EMG Controlled Prosthetic Arm
Apr 26, 2025
·
1 min read
Prosthetic arm that can recoganize three gestures - pinch, grasp and release from EMG signals. I focussed on the machine learning model to classify the different guestures, and coding the microcontroller.
Everything in this video (except for the laptop, electrodes and OpenBCI module) has been made in house! The hand is 3D printed and the PCB was printed at IITB. Notice how the probabilities of different motions (seen in red, green and blue on the computer screen) fluctuate as the motion is changed!
Authors
Anshu Arora
(अंशु अरोड़ा)
MS Student
I am interested in machine learning and robotics, with a focus on reinforcement learning, optimization, and data-efficient learning algorithms for embodied agents. My goal is to develop systems that can generalize, adapt, and make effective decisions under real-world constraints. I am particularly excited by problems at the intersection of learning, control, and autonomous interaction.