Avatar The Society of Robotics and Automation is a society for VJTI students. As the name suggests, we deal with Robotics, Machine Vision and Automation

Unlocking the Future: The EMG ArmBand Project

To create an EMG (Electromyography) Arm Band, which may be worn as a bracelet, to detect hand movements and orientation via muscle impulses transmitted through your forearm.

Purva Yeshi

– Anuj Akotkar

Greetings, fellow tech enthusiasts! We are thrilled to embark on this exciting journey through the realm of Embedded Systems, IoT, PCB Designing, and Machine Learning with our innovative project - EMG ArmBand. Allow us to introduce ourselves and shed light on the captivating world we are about to explore.

Meet the Team:

Purva Yeshi I have enthusiasm for continuously learning about the latest technologies and methodologies within my field. Exploring new horizons is my passion, and I actively seek opportunities to translate my knowledge into practical solutions for real-world challenges.

Anuj Akotkar enjoy learning new technologies and methods in this field, and looking for opportunities to apply them to real-world problems & also enthusiastic about sharing my passion and knowledge with others, and I love to work with people who have similar interests and aspirations and thrilled to be part of this PROJECT- EMG ArmBand.

Why This Project?

Delving into the domains of embedded systems, IoT, PCB designing, and machine learning is not just a coincidence for us. These are the very realms that ignite our curiosity and passion. The EMG ArmBand brings all these domains together, making it the perfect playground for us to explore, innovate, and excel. The opportunity to merge our interests with a real-world application is what truly drew us to this project.

Project Overview:

Enter the captivating world of the EMG ArmBand, a project at the crossroads of innovation. Imagine a wearable bracelet that does more than accessorize your wrist. Our goal is to create a device that translates your hand movements and orientations into digital commands. The secret lies in harnessing the power of Electromyography (EMG).

The EMG Advantage:

Electromyography is a technique that detects electrical signals produced by muscle contractions. These signals hold the key to understanding and replicating hand gestures and movements. By tapping into these signals in the forearm, we aim to bridge the gap between biology and technology.

Our Aim:

At the heart of our project is the challenge of designing and integrating EMG sensors and microcontrollers within a sleek and functional wearable - the EMG ArmBand. We’re not stopping there; we’re infusing the ArmBand with the magic of Machine Learning. This will enable the device to learn and adapt to your unique muscle signals, making interaction more intuitive and responsive.

Project Domains:

  • Embedded Systems: Embedded systems are specialized computing systems designed to perform specific tasks or functions within a larger system. In this project, an embedded system would be the core component of EMG ArmBand. It would include microcontrollers or microprocessors that process data from EMG sensors, control device operations, and manage communication with other components. The embedded system ensures that the bracelet functions as intended and responds accurately to muscle impulses and hand movements.

  • IoT (Internet of Things): IoT refers to the network of physical devices, vehicles, buildings, and other items embedded with electronics, software, sensors, and connectivity. In this project, IoT elements could involve connecting the EMG ArmBand to the internet or other devices. This could allow for remote monitoring, data transmission, or even integration with other smart devices. For example, the arm band’s data on hand movements and orientation could be sent to a remote server for analysis and further processing.

  • Machine Learning (ML): Machine Learning is a subset of artificial intelligence that focuses on developing algorithms and models that enable systems to learn from data and make predictions or decisions without being explicitly programmed. In this project, ML would play a role in training the system to recognize and interpret muscle impulses from the EMG sensors. You would collect data from users wearing the arm band while performing various hand movements, and then use this data to train a model that can accurately classify different movements and orientations.

Hardware Components:

  • ESP32 Microcontroller with ESP-NOW Protocol: The ESP32 is a powerful and versatile microcontroller renowned for its Wi-Fi and Bluetooth capabilities, making it exceptionally well-suited for IoT applications. With its dual-core processor, an array of digital and analog pins, and generous memory and storage capacities, the ESP32 becomes a prime candidate for your EMG Armband project. The ESP32 will not only play the role of a central processing unit but will also seamlessly integrate the ESP-NOW protocol to facilitate efficient communication with ESP to ESP of the Armband system.

  • EMG Sensors: Electromyography(EMG) sensors detect and measure the electrical activity generated by muscle contractions. These sensors are crucial for capturing the muscle impulses transmitted through the forearm, which are then interpreted as hand movements and orientation. EMG sensors typically consist of electrodes that are placed on the skin’s surface or embedded within the arm band. They convert the analog electrical signals from the muscles into digital data that the microcontroller can process. The accuracy and sensitivity of the EMG sensors play a significant role in the overall performance of the Armband.

  • Flexible PCB (Flex PCB): The flexible printed circuit board(Flex PCB) serves as the physical platform for integrating the components of the arm band. It allows for bending and conforming to the shape of the forearm while hosting the ESP32 microcontroller, EMG sensors, power management circuits, and other necessary components. The layout and design of the Flex PCB are critical to ensure proper placement of components and efficient routing of connections while maintaining flexibility and durability.

The Road Ahead:

Of course, every new idea comes with its own set of challenges. We’re already spotting some potential hurdles, like getting the signals just right, figuring out where to place the sensors, and making sure our machine learning model learns the way we want it to. But you know what? It’s these very challenges that will add the spice to our project and make it uniquely ours.

Our Journey So Far:

Let’s fast-forward a bit and share what we’ve already achieved. We’ve delved into the intricate realm of LSA sensor readings, adeptly extracting raw values from the ADC without the reliance on the sraboard.h header.

What’s Brewing Next: But that’s just the beginning. Currently, our focus is fixated on the ESP-NOW Communication protocol. Using ESP-NOW for communication between components could enable seamless and efficient data exchange between the EMG sensors and the main microcontroller.