An IMU-based turn prediction system

Yu Chang Ho, Pei Chen Lee, Hsin Yu Yeh, Min Te Sun, Andy An Kai Jeng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Many fatal car accidents are rear-ended collisions. To help alleviate this issue, a lightweight vehicle turn prediction system is developed, which identifies the forthcoming turn event at the early stage so that the neighboring vehicles can be notified in advance to prevent traffic accidents. The system uses smartphone sensors and digital maps. The smartphone sensors (a.k.a Inertial measurement unit) collect position information of the vehicle and predict the future position using particle filters. These positions are used to compute the curvature of the vehicle trace. From digital maps, the curvature of the road that the vehicle is currently traveling is also computed. By examining the difference of these two curvatures as well as the speed of the vehicle, the system determines if the vehicle is making a turn at the early stage. The experimental results show that the proposed system can correctly identify all the turns on the road. In addition, the proposed system does not require extra hardware, which allows it for inexpensive large-scale deployment.

Original languageEnglish
Title of host publicationIEEE/IFIP Network Operations and Management Symposium
Subtitle of host publicationCognitive Management in a Cyber World, NOMS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781538634165
StatePublished - 6 Jul 2018
Event2018 IEEE/IFIP Network Operations and Management Symposium, NOMS 2018 - Taipei, Taiwan
Duration: 23 Apr 201827 Apr 2018

Publication series

NameIEEE/IFIP Network Operations and Management Symposium: Cognitive Management in a Cyber World, NOMS 2018


Conference2018 IEEE/IFIP Network Operations and Management Symposium, NOMS 2018


  • Digital maps
  • IMU
  • Inertial measurement unit
  • Smartphones
  • Turn prediction


Dive into the research topics of 'An IMU-based turn prediction system'. Together they form a unique fingerprint.

Cite this