About

Abstract

While many stores offer remote-controlled race cars, most lack autonomous capabilities. The primary objective of this project is to create a vehicle from the ground up that not only responds to manual remote control but also has the ability to navigate and race autonomously.

The remote control for this car will be in the form of an Android application, which establishes communication with the car through Bluetooth technology. This mobile application will serve as the interface for the user to steer and control the car when desired. 

To enable autonomous operation, the project involves the development and training of a convolutional neural network (CNN) using Python and popular machine learning libraries such as TensorFlow and Keras. This CNN will act as the “brain” of the car, processing sensory input and making real-time decisions based on the data it receives. This allows the car to react to its environment and navigate autonomously.

The chosen microcontroller for this project is a Raspberry Pi, a flexible and powerful single-board computer. The Raspberry Pi will serve as the central processing unit for the car, managing the CNN, sensor data, and all necessary computations for both manual and autonomous operation.

In summary, this project is an endeavor to create a unique race car that combines the fun of remote-controlled racing with the intelligence of autonomous navigation. The integration of an Android remote control application, a convolutional neural network, and a Raspberry Pi microcontroller will enable this car to provide a thrilling experience that caters to both manual and self-driving preferences.