Controlling A Robotic Arm Using Handwritten Digit Recognition Software

摘要

Repetitivetasks in the manufacturing industry is becoming more and more commonplace. Theability to write down a number set and operate the robot using that number setcould increase the productivity in the manufacturing industry. For thispurpose, our team came up with a robotic application which uses MNIST data setprovided by Tensorflow to employ deep learning to identify handwritten digits.?The systemis equipped with a robotic arm, where an electromagnet is placed on top of therobotic arm. The movement of the robotic arm is triggered via the recognitionof handwritten digits using the MNIST data set. The real time image is capturedvia an external webcam. This robot was designed as a prototype to reducerepetitive tasks conducted by humans.