/AnkiWhere

Object detection for Cozmo Anki robots

Primary LanguageJupyter Notebook

data visualization samples

Anki Learn is a project aimed to add a custom object detection to Cozmo's Anki robots. It is based on project CozmoPedia developed by prof. Dave Touretzky and used in Cognitive Robotics course at Carnegie Mellon University.

Project Architecture

Project Architecture

Image Classification

For the image classification, I used transfer lerning to over Inception model to train the model with images taken from the Cozmo's onboard caemra. Image Classification Image Classification Results

Image Detection and Turning towards the object

For image detection, I used slicing technique to divide the image into vertical slices and find the object in them. The processed data would be used by the state machine to direct the robot. Image Detection

The overall architecture is illustrated here: Image Detection