Deep Learning with Domain Randomization Course - Python
Learn how to train any robot to recognize an object and pinpoint its 3D location with only an RGB camera and a lot of training with Keras.
Course Summary
Welcome to this micro course! This course is intended for the people that want to learn about deep learning using Keras.
In this case, we use a very interesting approach to learning which is Environment Randomization This method exploits the versatility of environment generation in simulations to train a robot in a way that the resulting model is very robust, no matter the lighting conditions. It also makes the transition from simulated learning to reality much smoother and fast. Learn through hands-on experience how to train a robot for 3D object recognition using random environments.
Keras will be the cornerstone of this system and you will learn all the necessary skills to generate training data, convert it to a database, train a MobileNetV2 model, retrain it and make predictions with it.
The final project is the training of a garbage picking robot, from training data generation to the final garbage detection and picking program. Dive into the fantastic world of DeepLearning with Keras right now!
What you will learn
- How to use Keras in a basic way
- How to train a deep neural network using a Gazebo Simulation
- How to work with ROS+Gazebo+Keras in tandem.
- How the Random Environment generation works in Gazebo.
Course Overview
Quick Demo
Unit for previewing the contents of the Course.
Step By Step Simple Guide
Learn the basic steps in order to train a neural network so that it can recognize an object and tell us its location in 3D space.
Exercises For XY motion Spam
Learn how to retrain a previously trained model and work on improving our detection model.
Exercises for Spam and a Distractor
Distract the model with another object in the scene that moves around and could be mistaken by the target SPAM object.
Exercises with Distractor and Random Env
Train the model with a random environment to make it more robust in any lighting condition. You will also train with a huge image database to emulate the real deal.
Microproject Garbage Collector
It's time for you to test everything you have learned with this course! You will work with a Garbage Collector robot. With it, you have to find an object amidst other distractors, move to a picking distance, and pick that object.
Teachers
Miguel Angel Rodriguez
Crashing engineering problems. Building solutions.
Robots used
Fetch robot
Garbage Collector Robot robot
Learning Path
Machine Learning for Robots
