DOI QR코드

DOI QR Code

The road roughness based Braking Pressure Calculation System(BPCS) for an Autonomous Vehicle Stability

자율차량 안정성을 위한 도로 거칠기 기반 제동압력 계산 시스템

  • Son, Su-Rak (Department of Software Engineering, Catholic kwandong University) ;
  • Lee, Byung-Kwan (Department of Software Engineering, Catholic kwandong University) ;
  • Sim, Son-Kweon (Department of Software Engineering, Catholic kwandong University)
  • Received : 2020.07.30
  • Accepted : 2020.08.27
  • Published : 2020.10.30

Abstract

This paper proposes the road roughness based Braking Pressure Calculation System(BPCS) for an Autonomous Vehicle Stability. The system consists of an image normalization module that processes the front image of a vehicle to fit the input of the random forest, a Random Forest based Road Roughness Classification Module that distinguish the roughness of the road on which the vehicle is travelling by using the weather information and the front image of a vehicle as an input, and a brake pressure control module that modifies a friction coefficient applied to the vehicle according to the road roughness and determines the braking strength to maintain optimal driving according to a vehicle ahead. To verify the efficiency of the BPCS experiment was conducted with a random forest model. The result of the experiment shows that the accuracy of the random forest model was about 2% higher than that of the SVM, and that 7 features should be bagged to make an accurate random forest model. Therefore, the BPCS satisfies both real-time and accuracy in situations where the vehicle needs to brake.

본 논문은 자율차량 안정성을 위한 도로 거칠기 기반 제동압력 계산 시스템을 제안한다. 제동압력 계산 시스템는 차량의 전방 이미지를 랜덤 포레스트의 입력에 맞게 가공하는 이미지 정규화 모듈, 기상정보와 이미지 정규화 모듈에서 정규화된 차량 전방 이미지를 입력으로 사용하여 차량이 주행 중인 도로의 거칠기를 구별하는 랜덤 포레스트 기반 도로 거칠기 분류 모듈과 도로 거칠기에 따라 차량에 적용되는 마찰 계수를 수정하고, 전방 차량에 따라 최적 주행을 유지하는 브레이킹 강도를 결정하는 차량 브레이크 압력 제어 모듈로 구성된다. 본 논문은 제동압력 계산 시스템의 효율성을 검증하기 위해 제동압력 계산 시스템에 사용되는 랜덤 포레스트 모델을 중심으로 실험이 진행되었다. 실험 결과, 랜덤 포레스트 모델의 정확도는 SVM보다 약 2% 높았고, 정확한 랜덤 포레스트 모델 구성을 위해 7개의 특징이 중복 허용 임의 추출되어야 한다는 결론이 도출되었다. 따라서 제동압력 계산 시스템은 차량이 제동해야 하는 상황에서 정확성 모두를 만족할 수 있다.

Keywords

References

  1. "자율주행 차 사고, 뒤따르던 일반 차와 충돌 많았다." 김영주, https://news.joins.com/ article/23718449
  2. Nguyen Manh Cuong, Jaesung Lee, "Automatic Detection of ROI for Vehicle Positioning", Proceedings of Symposium of the Korean In stitute of communications and Information Sciences, pp. 164-165, June, 2016
  3. Lee, Seung-Hyun, Kim, Tae-Dong, Yi, Kang, Jung, Kyeong-Hoon, "Hypothesis Generation for Vehicle Detection by Combining Shadow and Edge", Conference of the Korean Society Of Broad Engineers, pp. 316-319, June, 2016
  4. Hyun-cheol Yoon, Ju Yong Choi, "Transportation vehicle active safety warning systems developed algorithms". Fall Conference and Exhibition of the Korean Society Of Automotive Engineers, pp. 734-735, November, 2014
  5. Jongcherl Park, Hojun Lee, Kyongsu Yi, "Cut-in Intension Inference based on Human Driving Data Analysis using Random Forest Method", The Korean Society of Mechanical Engineers 2018 Conference, pp. 1703-1708, December, 2018
  6. Duyoung Heo, Sang Jun Kim, Choong Sub Kwak, Jae-Yeal Nam, Byoung Chul Ko,"Vehicle Headlight and Taillight Recognition in Nighttime using Low-Exposure Camera and Wavelet-based Random Forest", JOURNAL OF BROADCAST ENGINEERING Vol.22, No.3, ,pp. 282-294, May, 2017 https://doi.org/10.5909/JBE.2017.22.3.282
  7. Chanyong Choi, Hunki Kim, Young Cheul Kim, Sang-su Kim, "Prediction of Track Quality Index (TQI) Using Vehicle Acceleration Data based on Machine Learning", Journal of Korean Geosynthetics Society, Vol.19, No.1, pp. 45-53, March, 2020
  8. Kwangseub Kim, Wang Maosen, Naktak Jung, Seongmo Yang, Sehoon Yoo, Daeseong Gi, Myungwon Suh, "A Study on Drowsy Driving Behavior Detection Based on Driving Information", Spring Conference of the Korean Society Of Automotive Engineers, pp.702-705, May, 2015
  9. Lynn B. Fricke, Traffic Accident Reconstruction, pp. 62-114, Northwest- ern University Traffic Institute, 1990