1 Star 2 Fork 0

nealliu / Self_Driving_Car_Simulation_In_MATLAB

Create your Gitee Account
Explore and code with more than 6 million developers,Free private repositories !:)
Sign up
This repository doesn't specify license. Without author's permission, this code is only for learning and cannot be used for other purposes.
Clone or download
Notice: Creating folder will generate an empty file .keep, because not support in Git

Self-Driving Car Simulation In MATLAB

This repository contains a series of self-driving car simulations in MATLAB. The simulations are mainly focused on Controlls, Sensor Fusion, State Estimation and Localization in the context of Self-Driving Cars.

1. Lane Keeping Assist System Simulation for an autonomous vehicle in MATLAB/SIMULINK

This project uses the principlas of computer vision and control to simulate a lane keeping assist system for self driving cars in simulink. The computer vision toolbox in simulink is used to detect the lane lines, and a PID controller is utulized to drive the vehicle in between the lane lines.

First, the sequence of images captured by the camera are converted to the HSV color space. A threshold is applied to the S-channel in the HSV color space to isolate the lane lines. The binary image is transformed using a projective transformation to obtain a bird's eye view of the scene. Finally, the bird's eye view is processed using a 2D point cloud analyzer in a Simulink User-defined function to detect the left and right lanes.

2. PID Controller Design for Tracking

3. A Hybrid Automaton Design

The dynamics of the car is implemented and a PID controller drives the car towards the specified Goal while avoiding the obstacle in the map. The dynamics of the car and the controller are all implanted in Car.m file using object-oriented programming in MATLAB. The main function runs the car model and plots the results to generate the GIF file for this simulation.

NOTE: Run the Main.m file in each of the the folders for the simulation to start.

The code associated with each of simulations are categorized in different folders. The code is standalone and should run on any MATLAB version without requiring additional dependencies.

Comments ( 0 )

Sign in for post a comment


No release




load more
can not load any more