Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2020, Vol. 54 Issue (10): 1892-1898    DOI: 10.3785/j.issn.1008-973X.2020.10.004
计算机技术     
用于轿车PEPS系统的双终端差分改进识别算法
刘凯1(),吉小军1,*(),赵忠华1,曹一文1,杨剑2,庞晓锋2
1. 上海交通大学 电子信息与电气工程学院，上海 200240
2. 上汽集团技术中心，上海 201800
Dual terminal differential improved recognition algorithm for car PEPS system
Kai LIU1(),Xiao-jun JI1,*(),Zhong-hua ZHAO1,Yi-wen CAO1,Jian YANG2,Xiao-feng PANG2
1. School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. Technology Center of SAIC Motor, Shanghai 201800, China
 全文: PDF(937 KB)   HTML
摘要：

针对基于智能手机的汽车无钥匙进入和启动系统（PEPS）车内外高精度辨识技术需求，设计基于双终端的差分K近邻定位算法. 通过改进的Dempster-Shafer证据理论，将双终端算法与典型单终端算法的辨识结果进行融合，提升识别算法的鲁棒性与准确性. 与传统的K近邻和概率分布法相比，融合算法在实验场景中对终端车内外状态的辨识准确率提升10%. 在传统定位算法易出现误判的车窗附近范围内，将误差距离从距车窗20 cm缩小到距车窗5 cm.
关键词： 无钥匙进入与启动系统(PEPS);  接收信号强度;  位置指纹;  K近邻法;  差分;  Dempster-Shafer证据理论    
Abstract:

A differential K-nearest neighbor positioning algorithm based on dual terminals was designed aiming at the need for high-precision identification technology of Smartphone-based car passive entry and passive start (PEPS) system. The recognition results of the dual-terminal algorithm and the typical single-terminal algorithm were merged to improve the robustness and accuracy of the recognition algorithm through the improved Dempster-Shafer evidence theory. The accuracy of the internal and external state recognition of the terminal car was improved by 10% in the experimental scene by using the fusion algorithm. The error distance near the window was reduced from 20 cm to 5 cm in the vicinity of the window in which the conventional positioning algorithm was prone to misjudgment.
Key words: passive entry and passive start (PEPS)    received signal strength    location fingerprint    K-nearest neighbor algorithm    difference    Dempster-Shafer evidence theory
收稿日期: 2019-09-28 出版日期: 2020-10-28
CLC:  TP 273  
基金资助: 上海汽车工业科技发展基金会资助项目
通讯作者: 吉小军     E-mail: 1148035619@sjtu.edu.cn;jxj127@sjtu.edu.cn
作者简介: 刘凯（1994—），男，硕士生，从事无线定位算法的研究. orcid.org/000-0001-6066-5424. E-mail： 1148035619@sjtu.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
刘凯
吉小军
赵忠华
曹一文
杨剑
庞晓锋

引用本文:

刘凯,吉小军,赵忠华,曹一文,杨剑,庞晓锋. 用于轿车PEPS系统的双终端差分改进识别算法[J]. 浙江大学学报(工学版), 2020, 54(10): 1892-1898.

Kai LIU,Xiao-jun JI,Zhong-hua ZHAO,Yi-wen CAO,Jian YANG,Xiao-feng PANG. Dual terminal differential improved recognition algorithm for car PEPS system. Journal of ZheJiang University (Engineering Science), 2020, 54(10): 1892-1898.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2020.10.004    或    http://www.zjujournals.com/eng/CN/Y2020/V54/I10/1892

图 1  离线阶段与在线阶段流程
图 2  在线阶段匹配算法的示意图
图 3  双终端RSS的差分效果
图 4  信标总体布局与信标布局实例
算法 Aout / % Ain / %
KNN 100 95.92
DKNN 99.16 92.52
Bayes 89.6 96.60
LR 100 93.54
DS 100 97.34
表 1  各算法内、外辨识性能
图 5  主驾驶车窗内溢5 cm辨识结果
图 6  主驾驶车窗外溢5 cm辨识结果
位置 Aout / % Ain / %
外溢5 cm 外溢10 cm 内溢5 cm 内溢10 cm
左前窗 100 100 100 100
右前窗 100 100 100 100
左后窗 100 100 100 100
右后窗 93.6 95.8 98.1 100
表 2  DS融合算法在车窗附近的辨识性能
1 BAHL P, PADMANABHAN V N. RADAR: an in-building RF-based user location and tracking system [C]// 19th Annual Joint Conference of the IEEE Computer and Communications Societies. Tel Aviv: IEEE, 2000: 775-784.
2 李华亮. WLAN环境下的室内定位算法研究[D]. 长春: 吉林大学, 2016.
LI Hua-liang. Research on indoor location algorithm in WLAN [D]. Changchun: Jilin University, 2016.
3 KARANI R, DHOTE S, KHANDURI N, et al. Implementation and design issues for using Bluetooth low energy in passive keyless entry systems [C]// 2016 IEEE Annual India Conference. Bangalore: IEEE, 2016: 1-6.
4 KARLSSON E, LAGERBIELKE A. Demonstrator development for phone as a key based on Bluetooth low energy [D]. Link?ping: Link?ping University, 2017.
5 全祯业. PEPS系统的安全与可靠性研究[D]. 贵阳: 贵州大学, 2016.
QUAN Zhen-ye. Research on the safety and reliability of PEPS system [D]. Guiyang: Guizhou University, 2016.
6 SHIN B, LEE J H, LEE T, et al. Enhanced weighted K-nearest neighbor algorithm for indoor Wi-Fi positioning systems [C]// International Conference on Computing Technology and Information Management. Seoul: IEEE, 2012: 574-577.
7 XIE Y, WANG Y, NALLANATHAN A, et al An improved K-nearest-neighbor indoor localization method based on Spearman distance[J]. IEEE Signal Processing Letters, 2016, 23 (3): 351- 355
doi: 10.1109/LSP.2016.2519607
8 ZHANG A, YUAN Y, WU Q, et al Wireless localization based on RSSI fingerprint feature vector[J]. International Journal of Distributed Sensor Networks, 2015, (9): 1- 7
9 PEI L, CHEN R, LIU J, et al. Inquiry-based Bluetooth indoor positioning via RSSI probability distributions [C]// International Conference on Advances in Satellite and Space Communications. Athens: IEEE, 2010: 151-156.
10 陈丽娜. WLAN位置指纹室内定位关键技术研究[D]. 上海: 华东师范大学, 2014.
CHEN Li-na. Research on major technology of using WLAN and fingerprint for indoor positioning [D]. Shanghai: East China Normal University, 2014.
11 CHEN L Bayesian fusion for indoor positioning using Bluetooth fingerprints[J]. Wireless Personal Communications, 2013, 70 (4): 1735- 1745
doi: 10.1007/s11277-012-0777-1
12 GELMINI S, STRADA S, TANELLI M, et al. Analysis and development of a novel algorithm for the in-vehicle hand-usage of a smartphone [C] // IEEE International Conference on Systems, Man, and Cybernetics. Miyazaki: IEEE, 2018: 1239-1244.
13 REN Qing-yu. On the potential of geomagnetism-aided vehicle in-out detection using BLE RSS [C]// 第38届中国控制会议论文集(3). 广州: 上海系统科学出版社, 2019: 6.
14 KING T, KOPF S, HAENSELMANN T, et al. COMPASS: a probabilistic indoor positioning system based on 802.11 and digital compasses [C]// ACM Workshop on Wireless Network Testbeds, Experimental Evaluation and Characterization. California: ACM, 2006: 34-40.
15 DEMPSTER A P Upper and lower probabilities induced by a multivalued mapping[J]. Annals of Mathematical Statistics, 1967, 38 (2): 325- 339
doi: 10.1214/aoms/1177698950
16 SHAFER G A. Mathematical theory of evidence [M]. Princeton: Princeton University Press, 1976.
17 ZADEH L A Review of Shafer’s a mathematical theory of evidence[J]. AI Magazine, 1984, 5 (3): 81- 83
18 LIU W Analyzing the degree of conflict among belief functions[J]. Artificial Intelligence, 2006, 170 (11): 909- 924
doi: 10.1016/j.artint.2006.05.002
19 YONG D, DONG W, QI L I, et al A new method to analyze evidence conflict[J]. Control Theory and Applications, 2011, 28 (6): 839- 844
20 WANG D, Li Q, JIANG W, et al New method to combine conflict evidence based on pignistic probability distance[J]. Infrared and Laser Engineering, 2009, 38 (1): 149- 154
21 张明华. 基于WLAN的室内定位技术研究[D]. 上海: 上海交通大学, 2009.
ZHANG Ming-hua. Study on WLAN based indoor location estimation technology [D]. Shanghai: Shanghai Jiaotong University, 2009.
[1] 李林楠,张为,党艳杰,李泰安. 低功耗差分复用波束合成器的设计[J]. 浙江大学学报(工学版), 2021, 55(3): 571-577.
[2] 周爱民,刘宏斌,张书涛,欧阳晋焱. 面向汽车主客观审美评价的不确定性推理模型[J]. 浙江大学学报(工学版), 2021, 55(3): 419-429.
[3] 董大钊,徐冠华,高继良,徐月同,傅建中. 基于机器视觉的机器人装配位姿在线校正算法[J]. 浙江大学学报(工学版), 2021, 55(1): 145-152.
[4] 徐思远,杜军,赵光喜,魏正英. 45钢/锡铅合金复合结构熔融沉积中熔滴过渡行为[J]. 浙江大学学报(工学版), 2020, 54(11): 2224-2232.
[5] 张磊,张菁. 支持数据实用性和容错的差分隐私保护方案[J]. 浙江大学学报(工学版), 2019, 53(8): 1496-1505.
[6] 王硕朋,杨鹏,孙昊,刘迈. 两级参考点匹配位置指纹声源定位方法[J]. 浙江大学学报(工学版), 2019, 53(6): 1198-1204.
[7] 黄梓亮, 欧阳小平, 赵天菲, 张建波, 周亮, 杨华勇. 飞机液压含气量检测系统特性[J]. 浙江大学学报(工学版), 2019, 53(1): 158-165.
[8] 高冠, 朱瑞, 贺治国, 游景皓. 自由液面水流与固体构筑物作用的高精度数值模拟[J]. 浙江大学学报(工学版), 2018, 52(6): 1201-1208.
[9] 梁小龙, 乔文丽, 赵西增. 分层环境中异重流运动问题的直接数值模拟[J]. 浙江大学学报(工学版), 2018, 52(5): 996-1001.
[10] 高鹏辉, 赵武峰, 沈继忠. 结合背景差分与光流法的人群状态突变检测[J]. 浙江大学学报(工学版), 2018, 52(4): 649-656.
[11] 陈星宇, 黄善和, 何昊哲. 探测频率对多频声学测沙技术测量误差的影响[J]. 浙江大学学报(工学版), 2018, 52(2): 307-316.
[12] 王硕朋, 杨鹏, 孙昊. 听觉定位数据库构建过程优化[J]. 浙江大学学报(工学版), 2018, 52(10): 1973-1979.
[13] 毕晓君, 王佳荟. 基于混合学习策略的教与学优化算法[J]. 浙江大学学报(工学版), 2017, 51(5): 1024-1031.
[14] 胡祝华, 赵瑶池, 程杰仁, 彭金莲. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报(工学版), 2014, 48(8): 1488-1495.
[15] 杨朝晖, 张进华, 洪军, 姚建国, 王煜. 超高精度滚动轴承旋转精度测试系统误差分析[J]. 浙江大学学报(工学版), 2014, 48(6): 1095-1101.