Hybrid Metric‐Topological Localization for Robots in Pipe Networks.
Saved in:
| Title: | Hybrid Metric‐Topological Localization for Robots in Pipe Networks. |
|---|---|
| Authors: | Worley, Rob1 (AUTHOR) r.worley@sheffield.ac.uk, Anderson, Sean R.1 (AUTHOR) |
| Source: | Journal of Field Robotics. May2025, Vol. 42 Issue 3, p806-826. 21p. |
| Subjects: | Viterbi decoding, Mobile robots, Buried pipes (Engineering), Error rates, Acoustic measurements |
| Abstract: | Accurate, reliable, and efficient robot localization is essential for long‐term autonomous robotic inspection of buried pipe networks. It is necessary for path planning and for locating detected faults in the network. This paper proposes a novel localization algorithm designed for limited, high‐uncertainty sensing in network environments. The localization method is developed from the Viterbi algorithm, which efficiently searches for the most likely robot trajectory amongst multiple hypotheses. It is augmented to facilitate hybrid metric‐topological localization, and it is improved to efficiently spend computation on useful points in time. Results using field robot data from a sewer network demonstrate the algorithm's practical applicability, as the algorithm is shown to robustly produce a coherent trajectory estimate with low error in estimated location, compared with a particle filter alternative that incorrectly jumps between parts of the network. Results using simulated data demonstrate the algorithm's robust performance at large spatial and temporal scales. In 79% of trajectories, the algorithm produces less error than a particle filter, while requiring a median of 0.18 times the computation time, demonstrating a substantial improvement in computational efficiency with comparable or superior accuracy. The flexibility of the algorithm is also demonstrated in simulation by incorporating measurements representing acoustic echo sensing and pipe gradient sensing, which is shown to reduce the error rate from 28% to 7% or below, in the case of large uncertainty in all other inputs. These results demonstrate that the proposed localization method improves the computational efficiency, accuracy, and robustness of localization compared to a particle filter specialized to the pipe environment, even in the presence of limited and high‐uncertainty sensing. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Field Robotics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 184466544 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Hybrid Metric‐Topological Localization for Robots in Pipe Networks. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Worley%2C+Rob%22">Worley, Rob</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> r.worley@sheffield.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Anderson%2C+Sean+R%2E%22">Anderson, Sean R.</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Field+Robotics%22">Journal of Field Robotics</searchLink>. May2025, Vol. 42 Issue 3, p806-826. 21p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Viterbi+decoding%22">Viterbi decoding</searchLink><br /><searchLink fieldCode="DE" term="%22Mobile+robots%22">Mobile robots</searchLink><br /><searchLink fieldCode="DE" term="%22Buried+pipes+%28Engineering%29%22">Buried pipes (Engineering)</searchLink><br /><searchLink fieldCode="DE" term="%22Error+rates%22">Error rates</searchLink><br /><searchLink fieldCode="DE" term="%22Acoustic+measurements%22">Acoustic measurements</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Accurate, reliable, and efficient robot localization is essential for long‐term autonomous robotic inspection of buried pipe networks. It is necessary for path planning and for locating detected faults in the network. This paper proposes a novel localization algorithm designed for limited, high‐uncertainty sensing in network environments. The localization method is developed from the Viterbi algorithm, which efficiently searches for the most likely robot trajectory amongst multiple hypotheses. It is augmented to facilitate hybrid metric‐topological localization, and it is improved to efficiently spend computation on useful points in time. Results using field robot data from a sewer network demonstrate the algorithm's practical applicability, as the algorithm is shown to robustly produce a coherent trajectory estimate with low error in estimated location, compared with a particle filter alternative that incorrectly jumps between parts of the network. Results using simulated data demonstrate the algorithm's robust performance at large spatial and temporal scales. In 79% of trajectories, the algorithm produces less error than a particle filter, while requiring a median of 0.18 times the computation time, demonstrating a substantial improvement in computational efficiency with comparable or superior accuracy. The flexibility of the algorithm is also demonstrated in simulation by incorporating measurements representing acoustic echo sensing and pipe gradient sensing, which is shown to reduce the error rate from 28% to 7% or below, in the case of large uncertainty in all other inputs. These results demonstrate that the proposed localization method improves the computational efficiency, accuracy, and robustness of localization compared to a particle filter specialized to the pipe environment, even in the presence of limited and high‐uncertainty sensing. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Field Robotics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=184466544 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1002/rob.22495 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 806 Subjects: – SubjectFull: Viterbi decoding Type: general – SubjectFull: Mobile robots Type: general – SubjectFull: Buried pipes (Engineering) Type: general – SubjectFull: Error rates Type: general – SubjectFull: Acoustic measurements Type: general Titles: – TitleFull: Hybrid Metric‐Topological Localization for Robots in Pipe Networks. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Worley, Rob – PersonEntity: Name: NameFull: Anderson, Sean R. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 15564959 Numbering: – Type: volume Value: 42 – Type: issue Value: 3 Titles: – TitleFull: Journal of Field Robotics Type: main |
| ResultId | 1 |
