Autonomous Car

Autonomous vehicles are automobiles that can move without any intervention by detecting the road, traffic flow, and surrounding objects with the help of the control system they have. These vehicles can detect objects around them by using technologies and techniques such as RADAR, LIDAR, GPS, Odometr

Project Title

Autonomous Car

Project Area of Specialization

Artificial Intelligence

Project Summary

Autonomous vehicles are automobiles that can move without any intervention by detecting the road, traffic flow, and surrounding objects with the help of the control system they have. These vehicles can detect objects around them by using technologies and techniques such as RADAR, LIDAR, GPS, Odometry, and Computer Vision. 

So our aim is to simulate will be the ability to detect the traffic sign and able to control cars by Video and Image Analyzing, The autonomous car will use visual information; therefore, it is required to have multiple cameras mounted on the vehicle.

Project Objectives

In this project, we aimed to add an emergency vehicle priority awareness feature to autonomous cars. The autonomous car that we simulate will be able to detect the vehicles, signs, paths, and objects, and their location and direction. The autonomous car will use visual information; therefore, it is required to have multiple cameras mounted on the vehicle.

Our system will include:

• Lane is detecting and following
• Object recognition and auto brake
• Route Planning

The purpose of this document is to provide a debriefed view of the requirements and specifications of the project called M-Car.

The goal of this project is to make an autonomous self-driving car, capable of maneuvering around bends, avoiding obstacles and following traffic signals and road signs.

The tools used in this project and described in this document are:

• Python library for machine learning
• C++ for Car Control.

The hardware used in this project and described in this document are:

• RC Car serving as the actual self-driving car
• Image Processing used for controlling the car speed and turning radius
• Camera to detect objects in front of the car
• Raspberry Pi used for capturing and transmission of camera data and communicating
• Android App Or web app used for capturing objects in front of the car

Project Implementation Method

Hybrid Model

In this model the product is developed in increments and in module-wise one after one, each module contains more functionalities than before. These smaller pieces are then built and delivered to clients in increments. Quick response from clients. Each module is smaller than compared to the whole module. This model is used in our project.

 System overview

We aimed to add emergency vehicle priority awareness features to autonomous cars. In our project, we plan to use Artificial Intelligence, Machine Learning, and Image Processing methods and test the results in a simulation environment. The Autonomous Vehicle Drive Simulator that we will use need to provide us to simulate sensors such as LIDAR, GPS, radar and gives potential sensor outputs, with these outputs and by trying out possible traffic scenarios we will improve the software that we will make.

When an emergency vehicle approaches, with audio sensors the vehicle, will recognize sirens and light sensors it will check if an emergency vehicle is behind the car and not on the opposite side of the road, then will switch to an available line to clear emergency vehicle’s way. This feature not only emptying based on one lane rule because the emergency vehicle can approach from the left lane, try to make an emergency corridor, or can use the shoulder of the road.

5. Architectural design

The structure of the system explains its core components, their relationships, and how they deal with each other. Software architecture and design includes several factors such as business strategy, quality attributes, human dynamics, design, and IT environment. In Architecture, nonfunctional decisions are cast and separated by the functional requirements. In Design, functional requirements are accomplished. Client module is very important. It is a major module in this client have can see car performance, accuracy its status and can also drive it by app A combination of the modules makes up the system. We can use flowcharts to represent and illustrate the architecture.

Benefits of the Project

Safety Requirements

• Systems Safety: Vehicle will be tested in different environments to make sure it responds safely to software malfunctions, near crashes, near breakdowns, loss of traction and other risks.
• Ethical Considerations: Humans have to take instant ethical decisions several times when on road. The car will also be programmed to make ethical decisions in case of emergency.
• Detection and Response: Vehicle will be able to detect and respond to other vehicles, pedestrians, animals and traffic signals. It will be able to change lanes, take turns and overtake other vehicles on the road based on the detection.
• Laws and Practices: Vehicle will follow laws of the location it is being operated in. It will be able to recognize different speed limits and traffic rules of different states and cities. The vehicle should be able to violate the law to avoid any fatal accident.
• Certifications: Any new software updates or driverless features must be submitted and get verified from USA

5.3 Security Requirements

• Data Sharing: Self-driving car collects a lot of data on the go. Data and statistics storage will be done to maintain the correct functioning of the car and to reconstruct what went wrong in case of a breakdown.
•  

5.4 Software Quality Attributes

• Compatibility: Any additional feature that will be added to the self-driving car should peacefully co-exist with existing features.
• Error Handling: The vehicle should not cause or trigger any events that create an accident-prone situation on the road events as loss of network.

Technical Details of Final Deliverable

Deep Learning Model design

This project is coded in C++, Python, C++ is used for Circuit; python is used for Raspberry Pi are used in android applications.

TensorFlow

It's a machine learning library for developing and implementing machine learning algorithms. It is a combination of both customizability and simplicity of use.

Raspberry Pi

It is a small form factor microprocessor. It provides the right mix of portability and CPU power for the application. It is used for preprocessing the image data and sending it to the GCP server.

Final Deliverable of the Project

Hardware System

Core Industry

Transportation

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com