Main Content

This robot has been a dream robot for me to build for a long time. Before diving into how to build this robot, let me give a quick overview of what this robot is capable of!

You can ask the robot to follow you around. (Done via the TensorFlow face detection computer vision algorithm)
You can ask the robot to find you and then follow you. (Again this will use computer vision + ML)
You can ask the robot to find any object (from this list) for you, pick it up using its robotic sled and bring it to where you are.
You can give the robot a voice command to carry the collected item and follow you around like an assistant robot.
Best part of all this is you can issue all these commands via speech as the robot has voice recognition.
This robot is truly special because it can use Machine Learning models to ‘see’ the world via a generic camera and perform tasks depending on how the detected object’s position is changing in the camera.

This robot is built around the ever popular Raspberry pi, the incredibly powerful RoboClaw motor controller, and the common Rover 5 robot platform. Furthermore, all the additional physical parts are 3D printed. This robot also uses the Tensorflow USB Coral accelerator to speed up the Raspberry Pi’s slow object detection. More on all this in the next few steps

The first part of this Instructables guide will cover some the theory behind how the algorithms and code works. The second half of this Instructables guide will cover how you can build this robot yourself including the physical building + installing libraries etc.”

Link to article