Indoor trajectory identification: Snapping with uncertainty

Ravi Shroff, Yilong Zha, Richard Wang, Manuela Veloso, Srinivasan Seshan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider the problem of indoor human trajectory identification using odomctry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments decreases monotonically. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.

Original languageEnglish (US)
Title of host publicationArtificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report
PublisherAI Access Foundation
Pages28-34
Number of pages7
VolumeWS-15-04
ISBN (Electronic)9781577357155
StatePublished - 2015
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States
Duration: Jan 25 2015Jan 30 2015

Other

Other29th AAAI Conference on Artificial Intelligence, AAAI 2015
CountryUnited States
CityAustin
Period1/25/151/30/15

Fingerprint

Trajectories
Smartphones
Agglomeration
Uncertainty
Sensors

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Shroff, R., Zha, Y., Wang, R., Veloso, M., & Seshan, S. (2015). Indoor trajectory identification: Snapping with uncertainty. In Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report (Vol. WS-15-04, pp. 28-34). AI Access Foundation.

Indoor trajectory identification : Snapping with uncertainty. / Shroff, Ravi; Zha, Yilong; Wang, Richard; Veloso, Manuela; Seshan, Srinivasan.

Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. Vol. WS-15-04 AI Access Foundation, 2015. p. 28-34.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shroff, R, Zha, Y, Wang, R, Veloso, M & Seshan, S 2015, Indoor trajectory identification: Snapping with uncertainty. in Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. vol. WS-15-04, AI Access Foundation, pp. 28-34, 29th AAAI Conference on Artificial Intelligence, AAAI 2015, Austin, United States, 1/25/15.
Shroff R, Zha Y, Wang R, Veloso M, Seshan S. Indoor trajectory identification: Snapping with uncertainty. In Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. Vol. WS-15-04. AI Access Foundation. 2015. p. 28-34
Shroff, Ravi ; Zha, Yilong ; Wang, Richard ; Veloso, Manuela ; Seshan, Srinivasan. / Indoor trajectory identification : Snapping with uncertainty. Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. Vol. WS-15-04 AI Access Foundation, 2015. pp. 28-34
@inproceedings{73c33b6abd9d488e96bcb02faffb8cb6,
title = "Indoor trajectory identification: Snapping with uncertainty",
abstract = "We consider the problem of indoor human trajectory identification using odomctry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments decreases monotonically. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.",
author = "Ravi Shroff and Yilong Zha and Richard Wang and Manuela Veloso and Srinivasan Seshan",
year = "2015",
language = "English (US)",
volume = "WS-15-04",
pages = "28--34",
booktitle = "Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report",
publisher = "AI Access Foundation",

}

TY - GEN

T1 - Indoor trajectory identification

T2 - Snapping with uncertainty

AU - Shroff, Ravi

AU - Zha, Yilong

AU - Wang, Richard

AU - Veloso, Manuela

AU - Seshan, Srinivasan

PY - 2015

Y1 - 2015

N2 - We consider the problem of indoor human trajectory identification using odomctry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments decreases monotonically. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.

AB - We consider the problem of indoor human trajectory identification using odomctry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments decreases monotonically. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.

UR - http://www.scopus.com/inward/record.url?scp=84964577610&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964577610&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84964577610

VL - WS-15-04

SP - 28

EP - 34

BT - Artificial Intelligence for Cities - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report

PB - AI Access Foundation

ER -