AI Powered Bionic Arm

Introduction

The world of prosthetic hands is becoming more and more sophisticated. However, they are sometimes simply too expensive. This is especially the case for children, who often need a new hand every year as they grow. Not having use of one extremity is exceptionally restrictive.Every year in the UK around 600 people suffer the loss of upper limbs, half of whom are aged 15 to 54. In the US, there are 500,000 new upper limb amputees each year. This device could lead to a new generation of prosthetic limbs giving the user the ability to reach for objects without thinking.

How it Works

A camera fitted to the hand rapidly takes a picture of the object in front of it and feeds the information to an electronic “brain”. The computer automatically assesses the object's shape and size within seconds and triggers the correct movements needed to pick it up, whether a light pinch or firm grip. In fact, just like a real hand, the user can reach out and pick up a cup or a biscuit with nothing more than a quick glance in the right direction.

Why 3D Print it?

• 3D Printing a bionic hand would cost way lesser than getting it manufactured, say using Injection Molding
• Its cost effectiveness is an advantage especially for kid, who are going to need a new Bionic Hand in every year as they grow.
• It would lead to shorter wait time for the people in need of a bionic hand.
• The biggest advantage of 3D Printing it will be that the 3D models of the hand can be designed in one corner of the world and be sent across the globe to be printed on any other Desktop or Commercial Grade 3D Printer, which would not be possible by using other types of manufacturing methods.

Advantages of a Bionic Hand based on AI

• Current prosthetic hands are controlled by myoelectric signals, muscular electrical activity recorded from the skin surface. Learning to operate them takes practice, concentration and time. Developing the new system, based on artificial intelligence (AI), involved “teaching” a computer how to recognize the grip needed for different objects can turn out to be breakthrough.
• This whole system is based on machine learning,so the computer isn't just matching an image, it's learning to recognize objects and group them according to the grip type the hand has to perform its task. This enables it to accurately assess and pick up an object which it has never seen before, a huge step forward in the development of bionic limbs.
• This is a sideways approach. While other attempts are trying to get the hands to pass touch information back to the user, reproducing how actual hands work. This solves the problem with a different approach. Instead of touch it uses vision and pattern recognition.

Conclusion

The uniqueness of this system is that it's much more flexible and the hand is able to pick up normal objects, which is necessary since in everyday chores people effortlessly pick up a variety of objects that they have never seen before. This project aims at helping millions of people across the world. All of this can be achieved at a fraction of the cost of a Bionic arm that is industrially manufactured.