Point cloud based place recognition and localization for autonomous robots using deep learning
Localization is of paramount importance for robots such as self-driving cars and drones to achieve full autonomy, especially when GPS signals are unavailable. Most of the researchers focus on putting forward 2D-images-based place recognition and localization algorithms, few researchers pay atten...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/154277 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-154277 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1542772023-07-04T15:22:27Z Point cloud based place recognition and localization for autonomous robots using deep learning Fang, Shu Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering::Electrical and electronic engineering Localization is of paramount importance for robots such as self-driving cars and drones to achieve full autonomy, especially when GPS signals are unavailable. Most of the researchers focus on putting forward 2D-images-based place recognition and localization algorithms, few researchers pay attention to letting robots use point cloud to perform localization work, due to the difficulty of extracting point cloud's local features, which can be transformed into global descriptors. However, point cloud do outperform images in many aspects: point cloud are invariant to drastic lighting changes, thus making it more robust to perform localization tasks on queries that are taken from different times of the day or different seasons of the year. Also, more accurate localization information can be obtained from point cloud compared to images due to the availability of precise depth information in point cloud. To learn a robust point-cloud-based representation. We propose a novel attentional encoding strategy named Pointnet-ShadowVLAD. In this work, our contribution lies in: (1) Introducing non-informative clusters to help the network ignore misleading information in the point cloud. (2) Propose a novel initialization approach to set the location of informative clusters and non-informative clusters, thus the attention of the network can be optimized from both topological priors and information-based learning. Master of Science (Computer Control and Automation) 2021-12-20T04:34:12Z 2021-12-20T04:34:12Z 2021 Thesis-Master by Coursework Fang, S. (2021). Point cloud based place recognition and localization for autonomous robots using deep learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154277 https://hdl.handle.net/10356/154277 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering |
spellingShingle |
Engineering::Electrical and electronic engineering Fang, Shu Point cloud based place recognition and localization for autonomous robots using deep learning |
description |
Localization is of paramount importance for robots such as self-driving cars and drones to achieve full autonomy, especially when GPS signals are unavailable.
Most of the researchers focus on putting forward 2D-images-based place recognition and localization algorithms, few researchers pay attention to letting robots use point cloud to perform localization work, due to the difficulty of extracting point cloud's local features, which can be transformed into global descriptors. However, point cloud do outperform images in many aspects: point cloud are invariant to drastic lighting changes, thus making it more robust to perform localization tasks on queries that are taken from different times of the day or different seasons of the year. Also, more accurate localization information can be obtained from point cloud compared to images due to the availability of precise depth information in point cloud.
To learn a robust point-cloud-based representation. We propose a novel attentional encoding strategy named Pointnet-ShadowVLAD. In this work, our contribution lies in: (1) Introducing non-informative clusters to help the network ignore misleading information in the point cloud. (2) Propose a novel initialization approach to set the location of informative clusters and non-informative clusters, thus the attention of the network can be optimized from both topological priors and information-based learning. |
author2 |
Wang Dan Wei |
author_facet |
Wang Dan Wei Fang, Shu |
format |
Thesis-Master by Coursework |
author |
Fang, Shu |
author_sort |
Fang, Shu |
title |
Point cloud based place recognition and localization for autonomous robots using deep learning |
title_short |
Point cloud based place recognition and localization for autonomous robots using deep learning |
title_full |
Point cloud based place recognition and localization for autonomous robots using deep learning |
title_fullStr |
Point cloud based place recognition and localization for autonomous robots using deep learning |
title_full_unstemmed |
Point cloud based place recognition and localization for autonomous robots using deep learning |
title_sort |
point cloud based place recognition and localization for autonomous robots using deep learning |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/154277 |
_version_ |
1772828783244476416 |