An Algorithm for Speed Optimization in Autonomous Vehicles

Session

Computer Science and Communication Engineering

Description

This paper presents an algorithm for speed optimization in autonomous vehicles. The simulation of tracking multiple objects is performed by “Computer Vision System Toolbox” in MATLAB. The test car is equipped by Vision sensor, Radar sensor and inertial measurement unit (IMU). The most dangerous object is defined as the vehicle / static obstacle that is in the lane and is closest in front of the car. Once the most dangerous object is found, the relative speed between this object and the car is calculated. The relative distance to the most dangerous object and the relative speed are used to calculate the necessary deceleration. Also a terrain roughness is evaluated. Based on this evaluation, the optimal speed is calculated. In this way the car can slow before hitting an obstacle or a rough terrain on the road. The proposed algorithm should be tested on a sample of different scenarios and could be implemented successfully as a software component in real format.

Keywords:

Autonomous vehicles, Speed optimization, MATLAB

Session Chair

Bertan Karahoda

Session Co-Chair

Krenare Pireva

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-437-69-1

Location

Pristina, Kosovo

Start Date

27-10-2018 10:45 AM

End Date

27-10-2018 12:15 PM

DOI

10.33107/ubt-ic.2018.81

This document is currently not available here.

Share

COinS
 
Oct 27th, 10:45 AM Oct 27th, 12:15 PM

An Algorithm for Speed Optimization in Autonomous Vehicles

Pristina, Kosovo

This paper presents an algorithm for speed optimization in autonomous vehicles. The simulation of tracking multiple objects is performed by “Computer Vision System Toolbox” in MATLAB. The test car is equipped by Vision sensor, Radar sensor and inertial measurement unit (IMU). The most dangerous object is defined as the vehicle / static obstacle that is in the lane and is closest in front of the car. Once the most dangerous object is found, the relative speed between this object and the car is calculated. The relative distance to the most dangerous object and the relative speed are used to calculate the necessary deceleration. Also a terrain roughness is evaluated. Based on this evaluation, the optimal speed is calculated. In this way the car can slow before hitting an obstacle or a rough terrain on the road. The proposed algorithm should be tested on a sample of different scenarios and could be implemented successfully as a software component in real format.