Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Centerlane Violation for vehicle in opposite direction using Fuzzy Logic and Interacting Multiple Model

퍼지 논리와 Interacting Multiple Model (IMM)을 통한 잡음환경에서의 맞은편 차량의 중앙선 침범 예측

  • Kim, Beomseong (School of Electrical and Electronics Engineering, Yonsei University) ;
  • Choi, Baehoon (School of Electrical and Electronics Engineering, Yonsei University) ;
  • An, Jhonghyen (School of Electrical and Electronics Engineering, Yonsei University) ;
  • Lee, Heejin (Electrical, Electronic and Control Engineering, Hankyong National University) ;
  • Kim, Euntai (School of Electrical and Electronics Engineering, Yonsei University)
  • 김범성 (연세대학교 전기전자공학부) ;
  • 최배훈 (연세대학교 전기전자공학부) ;
  • 안종현 (연세대학교 전기전자공학부) ;
  • 이희진 (국립한경대학교 전기전자제어공학과) ;
  • 김은태 (연세대학교 전기전자공학부)
  • Received : 2013.05.25
  • Accepted : 2013.10.14
  • Published : 2013.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

For intelligent vehicle technology, it is very important to recognize the states of around vehicles and assess the collision risk for safety driving of the vehicle. Specifically, it is very fatal the collision with the vehicle coming from opposite direction. In this paper, a centerlane violation prediction method is proposed. Only radar signal based prediction makes lots of false alarm cause of measurement noise and the false alarm can make more danger situation than the non-prediction situation. We proposed the novel prediction method using IMM algorithm and fuzzy logic to increase accuracy and get rid of false positive. Fuzzy logic adjusts the radar signal and the IMM algorithm appropriately. It is verified by the computer simulation that shows stable prediction result and fewer number of false alarm.

지능형 차량의 안전 주행을 위해서 주변 차량의 상태를 파악하고, 충돌 위험도를 판단하는 일은 매우 중요하다. 특히 중앙선을 침범하여 주행하는 차량과의 충돌은 치명적일 수 있다. 맞은편에서 다가오는 차량의 중앙선 침범을 지능형 차량의 주요 센서 가운데 하나인 레이더 센서만을 이용하여 예측하면 센서의 특성상 발생하는 노이즈로 인해 오인식의 가능성이 높다. 오인식은 중앙선 침범보다 더 위험한 결과를 초래하기도 한다. 본 논문에서는 레이더 신호에 IMM을 사용한 추적 알고리즘과 퍼지 논리를 적용하여 중앙선 침범 예측의 정확도를 높이고 오인식을 감소시킬 수 있는 알고리즘을 제안한다. 퍼지 로직은 레이더 신호와 IMM알고리즘의 결합을 적절히 조절하는 기능을 한다. 제안된 알고리즘은 컴퓨터 모의 실험을 통해 오인식의 감소가 효과적으로 이루어짐이 검증되었다.

Keywords

References

  1. Korean National Police Agency, The 2013 Traffic accident statistics, pp 46,2013
  2. M. Distner, M. Bengtsson, T. Broberg, and L. Jakobsson, "City safety-A system addressing rear-end collisions at low speeds," in Proc. 21st Enhanc. Safety Veh. Conf., Stuttgart, Germany, 2009, paper 09-0371.
  3. M. Brannstrom, F. Sandblom, and L. Hammarstrand "A Probabilistic Framework for Decision-Making in Collision Avoidance Systems," IEEE Transactions on Intelligent Transportation Systems, vol. 14, no.2, Jun.2013.
  4. J. Jansson, Collision avoidance theory with application to automo-tive collision mitigation, Ph.D. dissertation, Linkping Univ., Linkping,Sweden, Jun. 2005.
  5. S. Park, J. P. Hwang, E. Kim and H. J. Kang, "Vehicle tracking using a microwave radar for situation awareness," Control Engineering Practice, vol.18, issue.4, pp.383-395, April, 2010. https://doi.org/10.1016/j.conengprac.2009.12.006
  6. S. Park, J. P. Hwang, K. J. Ryu, E. Kim, "Vehicle-Tracking with Distorted Measurement via Fuzzy Interacting Multiple Model,", Journal of Korean Institute of Intelligent Systems, vol. 18, no. 6, pp.863-870, 2008 https://doi.org/10.5391/JKIIS.2008.18.6.863
  7. H. Kim, "Adaptive Fuzzy IMM Algorithm for Position Tracking of Maneuvering Target", Journal of Fuzzy Logic and Intelligent Systems, vol. 17, no. 7, pp.855-861, 2007. https://doi.org/10.5391/JKIIS.2007.17.7.855
  8. B. Choi, B. Kim, J. An, C. Yoon, E. Kim, "Prediction of Centerlane Violation for vehicle in opposite direction using Interacting Multiple Model," in proc. of the Korean Institute of Intelligent Systems Conference, Vol. 23, No. 1, pp.207-208, Dae-gu, Apr 2013.

Cited by

  1. MCMC Particle Filter based Multiple Preceeding Vehicle Tracking System for Intelligent Vehicle vol.25, pp.2, 2015, https://doi.org/10.5391/JKIIS.2015.25.2.186