MACHINE LEARNING BASED ECO FRIENDLY AUTONOMOUS CAR

Automation can help reduce the number of crashes on our roads. Government data identifies driver behavior of error as a factor in 94 percent of crashes , and self-driving vehicles can help reduce driver error. Higher levels of autonomy have the potential to reduce risky and dangerous driver behavior

Project Title

MACHINE LEARNING BASED ECO FRIENDLY AUTONOMOUS CAR

Project Area of Specialization

Artificial Intelligence

Project Summary

Automation can help reduce the number of crashes on our roads. Government data identifies driver behavior of error as a factor in 94 percent of crashes , and self-driving vehicles can help reduce driver error. Higher levels of autonomy have the potential to reduce risky and dangerous driver behaviors.

In conclusion, driverless cars are actually good at this era where technology has really evolved , however , we must take great control of these vehicles since we cannot trust technology one hundred percent since there are also many problems associated with technology . Companies manufacturing them should take great care and control mechanisms for these vehicles.

Project Objectives

• Collection of self-generated data set on the customized track.
• Real time lane detection using Open CV or any other tool found useful as we progress.
• Trained the model via deep learning   frameworks such as Tensor Flow, Py torch or any other tool found useful as we progress.
• Better Town Traffic, correspondingly leading to peaceful town.
• Easy for Disabled people, older citizens, and children to travel on their own.
• Driving fatigue and getting lost would be things of the past.
• Increases safety

Project Implementation Method

Benefits of the Project

Automation can help reduce the number of crashes on our roads. Government data identifies driver behavior of error as a factor in 94 percent of crashes , and self-driving vehicles can help reduce driver error. Higher levels of autonomy have the potential to reduce risky and dangerous driver behaviors.

Technical Details of Final Deliverable

Jetson  Nano:

NVIDIA Jetson Nano enables the development of millions of new small, low-power AI systems. It opens new worlds of embedded IoT applications, including entry-level Network Video Recorders (NVRs), home robots, and intelligent gateways with full analytics capabilities.  Jetson is a low-power system and is designed for accelerating machine learning applications.

Pi Camera V2:

 The Raspberry Pi camera module can be used to capture photograph as well as take high-definition video. The camera module is 8 megapixel fixed-focus camera that supports 1080p30, 720p60 and video modes.  It can be accessed through the MMAL (Multi-Media Abstraction Layer), Video for Linux Application Programming Interface and there are numerous third-party libraries built for it, such as the Pi camera Python library. The camera module is used in home security applications but in this project we use camera for capturing images.

1. Proposed Software Detail

JETSON NANO OS:

The official operating system for the Jetson Nano and other Jetson boards                 is called Linux4Tegra, which is actually a version of Ubuntu 18.04 that’s designed to run on Nvidia’s hardware. Ubuntu (pronounced oo-BOON-too) is an open  source  Debian-based Linux distribution. Sponsored by Canonical Ltd., Ubuntu is considered a good distribution for beginners. The operating system was intended primarily for personal computers (PCs) but it can also be used on servers.

Python:

 Python was created by Guido van Rossem during 1985- 1990. It is a general-purpose, object-oriented, interactive, and high-level programming language. Its syntax allows the programmers to express concepts in less lines of code when compared with other languages like java, C or C++. It provides high-level dynamic data types and supports dynamic type checking.

Open CV:

 It (Open Source Computer Vision) is a library of programming functions   mainly aimed at real-time computer vision. This library allows these features be implemented on computers with relative ease, provide a simple computer vision infrastructure to prototype quickly sophisticated applications. It has over 2500 optimized algorithms, including both a set of classical algorithms and the state of the art algorithms in Computer Vision, which can be used for image processing, detection and face recognition, object identification, classification actions, traces, and other functions.  It is based on C++ but wrappers are available in python as well. Here it is used to detect the roads and guide the car on unknown roads.

Final Deliverable of the Project

Hardware System

Core Industry

Transportation

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Required Resources

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