Solid State Lidar Integration Tutorial #3719
beginningfan
started this conversation in
Show and tell
Replies: 1 comment 1 reply
-
Thank you for sharing. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
The LiDAR currently used by Autoware is Ouster-64. This LIDAR has low detection ability for distant targets, with only a few points on a vehicle at a distance of 30 meters.So we added a LIDAR RS-m1 of robosense to the existing code to enhance the detection ability of distant targets ahead.
This is the introduce of m1.
And in the picture below, we can clearly compare the detection effects of two LiDARs on distant targets. There are two cars here, one is at a distance of 20 meters. The other is at 50 meters. The white points are from ouster-64. The red points are from rs-m1.
You can click on the image below to jump to our introduction video
Here is the tutorial to add another LIDAR to autoware.
add lidar name here
The topic of robosense's official lidar driver is
rslidar_points
. To adapt to existing code, we need to modify the topic name fromerslidar_points
to/sensing/lidar/rslidar/outlier_filtered/pointcloud
.As usual, I use the pointcloud from rslidar whithout preprocessing. If you need preprocessing, you have to make sure the output topic is
/sensing/lidar/rslidar/outlier_filtered/pointcloud
.add
rslidar_crop_box_filter
andrslidar_ground_filter
here after "common_ground_filter"The specific parameter values need to be adjusted according to the actual situation.
Don't forget to add the TF for rslidar
Here is our calibration tool whitch you can use to calibrate your LIDARs
Beta Was this translation helpful? Give feedback.
All reactions