Simulation based vehicle movement tracking using Kalman Filter algorithm for Autonomous vehicles

In the domain of Software automotive industry, one of the most widely used algorithms for performing analysis of driving operations is the Kalman filter algorithm. In today's world of advanced machine learning, the Kalman filter remains an important tool to fuse measurements from several sensor...

Full description

Saved in:
Bibliographic Details
Published in2021 2nd International Conference on Intelligent Engineering and Management (ICIEM) pp. 205 - 210
Main Authors Rana, Kritika, Kaur, Parampreet
Format Conference Proceeding
LanguageEnglish
Published IEEE 28.04.2021
Subjects
Kalman filter
Machine learning algorithms
MATLAB
Real-time systems
Service robots
simulation
Software algorithms
Time measurement
Tracking
vehicle tracking
Online AccessGet full text
DOI10.1109/ICIEM51511.2021.9445285

Cover

More Information
Summary:In the domain of Software automotive industry, one of the most widely used algorithms for performing analysis of driving operations is the Kalman filter algorithm. In today's world of advanced machine learning, the Kalman filter remains an important tool to fuse measurements from several sensors to estimate the real time state of robotics systems such as a self-driving vehicle. Kalman filter is able to update an estimate of evolving nature of continuously changing states of the common filters to take a probabilistic estimate. The driving scenario results are updated in real time using 2-steps update and correction method. In this paper, we have described the process of Kalman filter and its variant to estimate about the detection of moving object in a given traffic scenario using advance toolboxes of MATLAB. Results have been shown for multiple changing parameters.
DOI:10.1109/ICIEM51511.2021.9445285