A hierarchical framework for collaborative probabilistic semantic mapping

Performing collaborative semantic mapping is a critical challenge for cooperative robots to maintain a comprehensive contextual understanding of the surroundings. Most of the existing work either focus on single robot semantic mapping or collaborative geometry mapping. In this paper, a novel hierarc...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue, Yufeng, Zhao, Chunyang, Li, Ruilin, Yang, Chule, Zhang, Jun, Wen, Mingxing, Wang, Yuanzhe, Wang, Danwei
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/147250
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-147250
record_format dspace
spelling sg-ntu-dr.10356-1472502021-03-29T08:48:46Z A hierarchical framework for collaborative probabilistic semantic mapping Yue, Yufeng Zhao, Chunyang Li, Ruilin Yang, Chule Zhang, Jun Wen, Mingxing Wang, Yuanzhe Wang, Danwei School of Electrical and Electronic Engineering 2020 IEEE International Conference on Robotics and Automation (ICRA) Engineering Semantics Collaboration Performing collaborative semantic mapping is a critical challenge for cooperative robots to maintain a comprehensive contextual understanding of the surroundings. Most of the existing work either focus on single robot semantic mapping or collaborative geometry mapping. In this paper, a novel hierarchical collaborative probabilistic semantic mapping framework is proposed, where the problem is formulated in a distributed setting. The key novelty of this work is the mathematical modeling of the overall collaborative semantic mapping problem and the derivation of its probability decomposition. In the single robot level, the semantic point cloud is obtained based on heterogeneous sensor fusion model and is used to generate local semantic maps. Since the voxel correspondence is unknown in collaborative robots level, an Expectation-Maximization approach is proposed to estimate the hidden data association, where Bayesian rule is applied to perform semantic and occupancy probability update. The experimental results show the high quality global semantic map, demonstrating the accuracy and utility of 3D semantic map fusion algorithm in real missions. 2021-03-29T08:46:07Z 2021-03-29T08:46:07Z 2020 Conference Paper Yue, Y., Zhao, C., Li, R., Yang, C., Zhang, J., Wen, M., Wang, Y. & Wang, D. (2020). A hierarchical framework for collaborative probabilistic semantic mapping. 2020 IEEE International Conference on Robotics and Automation (ICRA), 9659-9665. https://dx.doi.org/10.1109/ICRA40945.2020.9197261 9781728173955 https://hdl.handle.net/10356/147250 10.1109/ICRA40945.2020.9197261 2-s2.0-85092703169 9659 9665 en © 2020 Institute of Electrical and Electronics Engineers (IEEE). All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Semantics
Collaboration
spellingShingle Engineering
Semantics
Collaboration
Yue, Yufeng
Zhao, Chunyang
Li, Ruilin
Yang, Chule
Zhang, Jun
Wen, Mingxing
Wang, Yuanzhe
Wang, Danwei
A hierarchical framework for collaborative probabilistic semantic mapping
description Performing collaborative semantic mapping is a critical challenge for cooperative robots to maintain a comprehensive contextual understanding of the surroundings. Most of the existing work either focus on single robot semantic mapping or collaborative geometry mapping. In this paper, a novel hierarchical collaborative probabilistic semantic mapping framework is proposed, where the problem is formulated in a distributed setting. The key novelty of this work is the mathematical modeling of the overall collaborative semantic mapping problem and the derivation of its probability decomposition. In the single robot level, the semantic point cloud is obtained based on heterogeneous sensor fusion model and is used to generate local semantic maps. Since the voxel correspondence is unknown in collaborative robots level, an Expectation-Maximization approach is proposed to estimate the hidden data association, where Bayesian rule is applied to perform semantic and occupancy probability update. The experimental results show the high quality global semantic map, demonstrating the accuracy and utility of 3D semantic map fusion algorithm in real missions.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Yue, Yufeng
Zhao, Chunyang
Li, Ruilin
Yang, Chule
Zhang, Jun
Wen, Mingxing
Wang, Yuanzhe
Wang, Danwei
format Conference or Workshop Item
author Yue, Yufeng
Zhao, Chunyang
Li, Ruilin
Yang, Chule
Zhang, Jun
Wen, Mingxing
Wang, Yuanzhe
Wang, Danwei
author_sort Yue, Yufeng
title A hierarchical framework for collaborative probabilistic semantic mapping
title_short A hierarchical framework for collaborative probabilistic semantic mapping
title_full A hierarchical framework for collaborative probabilistic semantic mapping
title_fullStr A hierarchical framework for collaborative probabilistic semantic mapping
title_full_unstemmed A hierarchical framework for collaborative probabilistic semantic mapping
title_sort hierarchical framework for collaborative probabilistic semantic mapping
publishDate 2021
url https://hdl.handle.net/10356/147250
_version_ 1695706206949081088