Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU
Localization in challenging, natural environments, such as forests or woodlands, is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this letter, we explore laser-based localization in both ur...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2019
|
| _version_ | 1826301204402012160 |
|---|---|
| author | Fallon, M Tinchev, G Penate-Sanchez, A |
| author_facet | Fallon, M Tinchev, G Penate-Sanchez, A |
| author_sort | Fallon, M |
| collection | OXFORD |
| description | Localization in challenging, natural environments, such as forests or woodlands, is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this letter, we explore laser-based localization in both urban and natural environments, which is suitable for online applications. We propose a deep learning approach capable of learning meaningful descriptors directly from three-dimensional point clouds by comparing triplets (anchor, positive, and negative examples). The approach learns a feature space representation for a set of segmented point clouds that are matched between a current and previous observations. Our learning method is tailored toward loop closure detection resulting in a small model that can be deployed using only a CPU. The proposed learning method would allow the full pipeline to run on robots with limited computational payloads, such as drones, quadrupeds, or Unmanned Ground Vehicles (UGVs). |
| first_indexed | 2024-03-07T05:28:51Z |
| format | Conference item |
| id | oxford-uuid:e181235e-f4e4-408d-8235-6899d922bf59 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T05:28:51Z |
| publishDate | 2019 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:e181235e-f4e4-408d-8235-6899d922bf592022-03-27T09:54:55ZLearning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPUConference itemhttp://purl.org/coar/resource_type/c_5794uuid:e181235e-f4e4-408d-8235-6899d922bf59Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2019Fallon, MTinchev, GPenate-Sanchez, ALocalization in challenging, natural environments, such as forests or woodlands, is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this letter, we explore laser-based localization in both urban and natural environments, which is suitable for online applications. We propose a deep learning approach capable of learning meaningful descriptors directly from three-dimensional point clouds by comparing triplets (anchor, positive, and negative examples). The approach learns a feature space representation for a set of segmented point clouds that are matched between a current and previous observations. Our learning method is tailored toward loop closure detection resulting in a small model that can be deployed using only a CPU. The proposed learning method would allow the full pipeline to run on robots with limited computational payloads, such as drones, quadrupeds, or Unmanned Ground Vehicles (UGVs). |
| spellingShingle | Fallon, M Tinchev, G Penate-Sanchez, A Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title | Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title_full | Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title_fullStr | Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title_full_unstemmed | Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title_short | Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU |
| title_sort | learning to see the wood for the trees deep laser localization in urban and natural environments on a cpu |
| work_keys_str_mv | AT fallonm learningtoseethewoodforthetreesdeeplaserlocalizationinurbanandnaturalenvironmentsonacpu AT tinchevg learningtoseethewoodforthetreesdeeplaserlocalizationinurbanandnaturalenvironmentsonacpu AT penatesancheza learningtoseethewoodforthetreesdeeplaserlocalizationinurbanandnaturalenvironmentsonacpu |