Journal of Shanghai Jiao Tong University (Science) ›› 2018, Vol. 23 ›› Issue (Sup. 1): 117-123.doi: 10.1007/s12204-018-2031-9

• • 上一篇    下一篇

Intelligent Vehicle Human-Simulated Steering Characteristics Access and Control Strategy

HUA Yiding (华一丁), GONG Jinfeng (龚进峰), RONG Hui (戎辉), WANG Wenyang (王文扬), GUO Peng (郭蓬), HE Jia (何佳)   

  1. (1. CATARC (Tianjin) Automotive Engineering Research Institute Co., Ltd., Tianjin 300300, China; 2. School of Mechanical Engineering, Tianjin University, Tianjin 300072, China; 3. China Automotive Technology and Research Center Co., Ltd., Tianjin 300300, China)
  • 发布日期:2018-12-26
  • 通讯作者: HUA Yiding (华一丁) E-mail:huayiding@catarc.ac.cn

Intelligent Vehicle Human-Simulated Steering Characteristics Access and Control Strategy

HUA Yiding (华一丁), GONG Jinfeng (龚进峰), RONG Hui (戎辉), WANG Wenyang (王文扬), GUO Peng (郭蓬), HE Jia (何佳)   

  1. (1. CATARC (Tianjin) Automotive Engineering Research Institute Co., Ltd., Tianjin 300300, China; 2. School of Mechanical Engineering, Tianjin University, Tianjin 300072, China; 3. China Automotive Technology and Research Center Co., Ltd., Tianjin 300300, China)
  • Published:2018-12-26
  • Contact: HUA Yiding (华一丁) E-mail:huayiding@catarc.ac.cn

摘要: As the traditional control algorithm is over-dependent on accurate vehicle model in intelligent vehicle steering control, a human-simulated intelligent control method is proposed based on experienced driver steering characteristics. Intelligent vehicle unmanned steering system dynamics model and the driver model are set up. Through experienced drivers’ trial run experiment, the analysis is mainly conducted on the double lanes condition. After the transformation of coordinates on global positioning system (GPS) derivative, the path information of local coordinates is accessed. The ideal driver steering path is obtained through fuzzy C-means clustering algorithm. The human-simulated intelligent controller is designed. Characteristic model is established according to the ideal and practical steering angle deviation and the deviation rate. Besides, the corresponding control rules and control modality set are designed. The joint simulation under CarSim joint/Simulink environment shows that the humanoid steering controller designed in this paper has better tracking performance than the model predictive control.

关键词: intelligent vehicle, experienced driver, steering characteristics, human-simulated intelligent control

Abstract: As the traditional control algorithm is over-dependent on accurate vehicle model in intelligent vehicle steering control, a human-simulated intelligent control method is proposed based on experienced driver steering characteristics. Intelligent vehicle unmanned steering system dynamics model and the driver model are set up. Through experienced drivers’ trial run experiment, the analysis is mainly conducted on the double lanes condition. After the transformation of coordinates on global positioning system (GPS) derivative, the path information of local coordinates is accessed. The ideal driver steering path is obtained through fuzzy C-means clustering algorithm. The human-simulated intelligent controller is designed. Characteristic model is established according to the ideal and practical steering angle deviation and the deviation rate. Besides, the corresponding control rules and control modality set are designed. The joint simulation under CarSim joint/Simulink environment shows that the humanoid steering controller designed in this paper has better tracking performance than the model predictive control.

Key words: human-simulated intelligent control, intelligent vehicle, experienced driver, steering characteristics

中图分类号: