Self Driving Car Prototype

Project Title

Self Driving Car Prototype

Project Area of Specialization Artificial IntelligenceProject Summary

A self-driving car can analyze surrounding without any human interactions and take decisions accordingly without any human interactions. A number of sensors are combined and are used to identify the pathway and road signal from the surroundings. An autonomous car is having reduced costs due to less wastage of fuel, increased safety, increased mobility, increased customer satisfaction and that’s why it has more advantage than traditional cars. The biggest benefit of using a self-driving car is significantly fewer traffic accidents. More than 90% of all accidents are caused by some degree of human error, including distraction, impaired driving, or poor decision making. With self-driving cars making decisions and communicating with one another, the number of accidents should reduce.

The scope of this project is so high because it’s estimated Self-driving cars could reduce vehicular deaths by 90% and bring these totals down. Autonomous cars could save people time by 40% by improving the flow of the traffic and allowing passengers to make phone calls, read, or catch up on work. Self-driving cars can drop harmful emissions up-to 60%, improve fuel economy by 10%, and can eliminate stop-and-go wave by 100%.

Project Objectives

1. To Acquise image from video frame.
2. Object Detection
3. Object Extraction
4. Object Recognition
5. Decision Making

Project Implementation Method

The project contains 3 phases Harware, Software and Designing phase. Each stage is divided into each of our team members. Abdul Qadeer Patujo will be reponsible for hardware of the project, Sajjad Qureshi will be responsible for software part of the project and Miss Rida Jafri will be responsible for all designing part of the project. We have divided our project into series of phases, when first phase is complete we can move to the other phase of the project. Let's go through all phases one by one, first phase of our project is hardware phase and in itself it is divided into more smaller phases. It contains assembling and testing hardware component, after this is done software phase comes now this is the most important part of the project it contains running and testing complex machine learning algorithms, for those we will use some of python's very popular machine learning libraries like (Keras, TensorFlow, Scipy) and for data cleaning and manipulation (Numpy and Pandas) will be used, and for object detection OpenCV will be used. After this the necessary phase comes up which is designing. In designing we'll design mini roads with cars and traffic signals to train our model and present our project working.

Benefits of the Project

• 90% reduction in traffic deaths.
• Eliminate stop-and-go waves by 100%.
• 40% reduction in travel time.
• 10% improvement in fuel economy.
• 60% drop in harmful emissions

Technical Details of Final Deliverable

In final we'll have a mini self driving car prototype which will contain hardware as well software and it will be able to acquise image from video frame, detect object, extract object, recognize and make a decision according. Model will be trained on traffic lights, stop signs, car objects and road lines on higher accuray rate upto 94-95%.

Final Deliverable of the Project HW/SW integrated systemCore Industry TransportationOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	77656
Raspberry pi 4 Model B 4GB	Equipment	1	25000	25000
Arduino UNO	Equipment	1	20357	20357
Robo chese car kit	Equipment	1	13600	13600
Camera	Equipment	1	2699	2699
Power Bank 10000 mah	Equipment	1	8000	8000
Track and Designing material	Miscellaneous	1	8000	8000