Pose Estimation and 3D Reconstruction for 3D Dispensing
Abstract: Currently in most of the cases the material deposition or dispensing is done only on planar surfaces, in applications such as extrusion 3D printing and surface mount technology (SMT) electronics assembly solutions. In future, the dispensing will be carried out on arbitrary three dimensional objects, where the dispenser needs to know the exact shape and location of them. This drives the necessity of using vision based high degree of freedom (DoF) robotic manipulator dispensers, instead of existing hard-coded Computer Numerical Control (CNC) based limited DoF 3D dispensers. Given a 3D object to be dispensed on and a CAD model of it along with the dispensing path, this thesis aims to answer the following industrial problem: How to adapt the 3D dispensing path if the object is displaced from CAD model position? The most important requirement is high dispensing accuracy, in the order of 100 _m with respect to the ideal (CAD) dispensing path, to improve the dispensing quality. Moreover, maintaining an appropriate distance between the dispensing tip and the surface of the object is important for both the positioning accuracy and the volume precision of the deposit. In order to achieve high dispensing accuracy, robust volumetric scanning (3D reconstruction) of the object closely resembling the CAD model and robotic manipulator with high path tracking accuracy are required. However, the scope of this thesis is restricted only to 3D reconstruction and dispensing path adaptation based on the object’s pose displacement. The additional requirements are low overall tact time and low equipment cost. This thesis aims at three things: i) investigating different types of fiducial marker based camera 3D pose estimations using low cost consumer-grade RGBD camera ii) generating 3D reconstruction of the object for all the pose estimation types and iii) finding the object pose displacement from CAD model position. Checkerboard and ArUco markers are used as fiducial markers. Different types of pose estimation involving RGB only and RGB-D fused techniques are used to find the pose of the object. Truncated Signed Distance Function (TSDF) is used for surface reconstruction and Iterative Closest Point (ICP) is used for finding the pose alignment between the CAD and reconstruction. Tests are conducted for different object shapes in different positions. Then the reconstruction and the dispensing path adaptation accuracy are evaluated, along with the alignment tact time.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)