Search

To address the issue of dynamic 3D circular features recognition in robot arm grasping, we propose a feature-based and incremental simultaneous points and circles structure from motion system. First, we represent the 3D target scene with sparse point cloud from multiple observations. The fundamental points construction pipeline combines the benefits of feature-based mapping and probabilistic depth estimation, which reduce the computational cost of generating practical 3D structures. Second, accurate 3D circles are extracted from the keyframes and are optimized in the backend. The circles construction pipeline attempts to find potential circles in the produced sparse point cloud and apply an adjusted level set method to do a novel 3D circle optimization process, which can work on keyframes smoothly. The integrated system is compared with other real-time construction systems and outperforms in industry scenes with more stable land-marks. Meanwhile the experimental results illustrate the ability of capturing circular features in target scenes.

In automated grasping of microparts or objects with unknown dimensions and orientations, at least two cameras have to be used to acquire the depth information. In addition to recognition and reconstruction of the real-world coordinates of the target objects, the system has to be able to detect also the real-world coordinates of the microgrippers from the images. This paper presents a scale and rotation invariant microgripper detection method that uses a planar pattern. The method is suitable especially for prototyping systems, whose composition might vary between the experiments. The gripper detection is shown to be accurate enough for challenging micromanipulation tasks of small electronic components and individual paper fibers.

In this paper a control strategy based on second order sliding modes, generally applicable for position tracking control of electro-hydraulic valve-cylinder drives (VCD), is proposed. The main target is to overcome problems with linear controllers deteriorating performance due to the strong nonlinearities characterizing VCD's. The proposed controller requires pressure-, valve- and piston position measurements, and is based on the so-called super twisting algorithm and compensation of controlgain nonlinearities. Simulation results demonstrate strong robustness when subjected to large perturbations in coulomb friction.