inputs. An easy way is to first integrate multiple LIDAR data into one...

Thanks for your feature request. Although I think it's a reasonable feature, I don't have enough time to implement and test it unfortunately. I believe the requested feature can be...

What ```computeCovariances()``` in ```gicp.h``` computes is not the covariance of a pose but the covariance of a point. Estimating the covariance of a scan matching result is actually difficult to...

Hi @robot54 , I think you can give GICP a try. I found that NDT shows a large drift in a large environment while GICP is much accurate in many...

Please make sure that ```fast_gicp``` package is cloned with ```--recursive``` option.