Scribd
Upload
9 views4 pages

Self Driving Car Project

This project focuses on the development of self-driving cars using deep learning and real-time perception systems. It covers the architecture, algorithms, and essential modules such as lane detection and object detection, implemented in the CARLA simulator. The work also addresses ethical, regulatory, and safety concerns related to autonomous vehicles.

Uploaded by

healingspiritwolf100x
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views4 pages

Self Driving Car Project

This project focuses on the development of self-driving cars using deep learning and real-time perception systems. It covers the architecture, algorithms, and essential modules such as lane detection and object detection, implemented in the CARLA simulator. The work also addresses ethical, regulatory, and safety concerns related to autonomous vehicles.

Uploaded by

healingspiritwolf100x
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Self-Driving Cars: A Deep Learning-

Based Approach to Autonomous


Vehicle Technology
Submitted as a Major Project
Bachelor of Technology in Computer Science

By:
[Your Name Here]

May 2025
Abstract
Self-driving cars, also known as autonomous vehicles, are at the forefront of the
transportation revolution. With advancements in artificial intelligence (AI), deep learning,
computer vision, and sensor technologies, autonomous vehicles are no longer a futuristic
concept but a rapidly developing reality. This project explores the architecture,
components, algorithms, and software systems behind self-driving cars, with an emphasis
on deep learning and real-time perception systems. We implement essential modules such
as lane detection, object detection using YOLOv5, and PID-based control using the CARLA
simulator environment. By integrating these subsystems, we simulate a basic autonomous
driving loop. This work also examines ethical, regulatory, and safety concerns, providing a
comprehensive overview of the current landscape and future directions for self-driving
cars.
Introduction
...

Literature Review
...

Methodology
...

Implementation
The implementation section presents the code used to build various modules of the self-
driving system.

1. Lane Detection with OpenCV

import cv2
import numpy as np

def detect_lanes(image):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5, 5), 0)
edges = cv2.Canny(blur, 50, 150)
return edges

2. Object Detection using YOLOv5

# Inference using YOLOv5 (requires ultralytics package and pretrained model)


from ultralytics import YOLO

model = YOLO("yolov5s.pt")
results = model("test_image.jpg", show=True)

3. PID Steering Control

class PIDController:
def __init__(self, Kp, Ki, Kd):
self.Kp = Kp
self.Ki = Ki
self.Kd = Kd
self.prev_error = 0
self.integral = 0

def control(self, error, dt):


self.integral += error * dt
derivative = (error - self.prev_error) / dt
output = self.Kp * error + self.Ki * self.integral + self.Kd * derivative
self.prev_error = error
return output

Results and Evaluation


...

Discussion
...

Conclusion
...

References
1. Bojarski et al., “End to End Learning for Self-Driving Cars,” Nvidia, 2016.
2. Dosovitskiy et al., “CARLA: An Open Urban Driving Simulator,” arXiv, 2017.
3. Redmon et al., “YOLOv3: An Incremental Improvement,” arXiv, 2018.

You might also like