Tracking an elastic object with an RGB-D sensor for a pizza chef robot

This paper presents a method to track in real-time a 3D object which undergoes large deformations such as elastic ones, and fast rigid motions, using the point cloud data provided by a RGB-D sensor. This solution would contribute to robotic humanoid manipulation purposes. Our framework relies on a prior visual segmentation of the object in the image. The segmented point cloud is then registered first in a rigid manner and then by non-rigidly fitting the mesh, based on the Finite Element Method to model elasticity and on geometrical point-to-point correspondences to compute external forces exerted on the mesh. The real-time performance of the system is demonstrated on real data involving challenging deformations and motions, for a pizza dough to be ideally manipulated by a chef robot.