NEURAL NETWORK LATERAL DYNAMICS MODELING AND CONTROL BASED ON ED-LSTM FOR INTELLIGENT VEHICLE
-
摘要: 车辆动力学建模过程中通常会进行简化和假设, 导致模型在某些工况下无法准确反映车辆的实际动态特性, 影响控制精度甚至安全性. 鉴于此, 该文提出了一种基于数据驱动的非线性建模与控制方法, 建立了新型神经网络车辆横向动力学多步预测模型, 实现了智能汽车对参考轨迹的跟踪控制. 首先, 在分析车辆单轨模型并考虑轮胎非线性和纵向负载转移的基础上, 基于编码器-解码器结构设计神经网络横向动力学模型. 其中, 使用串行排列来扩展微分方程描述不完全的动力学信息, 隐藏层神经元学习车辆的高度非线性和强耦合特性, 进而提高模型全局计算精度. 利用所构建的数据集进行模型训练和测试, 结果表明, 相比于物理模型, 所提出的模型在不同路面附着系数条件下均具有更高的建模精度, 具有隐式预测路面摩擦条件能力. 其次, 利用提出的模型设计轨迹跟踪控制算法, 根据车辆稳态转向假设, 计算所需的前轮转向角和稳态质心侧偏角, 将稳态质心侧偏角纳入基于路径误差的转向反馈中, 实现参考轨迹跟踪控制. 最后, 使用CarSim/Simulink联合仿真及HIL实验测试进行不同工况试验的对比分析, 对所提出的基于神经网络模型的控制算法进行评价, 结果表明, 该模型能够实现智能汽车在高速下精确的跟踪控制效果, 并具有良好的横向稳定性.Abstract: Simplification and assumptions are usually made in the process of vehicle dynamics modeling, resulting in the model can not accurately reflect the actual dynamic characteristics of the vehicle under some working conditions, which affects the control accuracy and even safety. In view of this, this paper proposes a data-driven nonlinear modeling and control method, establishes a new neural network multi-step prediction model of vehicle lateral dynamics, and realizes the tracking control of reference trajectory of intelligent vehicle. Firstly, based on the analysis of vehicle single-track model and considering tire nonlinearity and longitudinal load transfer, a neural network lateral dynamics model is designed based on encoder decoder structure. Among them, the serial arrangement is used to expand the differential equation to describe the incomplete dynamic information, and the hidden layer neurons learn the highly nonlinear and strong coupling characteristics of the vehicle, so as to improve the global calculation accuracy of the model. Use the constructed data set for model training and testing, the results show that, compared with the physical model, the proposed model has higher modeling accuracy under different road adhesion coefficients, and has the ability to implicitly predict road friction conditions. Secondly, using the proposed model to design trajectory tracking control algorithm, according to the vehicle steady-state steering assumption, the required front wheel steering angle and steady-state sideslip angle are calculated, and the steady-state sideslip angle is incorporated into the steering feedback based on path error to realize the reference trajectory tracking control. Finally, comparative analysis of tests under different working conditions is carried out with Simulink / CarSim co-simulation and HiL experiments to evaluate the proposed control algorithm based on neural network model. The results show that the model can realize the accurate tracking control effect of intelligent vehicle at high speed, and has good lateral stability.
-
Key words:
- Intelligent vehicle /
- dynamics modeling /
- neural network /
- trajectory tracking control
-
图 3 ED-LSTM: 车辆横向动力学多步预测模型
Figure 3. ED-LSTM: Multi step prediction vehicle Lateral dynamics model
图 9 基于神经网络车辆动力学模型横向控制流程图
Figure 9. Lateral control flow chart of vehicle dynamics neural network model
图 10 双次换道曲线轨迹跟踪仿真对比
Figure 10. Trajectory tracking simulation comparison in double-lane change
13 横向加速度、质心侧偏角、横摆角速度对比(续)
13. Lateral acceleration, sideslip angle, yaw rate comparison (continued)
表 1 跟踪误差评价指标
Table 1. Evaluation indexes of tracking error
Error Classification Control Method Mean Value Standard Deviation Variance Minimum Maximum Range Lateral Error (m) ED-LSTM −0.00204 0.03145 9.914 × 10−4 −0.07254 0.08246 0.155 STM −0.00341 0.04716 0.00222 −0.09393 0.10255 0.19648 Heading Error (rad) ED-LSTM 4.334 × 10−5 0.00692 4.784 × 10−5 −0.01703 0.01258 0.0296 STM 9.119 × 10−5 0.00902 8.144 × 10−5 −0.02521 0.02322 0.04843 
下载: 导出CSV
-
[1] Tan D, Chen W, Wang H. On the use of monte-carlo simulation and deep fourier neural network in lane departure warning. IEEE Intelligent Transportation Systems Magazine, 2017, 9(4): 76-90 doi: 10.1109/MITS.2017.2743204 [2] 金辉, 丁峰. 智能车辆换道行驶的经济车速研究. 汽车工程, 2018, 40(5): 542-546 (Jin Hui, Ding Feng. Study on economic speed of intelligent vehicle changing lanes. Automotive Engineering, 2018, 40(5): 542-546 (in Chinese)Jin Hui, Ding Feng. Study on economic speed of intelligent vehicle changing lanes. Automotive Engineering, 2018, 40(5): 542-546 (in Chinese) [3] 蔡英凤, 臧勇, 孙晓强等. 基于可拓切换控制方法的智能车辆车道保持系统研究. 中国公路学报, 2019, 32(6): 43-52 (Cai Yingfeng, Zang Yong, Sun Xiaoqiang, et al. Research on intelligent vehicle lane keeping system based on extension switching control method. China Journal of Highway and Transport, 2019, 32(6): 43-52 (in Chinese)Cai Yingfeng, Zang Yong, Sun Xiaoqiang, et al. Research on intelligent vehicle lane keeping system based on extension switching control method. China Journal of Highway and Transport, 2019, 32(6): 43-52 (in Chinese) [4] Yakub F, Abu A, Sarip S, et al. Study of model predictive control for path-following autonomous ground vehicle control under crosswind effect. Journal of Control Science and Engineering, 2016, https://doi.org/10.1155/2016/6752671 [5] Jazar R N. Vehicle dynamics. New York: Springer, 2008 [6] Segel L. Theoretical prediction and experimental substantiation of the response of the automobile to steering control. Proceedings of the Institution of Mechanical Engineers:Automobile Division, 1956, 10(1): 310-330 doi: 10.1243/PIME_AUTO_1956_000_032_02 [7] Kazemi R, Bahaghighat M K, Panahi K. Yaw moment control of four wheel steering vehicle by fuzzy approach. In: IEEE International Conference on Industrial Technology, Chengdu, April, 2008 [8] 陈慧岩, 陈舒平, 龚建伟. 智能汽车横向控制方法研究综述. 兵工学报, 2017, 38(6): 1203-1214 (Chen Huiyan, Chen Shuping, Gong Jianwei. A survey of the research on the lateral control methods of intelligent vehicles. Acta Armamentarii, 2017, 38(6): 1203-1214 (in Chinese) doi: 10.3969/j.issn.1000-1093.2017.06.021Chen Huiyan, Chen Shuping, Gong Jianwei. A survey of the research on the lateral control methods of intelligent vehicles. Acta Armamentarii, 2017, 38(6): 1203-1214 (in Chinese) doi: 10.3969/j.issn.1000-1093.2017.06.021 [9] Liu J, Jayakumar P, Stein J L, et al. A study on model fidelity for model predictive control-based obstacle avoidance in high-speed autonomous ground vehicles. Vehicle System Dynamics, 2016, 54(11): 1629-1650 doi: 10.1080/00423114.2016.1223863 [10] Aouaouda S, Chadli M, Boukhnifer M, et al. Robust fault tolerant tracking controller design for vehicle dynamics: A descriptor approach. Mechatronics, 2015, 30: 316-326 doi: 10.1016/j.mechatronics.2014.09.011 [11] 王家恩, 陈无畏, 王檀彬等. 基于期望横摆角速度的视觉导航智能车辆横向控制. 机械工程学报, 2012, 48(4): 108-115 (Wang Jiaen, Chen Wuwei, Wang Tanbin, et al. Lateral control of vision guided intelligent vehicle based on expected yaw rate. Journal of Mechanical Engineering, 2012, 48(4): 108-115 (in Chinese) doi: 10.3901/JME.2012.04.108Wang Jiaen, Chen Wuwei, Wang Tanbin, et al. Lateral control of vision guided intelligent vehicle based on expected yaw rate. Journal of Mechanical Engineering, 2012, 48(4): 108-115 (in Chinese) doi: 10.3901/JME.2012.04.108 [12] Francesco B, Paolo F. MPC-based Approach to Active Steering for Autonomous Vehicle Systems. International Journal on Vehicle Autonomous Systems, 2005, 3(2/4): 265-291 [13] Falcone P, Borrelli F, Asgari J, et al. Predictive active steering control for autonomous vehicle systems. IEEE Transactions on Control Systems Technology, 2007, 15(3): 566-580 doi: 10.1109/TCST.2007.894653 [14] Hu C, Wang R, Yan F, et al. Output constraint control on path following of four-wheel independently actuated autonomous ground vehicles. IEEE Transactions on Vehicular Technology, 2015, 65(6): 4033-4043 [15] 江浩斌, 朱宸, 唐斌等. 基于可拓自抗扰的 ECHBPS 商用车横向稳定控制. 江苏大学学报(自然科学版), 2021, 42(2): 166-172 (Jiang Haobin, Zhu Chen, Tang Bin, et al. Lateral stability control of ECHBPS commercial vehicle based on extended active disturbance rejection. Journal of Jiangsu University (Natural Science Edition) , 2021, 42(2): 166-172 (in Chinese)Jiang Haobin, Zhu Chen, Tang Bin, et al. Lateral stability control of ECHBPS commercial vehicle based on extended active disturbance rejection. Journal of Jiangsu University (Natural Science Edition), 2021, 42(2): 166-172 (in Chinese) [16] 王海, 刘明亮, 蔡英凤等. 基于激光雷达与毫米波雷达融合的车辆目标检测算法. 江苏大学学报 (自然科学版), 2021, 42(4): 389-394 (Wang Hai, Liu Mingliang, Cai Yingfeng, et al. Vehicle target detection algorithm based on fusion of laser radar and millimeter wave radar. Journal of Jiangsu University (Natural Science Edition) , 2021, 42(4): 389-394 (in Chinese)Wang Hai, Liu Mingliang, Cai Yingfeng, et al. Vehicle target detection algorithm based on fusion of laser radar and millimeter wave radar. Journal of Jiangsu University (Natural Science Edition), 2021, 42(4): 389-394 (in Chinese) [17] Liu Z, Cai Y, Wang H, et al. Robust target recognition and tracking of self-driving cars with radar and camera information fusion under severe weather conditions. IEEE Transactions on Intelligent Transportation Systems, 2021,doi: 10.1109/TITS.2021.3059674 [18] Wang H, Yu Y, Cai Y, et al. A comparative study of state-of-the-art deep learning algorithms for vehicle detection. IEEE Intelligent Transportation Systems Magazine, 2019, 11(2): 82-95 doi: 10.1109/MITS.2019.2903518 [19] Cai Y, Dai L, Wang H, et al. DLnet With Training Task Conversion Stream for Precise Semantic Segmentation in Actual Traffic Scene. IEEE Transactions on Neural Networks and Learning Systems, 2021,doi: 10.1109/TNNLS.2021.3080261 [20] He K, Gkioxari G, Dollár P, et al. Mask r-cnn. In:Proceedings of The IEEE International Conference on Computer Vision, Venice, October, 2017: 2961-2969 [21] Cai Y, Dai L, Wang H, et al. Pedestrian motion trajectory prediction in intelligent driving from far shot first-person perspective video. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(6): 5298-5313 doi: 10.1109/TITS.2021.3052908 [22] 蔡英凤, 朱南楠, 邰康盛等. 基于注意力机制的车辆行为预测. 江苏大学学报(自然科学版), 2020, 41(2): 125-130 (Cai Yingfeng, Zhu Nannan, Tai Kangsheng, et al. Vehicle behavior prediction based on attention mechanism. Journal of Jiangsu University (Natural Science Edition) , 2020, 41(2): 125-130 (in Chinese)Cai Yingfeng, Zhu Nannan, Tai Kangsheng, et al. Vehicle behavior prediction based on attention mechanism. Journal of Jiangsu University (Natural Science Edition), 2020, 41(2): 125-130 (in Chinese) [23] Chen C, Seff A, Kornhauser A, et al. Deepdriving: Learning affordance for direct perception in autonomous driving. In:Proceedings of The IEEE International Conference on Computer Vision, Santiago, December, 2015: 2722-2730 [24] Bojarski M, Del Testa D, Dworakowski D, et al. End to end learning for self-driving cars. arXiv preprint, 2016, https://doi.org/10.48550/arXiv.1604.07316 [25] Kabzan J, Hewing L, Liniger A, et al. Learning-based model predictive control for autonomous racing. IEEE Robotics and Automation Letters, 2019, 4(4): 3363-3370 doi: 10.1109/LRA.2019.2926677 [26] Rutherford SJ, Cole DJ. Modelling nonlinear vehicle dynamics with neural networks. International Journal of Vehicle Design, 2010, 53(4): 260-287 doi: 10.1504/IJVD.2010.034101 [27] Ji X, He X, Lv C, et al. Adaptive-neural-network-based robust lateral motion control for autonomous vehicle at driving limits. Control Engineering Practice, 2018, 76: 41-53 doi: 10.1016/j.conengprac.2018.04.007 [28] Spielberg NA, Brown M, Kapania NR, et al. Neural network vehicle models for high-performance automated driving. Science Robotics, 2019, 4(28): eaaw1975 doi: 10.1126/scirobotics.aaw1975 [29] Devineau G, Polack P, Altché F, et al. Coupled longitudinal and lateral control of a vehicle using deep learning. In:21 st International Conference on Intelligent Transportation Systems, Hawaii, November, 2018: 642-649 [30] Fraikin N, Funk K, Frey M, et al. A fast and accurate hybrid simulation model for the large-scale testing of automated driving functions. Proceedings of the Institution of Mechanical Engineers, Part D:Journal of Automobile Engineering, 2020, 234(4): 1183-1196 doi: 10.1177/0954407019861245 [31] 臧勇. 基于可拓理论的智能汽车轨迹跟踪控制研究. [硕士论文]. 镇江: 江苏大学, 2020Zang Yong. Research on intelligent vehicle trajectory tracking control based on extension theory. [Master Thesis]. Zhenjiang: Jiangsu University, 2020 (in Chinese) -
下载:
点击查看大图
图(17) / 表(1)
计量
- 文章访问数: 37
- HTML全文浏览量: 7
- PDF下载量: 4
- 被引次数: 0
