Evaluation Model of Harmony with Traffic Based on Neural Network
CSTR:
Author:
Affiliation:

School of Automotive Studies, Tongji University, Shanghai 201804, China

Clc Number:

U467.1

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference [22]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    In order to study the subjective and objective mapping evaluation model of harmony with traffic for autonomous vehicles, this paper takes the highway on-ramp as a research scenario. First, based on the interaction sample data of natural driving data, a mapping evaluation model is constructed with objective index data and subjective evaluation results as model inputs and outputs, and objective indexes include average driving speed, side velocity, TTC, relative side velocity, deceleration degree of critical traffic participant and so on. Then, the influence of data preprocessing method and neural network type on the evaluation effect is analyzed using the 2×2 cross-comparison test. The results show that the precision of the BP neural network model and the Dropout neural network model based on Min-Max scaling is 95.71% and 80.00% respectively, and the precision of the BP neural network model and the Dropout neural network model based on staircase-function normalization is 94.60% and 73.25% respectively. It can be seen that the evaluation effect of the model is good, and the objective index set can express the evaluation of experts on the harmony with traffic. In terms of modeling method, the performance of the mapping evaluation model based on BP neural network is better than that of the Dropout neural network model, which can get more accurate evaluation results. In terms of data preprocessing method, the Min-Max scaling method can eliminate the magnitude difference between the data and keep the difference of objective index data between different samples, which can improve the evaluation accuracy of the mapping evaluation model. Therefore, when the sample size is small, the evaluation effect of the mapping evaluation model based on Min-Max scaling and the BP neural network is better.

    Table 4
    Table 3
    Table 2
    Fig.1 Schematic diagram of vehicle driving
    Fig.2 Topology of BP neural network
    Fig.3 Topology of Dropout neural network
    Fig.4 Scenario of ramp
    Table 1
    Reference
    [1] 陈君毅,李如冰,邢星宇,等.自动驾驶车辆智能性评价研究综述[J].同济大学学报(自然科学版),2019,47(12):1785. DOI: 10.11908/j.issn.0253-374x.2019.12.014.
    [2] WEI Junqing, DOLAN John M, LITKOUHI Bakhtiar. Autonomous vehicle social behavior for highway entrance ramp management[C]// Intelligent Vehicles Symposium. Gold Coast:IEEE, 2013:201-207.
    [3] HAOLAN M, XINGYU X, JUNYI C, et al. Comprehensive evaluation framework of autonomous vehicles' intelligence (CEFAVI)[C]// China-SAE Congress & Exhibition. Shanghai:SAECCE, 2019: 64-70.
    [4] 王越超,刘金国. 无人系统的自主性评价方法[J]. 科学通报,2012, 57(15):1290.
    [5] ZHANG X, ZHAO Y A, GAO L, et al. Evaluation framework and method of the intelligent behaviors of unmanned ground vehicles based on AHP scheme[C]//Applied Mechanics and Materials. [s.l.]:Trans Tech Publications, 2015,: 476-480.
    [6] 蒙昊蓝, 陈君毅, 邢星宇, 等. 自主泊车系统量化评价体系研究[J].同济大学学报(自然科学版),2018,46(S1):116.
    [7] GAO X, DONG G, GAO L. Fuzzy synthetic evaluation of driving abilities for intelligent vehicles[C]//2011 IEEE 2nd International Conference on Software Engineering and Service Science. Beijing:IEEE, 2011: 449-452.
    [8] BUDHANI N, JHA C K, BUDHANI S K. Prediction of stock market using artificial neural network[C]// International Conference on Soft Computing Techniques for Engineering & Technology. [s.l.]:IEEE, 2016: 320-328.
    [9] DU F, ZHAO Y, GAO L, et al. Evaluation of the autonomous parking system based on BP neural network[C]//2017 9th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC). Hangzhou:IEEE, 2017: 324-327.
    [10] 孙慧慧. 基于GA-BP神经网络的车内声品质评价研究[D]. 长春: 吉林大学, 2012.
    [11] LIU M, ZHANG M, HU J, et al. Evaluation method of handling force feedback comfort of vehicle gear lever[J]. China Mechanical Engineering, 2016, 27(15): 2100.
    [12] SU Z B, LI D R, LI B, et al. Objective visual comfort assessment model of stereoscopic images based on bp neural network[C]//2018 Tenth International Conference on Advanced Computational Intelligence (ICACI). Xiamen:[S.
    [13] 张昊, 王琪洁, 朱建军,等. 样本数据预处理对基于BP神经网络的GPS高程拟合的影响[J]. 大地测量与地球动力学, 2011,31(2):129.
    [14] KALIK S F, PROKHOROV D V. Automotive turing test[C]// The Workshop on Performance Metrics for Intelligent Systems. Gaithersburg: ACM, 2007:152-158.
    [15] 李可. 高速公路合流影响区车辆运行建模和仿真分析[D].武汉:华中科技大学,2015.
    [16] WANG Y, ZHANG Q, ZHANG L, et al. A method to automatic measuring riding comfort of autonomous vehicles[C]//8th International Conference on Design, User Experience, and Usability, DUXU 2019held as part of the 21st International Conference on Human-Computer Interaction. Orlando: [S.
    [17] 丛爽. 面向MATLAB工具箱的神经网络理论与应用[M].合肥: 中国科技大学出版社, 2009.
    [18] LIANG J, LIU R. Stacked denoising autoencoder and dropout together to prevent overfitting in deep neural network[C]// 2015 8th International Congress on Image and Signal Processing (CISP). Shenyang:IEEE, 2015:697-701.
    [19] 徐梓荐. 蒙特卡洛方法神经网络的激活函数研究及应用[D].兰州: 兰州大学, 2018.
    [20] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929.
    [21] AZHAR M A, THOMAS P A. Comparative review of feature selection and classification modeling[C]// 2019 International Conference on Advances in ComputingCommunication and Control (ICAC3). Mumbai: IEEE, 2019:9.
    [22] 孙娟娟, 刘缵武. 判断数据适合分级方法的理论分析[J]. 测绘工程, 2007, 16(5):14.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

CHEN Junyi, CHEN Lei, MENG Haolan, XIONG Lu. Evaluation Model of Harmony with Traffic Based on Neural Network[J].同济大学学报(自然科学版),2021,49(1):135~141

Copy
Share
Article Metrics
  • Abstract:532
  • PDF: 1005
  • HTML: 168
  • Cited by: 0
History
  • Received:June 19,2020
  • Online: February 26,2021
Article QR Code