A Predictive Control Algorithm Based on Driving Behavior Data Model

被引:1
作者
Han, XiangMin [1 ]
Bao, Hong [1 ]
Xuan, ZuXing [1 ]
Pan, Feng [2 ]
机构
[1] Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China
[2] Beijing Union Univ, Coll Robot, Beijing, Peoples R China
来源
2017 13TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS) | 2017年
关键词
driving behavior; intelligent driving; data model; predictive control; PID CONTROL; TRACKING; DESIGN;
D O I
10.1109/CIS.2017.00091
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
At present, most of the researches in intelligent driving field start up from algorithm, while ignoring the driving behavior of the human driver in solving the automatic control problem of the intelligent vehicle. This kind of algorithm gives priority to the fast convergence of the algorithm and does not fully consider the driving habit of human beings, so it is very difficult to achieve humanoid driving in real sense. This paper presents a speed control algorithm of intelligent vehicle based on human driver's driving behavior. With the collection of the data analysis and modeling of human driver's driving behavior, the control model satisfying the human driving behavior is established, thereby simulating the human's driving habit, so as to finally realize the adaptive tracking driven by driving data and to improve the longitudinal comfort of the passengers of automatic driving vehicle.
引用
收藏
页码:390 / 394
页数:5
相关论文
共 15 条
  • [1] PID control system analysis, design, and technology
    Ang, KH
    Chong, G
    Li, Y
    [J]. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2005, 13 (04) : 559 - 576
  • [2] Development and testing of a fully Adaptive Cruise Control system
    Bifulco, Gennaro Nicola
    Pariota, Luigi
    Simonelli, Fulvio
    Di Pace, Roberta
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2013, 29 : 156 - 170
  • [3] Model Predictive Control oriented experiment design for system identification: A graph theoretical approach
    Ebadat, Afrooz
    Valenzuela, Patricio E.
    Rojas, Cristian R.
    Wahlberg, Bo
    [J]. JOURNAL OF PROCESS CONTROL, 2017, 52 : 75 - 84
  • [4] The Lateral Tracking Control for the Intelligent Vehicle Based on Adaptive PID Neural Network
    Han, Gaining
    Fu, Weiping
    Wang, Wen
    Wu, Zongsheng
    [J]. SENSORS, 2017, 17 (06):
  • [5] An empirical evaluation of supervised learning approaches in assigning diagnosis codes to electronic medical records
    Kavuluru, Ramakanth
    Rios, Anthony
    Lu, Yuan
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2015, 65 (02) : 155 - 166
  • [6] Lafaye J, 2014, IEEE-RAS INT C HUMAN, P336, DOI 10.1109/HUMANOIDS.2014.7041381
  • [7] Ma SH, 2009, CCDC 2009: 21ST CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-6, PROCEEDINGS, P462, DOI 10.1109/CCDC.2009.5195008
  • [8] Mohri M., 2012, Foundations of machine learning
  • [9] Human driving data-based design of a vehicle adaptive cruise control algorithm
    Moon, Seungwuk
    Yi, Kyongsu
    [J]. VEHICLE SYSTEM DYNAMICS, 2008, 46 (08) : 661 - 690
  • [10] Dynamic sliding PID control for tracking of robot manipulators: theory and experiments
    Parra-Vega, V
    Arimoto, S
    Liu, YH
    Hirzinger, G
    Akella, P
    [J]. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 2003, 19 (06): : 967 - 976