Adaptive kinematic particle filter classifier for autonomous robots

Idris-Animashaun, Ayoola Bashir (2022) Adaptive kinematic particle filter classifier for autonomous robots. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Autonomous robots are finding more industrial and home usage. One of the challenges these robots face is how the robot can perceive its environment and move within the environment. This becomes more necessary when the environment is new or it changes. The robot uses unique landmarks within an environment to find itself. Particles, which are belief states of where the robot could be in an environment are generated, evaluated, resampled and when they converge, used to estimate the robot’s position. Sometimes, there is no landmark and this causes the particles to diverge from the robot’s position. Machine learning classifiers are used to detect the type of wheel on a robot, and depending on the wheel type, some constraint can be applied to the particle inputs to enable the particles continue on a set trajectory when the robot does not have any landmark to guide it within the environment.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Particle filter; Robots; Bayes Filter
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TJ Mechanical engineering and machinery Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	26 Jan 2023 16:08
Last Modified:	03 Mar 2023 11:20
URI:	https://norma.ncirl.ie/id/eprint/6136

Actions (login required)

View Item