A robotic system is developed to automate the packing of polycrystalline silicon nuggets into a fragile fused silica crucible in CZ semiconductor wafer production. The highly irregular shapes of the nuggets make this a difficult and challenging task. In this system, nugget grasping is done with a three-cup suction gripper and nugget manipulation is attained with a 7 DOF SCARA manipulator. An op...

This paper proposed a kinematic model and its calibration scheme to further improve an industrial robots absolute positioning accuracy over the entire workspace. To demonstrate effectiveness in simplified kinematics, this only targets SCARA (Selective Compliance Assembly Robot Arm)-type robot. The includes not link length errors rotary axis angular offsets, widely known as Denavit-Hartenberg (D...

This paper presents a new robot which produces four motions for high speed handling (three translations and one rotation about a given axis in world coordinates). This machine is an evolution of H4’s architecture. Firstly, H4 advantages are recalled, and some limitations are mentioned. To compensate for these limitations a new design of the traveling plate is proposed. A description of the whol...

In this paper are proposed two control algorithms, based on the sliding-mode technique, to track a trajectory and regulate the force ejected by the end effector in a 4-DOF Scara robot system subject to a position constraint. The system may be in non-constrained motion at some time, or in constrained motion at some other time. It is shown that the nonlinear system is globally asymptotically stab...

In this papera switching control strategy for robust stabilization of the 2nd-order non-holonornic 2-DOF SCARA robot Ft21)l is presented. The Ist joint is actuated by a direct drive motor, whereas the 2nd joint is equipped with a brake. The unactuated 2nd joint is controlled by non-collocated linearization and a PDcontroller. A stability region is den”ued and robustness is achieved by exploitin...

Abstract This work proposes a switched time delay control scheme based on neural networks for robots subjected to sensors faults. In this scheme, multilayer perceptron ( MLP ) artificial network ANN is introduced reproduce the same behavior of robot in case no The reproduction characteristic s allows instant detection any important sensor order compensate effects these faults robot’s behavior, ...

Abstract Because of their elastic links and joints, high-speed parallel robots for pick-and-place operations inevitably suffer from residual vibrations that significantly degrade positioning accuracy. An effective approach based on the input shaping technique is presented in this paper suppressing vibration these robots. After addressing design principle an shaper a robot with flexible actuated...

This paper presents the design, development and implementation of a Dynamic Fuzzy Neural Networks (D-FNNs) Controller suitable for real-time industrial applications. The unique feature of the D-FNNs controller is that it has dynamic self-organising structure, fast learning speed, good generalisation and flexibility in learning. The approach of rapid prototyping is employed to implement the D-FN...

Recent advances in data processing have stimulated the demand for learning graphs of very large scales. Graph Neural Networks (GNNs), being an emerging and powerful approach solving graph tasks, are known to be difficult scale up. Most scalable models apply node-based techniques simplifying expensive message-passing propagation procedure GNN. However, we find such acceleration insufficient when...