Automatic precision robot assembly system with microscopic vision and force sensor

Abstract

An automatic precision robot assembly system is established. The robot assembly system mainly consists of an industrial robot, three cameras, a micro force sensor, and a specific gripper. The industrial robot is a six-axis serial manipulator, which is used to conduct grasping and assembly subtasks. Two microscopic cameras are fixed on two high accuracy translational platforms to provide visual information in aligning stage for assembly. While one conventional camera is installed on the robotic end effector to guide the gripper to grasp component. The micro force sensor is installed on the robotic end effector to perceive the contacted forces in inserting stage. According to the characteristics of components, an adsorptive gripper is designed to pick up components. In addition, a three-stage "aligning-approaching-grasping" control strategy for grasping subtask and a two-stage "aligning-inserting" control strategy for assembly subtask are proposed. Position offset compensation is computed and introduced into aligning stage for assembly to make the grasped component in the microscopic cameras' small field of view. Finally, based on the established robot assembly system and the proposed control strategies, the assembly tasks including grasping and assembly are carried out automatically. With 30 grasping experiments, the success rate is 100%. Besides, the position and orientation alignment errors of pose alignment for assembly are less than 20 mm and 0.1 .

Micro-Vision Based High-Precision Space Assembly Approach for Trans-Scale Micro-Device: The CFTA Example

“…Recently, the micro-assembly technique has been widely applied to fields including aerospace, biomedical, materials science, and others MEMS, and micro-assembly robots have been developed for assembling micro-parts [ 1 , 2 , 3 ]. Micro-assembly robots are usually equipped with micro-vision for monitoring the assembly process [ 4 , 5 , 6 ]. However, micro-vision is problematic in that the larger the magnification, the smaller the field of view (FOV), that is, there is a contradiction between high precision detection and wide field of view.…”

Learn multi-step object sorting tasks through deep reinforcement learning

“…The new question is whether robots can adapt to new environment and take such multi-step tasks when the components and boxes are totally new or even when the sorting rules are changed. In this context, traditional control methods are unsatisfied to model complex unpredictable processes analytically [2,3,4]. Therefore, robots should not repetitively execute preprogrammed actions as usual, but learn how to plan and execute actions according to new situations and task requirements.…”

Finding the Optimal Pose of 2D LLT Sensors to Improve Object Pose Estimation

“…There are systems that perform assembly based on automatic guidance for large objects [1], where the robot end-effector must have a sensory subsystem to ensure sufficient precision. In [2], the authors deal with assembly of small components, where they use one camera in the end-effector to guide the robot to grasp objects, two cameras in the alignment phase of the object before assembly, followed by feedback from the force sensor during assembly; however, the object was correctly oriented for robot grasping. In the study [3], the authors achieve significant assembly accuracy with an industrial robot to hundredths of a degree by on-line movement compensation.…”