Week 0 - Laying the Groundwork
Summary
In my initial meeting with my advisor, we outlined the core objectives of my Final Year Project (TFG). To build a solid theoretical foundation, I began by reading a master’s thesis and also got started with GitHub Pages to maintain this weekly blog.
Progress This Week
This week, I focused on the previously mentioned thesis to gain a better understanding of the key concepts in autonomous driving:
Key Topics in Autonomous Driving
Computer Vision
Computer Vision is a branch of artificial intelligence focused on the processing of visual information. In the context of autonomous driving, it is used to detect objects in the vehicle’s environment and to extract relevant information from images captured by the vehicle’s cameras. Techniques such as image segmentation and feature detection are employed to process visual information.
Neural Networks
Neural Networks are a mathematical model inspired by the biological behavior of neurons and how these are organized in the brain. In the realm of autonomous driving, they are used to make decisions based on processed visual information. Various architectures of neural networks are described, such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), along with different databases and simulators used in research.
End-to-End Learning
End-to-End Learning is a machine learning technique that allows neural networks to be trained to perform a complete task, rather than breaking it down into sub-tasks. In the context of autonomous driving, it is used to train neural networks to autonomously drive the vehicle. Various neural network architectures used in research are introduced, such as PilotNet and ControlNet.
Simulators
Simulators are used to train and test neural networks in a safe and controlled environment. In the context of autonomous driving, they are used to train neural networks to drive the vehicle in various situations and environments. The use of the Gazebo simulator in research is described, along with different training and testing environments that allow the vehicle to learn various stimuli for driving in diverse situations.
Databases
Databases are used to train neural networks with visual information and speed data. In the realm of autonomous driving, they are used to train neural networks, allowing the system to learn from diverse situations and conditions.
As I’m gearing up to work with neural networks, I explored some instructional videos and even coded a few basic neural networks. I used Python, TensorFlow, Keras, and Google Colab for these initial hands-on exercises.