MartyG-RealSense
commented
1 year ago Hi @zhanglepy The paper at the link below (PDF document) uses an algorithm that the researchers developed to take data from a D435 depth camera to plan paths through agricultural greenhouses. In previous research they had used a 2D laser range finder to sense drivable areas prior to planning their paths, but the laser range finder had issues identifying the plants as obstacles. Using the depth camera allowed them to refine the algorithm to correctly allow the robot to move through the rows without collisions.
https://www.jstage.jst.go.jp/article/jsp/23/4/23_201/_pdf/-char/en
Alternatively, https://github.com/IntelRealSense/realsense-ros/issues/1522 has information about path planning with RealSense and ROS using the move_base package.
Another ROS method for path planning with a D435 is in the research paper here:
https://www.mdpi.com/2076-3417/11/4/1467
As these projects work with the D435 camera model and so do not rely on an IMU, they may be convertable for use with the D405 camera.
3D reconstruction and path planning Take photos with the D405 camera to obtain point cloud information of the object, and perform 3D reconstruction through multi angle registration. Then, based on the results of 3D reconstruction, do you have any methods for path planning on its surface?Finally, according to the planned path, control the motion of the robotic arm