AUTOMATIC ASSEMBLY OF INTERLOCKING BUILDING CUBES BY USING VISUAL SERVOING APPROACH

Most of the robotic arms are set up for operation by the teach-and-repeat (T&R) technique, also known as coordinate-based control, using pre-recorded coordination values to generate robotic arm trajectories. This technique is inefficient because it requires teaching a robotic arm every single coordinate point to complete an operation. It is a manual, tedious and time-consuming task. Moreover, this task needs to be repeated if there are slight changes in the operation. This paper studied the visual servoing approach to replace the T&R technique in assembling different interlocking building cubes (IBC) combinations. The proposed method uses an image-based visual servo (IBVS) with a dynamic look-and-move system, and the eye-to-hand system, which requires computing the incremental joint angles of the robotic arm, a novel kinematic formula with a combination of Trigonometry formulas has been proposed in this paper. The experimental results show the feasibility of using a visual servoing approach to complete the assembly tasks without relying on the T&R technique and achieved an average success rate of 90% and an average of 40.2 seconds for task duration. Thus, this eliminates the tedious and time-consuming tasks of teaching the coordinate points to the robotic arms. Further improvement on the servo motor, camera and computer processor can be done to increase the accuracy, computation time and task duration in future.