Modelling the Environment of a Mobile Robot Using a Time Series Convolutional Neural Network

Suryajaya, Shannon and Schwung, Andreas and Rusyadi, Rusman (2019) Modelling the Environment of a Mobile Robot Using a Time Series Convolutional Neural Network. Bachelor thesis, Swiss German University.

[img]
Preview
Text
Shannon Suryajaya 11501008 TOC.pdf

Download (1MB) | Preview
[img] Text
Shannon Suryajaya 11501008 1.pdf
Restricted to Registered users only

Download (509kB)
[img] Text
Shannon Suryajaya 11501008 2.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
Shannon Suryajaya 11501008 3.pdf
Restricted to Registered users only

Download (221kB)
[img] Text
Shannon Suryajaya 11501008 4.pdf
Restricted to Registered users only

Download (724kB)
[img] Text
Shannon Suryajaya 11501008 5.pdf
Restricted to Registered users only

Download (397kB)
[img]
Preview
Text
Shannon Suryajaya 11501008 Ref.pdf

Download (411kB) | Preview

Abstract

This thesis present a method for 2D laser scan matching using a 1D time series Convolutional Neural Network to solve SLAM problem. Scan matching is the problem of finding the relative position from two consecutive scans. The algorithm is verified with gazebo simulation data. In addition, a Lucas-Kanade optical flow is implemented to distinguish moving and not moving object. A ROS based system is implemented to integrate deep learning with SLAM and optical flow.

Item Type: Thesis (Bachelor)
Uncontrolled Keywords: Hector SLAM ; Scan Matching ; 1D Time Series Convolutional Neural Network ; Optical Flow
Subjects: T Technology > TJ Mechanical engineering and machinery > TJ163.12 Mechatronics
T Technology > TJ Mechanical engineering and machinery > TJ210 Robots (General)
T Technology > TJ Mechanical engineering and machinery > TJ212 Control engineering systems. Automatic machinery (General)
Divisions: Faculty of Engineering and Information Technology > Department of Mechatronics Engineering
Depositing User: Adityatama Ratangga
Date Deposited: 21 May 2020 15:34
Last Modified: 21 May 2020 15:34
URI: http://repository.sgu.ac.id/id/eprint/692

Actions (login required)

View Item View Item