Self Driving Car

Project Title

Self Driving Car

Project Area of Specialization Artificial IntelligenceProject Summary

Summary:

We are developing a self-driving car. This will be achieved using Artificial Intelligence & Computer Vision. The project will be a scaled-down version of an autonomous Vehicle such as Tesla's autopilot system. Hence, an RC car will be used for this purpose along with a raspberry Pi & an arduino microcontroller. 

A camera module & an ultrasonic sensor will be connected to the system in order to detect objects & identify lanes.The car will be trained in a special environment i.e. we will design a custom-made track that will consist of painted road lanes, along with miniature traffic signals, static pedestrians (for testing), & other small objects found within the environment of a typical real-world road.

The raspberry pi will collect the data from the connected sensors & will process it using different algorithms. The algorithms will make predictions based on the sensor data & these predictions will then be sent to the arduino which will control the behaviour of the car i.e. stopping, steering etc.

Project Objectives

1. The project will emulate the complete behaviour of a real-world self-driving car.
2. The project will aim to understand the importance of autonomous vehicles & its projected impact in the the Pakistani ecosystem.
3. We chose this particular project to push forward the culture of autonomous vehicles in pakistan as it is currently lagging behind in this domain.

Project Implementation Method

Equipment:

1. RC Car
2. Raspberry Pi 4 4GB
3. Arduino Microcontroller
4. Motorshield
5. Camera Module
6. Ultrasound Sensor
7. Custom-made track
8. Miscellaneous

Implementation:

First off, we will connect the motors of the RC car with the motorshield & the arduino. Then this arduino will be connected to a raspberry pi. A camera module will be attached to the raspberry pi.

The custom-made track is essential to our project. We will design it in such a way that it emulates a real world road scenario. We will then capture frames of this track & this data will be used to train the machine learning algorithm. Once trained, it will be able to predict & make decisions to help move the car intelligently.

For example, suppose the car detects a stop sign on the track or maybe it encounters a steep turn, the algorithm will predict what to do next & this prediction will be sent to the arduino via the raspberry pi. The arduino will then control the stopping or steering of the car accordingly. On the flip side, if the car doesn't encounter any obstacles, it will keep on driving itself while sensing the road lanes.

Benefits of the Project

Benefits:

1. This project is designed to shape a more autonomous future. We are doing our bit to push forward the idea of autonomous vehicles in Pakistan.
2. Albeit this project is a scaled-down version of a real-world autonomous vehicle, we are confident that our implementation of this idea will help convince local investors & industry leaders to get on the self-driving bandwagon.
3. This project will serve as a starting point to conversations that involve pushing our communities towards a future in which we have lesser road accidents & more autonomy.  
4. This project will help us understand computer vision & artifical intelligence at a much deeper & practical level.
5. This project will pave our way to careers that involve exciting challenges involving autonomous vehicles.

Technical Details of Final Deliverable

Final Deliverables:

1. The final prototype will deliver small-scale car(s) capable of full self-driving with major components incorporated into the body of the car. 
2. The project will also be coupled with a custom-made track which will serve as the environment for the small-scale car.
3. The project will deliver a complete software solution capable of tracking & prediction of obstacles, turns & other facets of real-world road scenario.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Transportation Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and Infrastructure, Sustainable Cities and CommunitiesRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	55612
Raspberry Pi 4 4GB	Equipment	2	7206	14412
Arduino	Equipment	2	650	1300
RC Car(s)	Equipment	2	5000	10000
Custom-track material	Equipment	1	5000	5000
Battery pack	Equipment	2	1000	2000
Camera module	Equipment	2	5000	10000
Ultrasonic sensor	Equipment	2	500	1000
Battery Charger	Equipment	2	1500	3000
Raspberry Pi power supply	Equipment	1	1100	1100
Miscellaneous	Miscellaneous	1	3000	3000
Google Colab Subscription (3 Months)	Equipment	3	1600	4800