|
|
Autonomous navigation algorithm for intelligent vehicle in weak GPS environment |
1. Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, Jiangsu 212013, China; 2. Department of Computer and Information Science, University of MichiganDearborn, Dearborn, Michigan MI 48128, USA
|
|
|
Abstract To solve the problem that global positioning system (GPS) was easy to fail in urban environment, an autonomous navigation algorithm for intelligent vehicle was proposed by visual location recognition. To identify the global position of vehicle in the GPSfree environment, the discriminative visual features in the image were obtained through the attention model and the finegrained feature extraction module, and the matching retrieval between the aerial image and the offline satellite image was realized. According to the vehicle position information, the elite ant colony optimization algorithm was used to output the direction of the road branch ahead for the vehicle and perform global path planning. The results show that the finegrained feature extraction module can extract more discriminative features. The labelsmoothed crossentropy loss function training can be used to achieve effective identification of actual environmental locations, and vehicles can use the proposed algorithm to navigate autonomously in weak GPS environment.
|
Received: 23 April 2021
|
|
|
|
[1] |
胡兵,杨明,郭林栋,等.基于地面快速鲁棒特征的智能车全局定位方法[J].上海交通大学学报,2019,53(2):203-208.
|
|
HU B, YANG M, GUO L D,et al. Global localization for intelligent vehicles using ground SURF[J]. Journal of Shanghai Jiaotong University, 2019,53(2):203-208.(in Chinese)
|
[2] |
CHEN Z T, LAM O, JACOBSON A, et al. Convolutional neural networkbased place recognition[C]∥Proceedings of the 16th Australasian Conference on Robotics and Automation 2014. Australian:Robotics and Automation Association, 2014: 1-8.
|
[3] |
LIN T Y, CUI Y, BELONGIE S, et al. Learning deep representations for groundtoaerial geolocalization[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,USA:IEEE,2015: 5007-5015.
|
[4] |
ARANDJELOVIC' R, GRONAT P, TORII A, et al. NetVLAD: CNN architecture for weakly supervised place recognition[C]∥Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington,USA:IEEE Computer Society,2016: 5297-5307.
|
[5] |
YU J, ZHU C, ZHANG J, et al. Spatial pyramidenhanced NetVLAD with weighted triplet loss for place recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(2): 661-674.
|
[6] |
CHEN Z T, LIU L Q, SA I, et al. Learning context flexible attention model for longterm visual place recognition[J]. IEEE Robotics and Automation Letters, 2018, 3(4): 4015-4022.
|
[7] |
GARG S, SENDERHAUF N, MILFORD M. LoST? appearanceinvariant place recognition for opposite viewpoints using visual semantics[C]∥Robotics: Science and Systems, 2018: 1-11.
|
[8] |
XIN Z, CAI Y H, LU T, et al. Localizing discriminative visual landmarks for place recognition[C]∥2019 International Conference on Robotics and Automation. Piscataway,USA:IEEE, 2019: 5979-5985.
|
[9] |
HU J, SHEN L, SUN G. Squeezeandexcitation networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,USA:IEEE, 2018: 7132-7141.
|
[10] |
DAI Z Z, CHEN M Q, GU X D, et al. Batch dropblock network for person reidentification and beyond[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway,USA:IEEE,2019: 3691-3701.
|
[11] |
吴麟麟,杨俊辉.基于改进AWA*算法的智能车辆全局路径规划研究[J].重庆理工大学学报(自然科学),2018,32(8):39-46.
|
|
WU L L,YANG J H. Research on global path planning of intelligent vehicles based on improved AWA* algorithm[J]. Journal of Chongqing University of Technology (Natural Science), 2018,32(8):39-46.(in Chinese)
|
[12] |
汪贵庆,袁杰,沈庆宏.基于精英蚁群算法的交通最优路径研究[J].南京大学学报(自然科学),2019,55(5):709-717.
|
|
WANG G Q,YUAN J,SHEN Q H. Research on traffic optimal path based on elite ant system[J]. Journal of Nanjing University(Natural Science), 2019,55(5):709-717.(in Chinese)
|
[13] |
ZHENG Z D, WEI Y C, YANG Y. University1652: a multiview multisource benchmark for dronebased geolocalization[C]∥Proceedings of the 28th ACM International Conference on Multimedia, 2020: 1395-1403.
|
[14] |
DING L R,LONG Z Y, MENG L X, et al. A practical crossview image matching method between uav and satellite for UAVbased geolocalization[J]. Remote Sensing, 2021, 13(1): 1-20.
|
[15] |
WANG T Y, ZHENG Z D, YAN C G, et al. Each part matters: local patterns facilitate crossview geolocalization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(2): 867-879.
|
|
|
|