Low cost vehicle driving assistance system
The project intends to increase vehicle operator awareness with the integration of a Low-Cost Driving Assistance system in older car models. Situational awareness during driving significantly reduces the number of road traffic accidents, as proved by literature. A 4-wheel mobile robot is used as the plant representing a vehicle for easier and rapid prototyping. The plant is controlled by a Raspberry Pi3 to achieve the desired control choice as well as do all required computational processes. Image processing using a retrained Resnet50 neural network is adopted for road traffic signs. A 54% accuracy rate for image recognition is recorded. The wheeled mobile robot is successfully modeled and deemed unstable while the circuit is simulated and works as expected.
Capstone Project submitted to the Department of Engineering, Ashesi University in partial fulfillment of the requirements for the award of Bachelor of Science degree in Electrical and Electronic Engineering, May 2020
traffic accidents, driver awareness, robot, road accident prevention