前车切入与切出工况下匀质队列速度规划与跟随控制

杨炜; 孙雪; 司宇; 韩毅; 蔡尧

doi:10.19818/j.cnki.1671-1637.2024.06.017

前车切入与切出工况下匀质队列速度规划与跟随控制

doi: 10.19818/j.cnki.1671-1637.2024.06.017

杨炜^1,,
孙雪¹,
司宇²,
韩毅¹,
蔡尧³

1.
长安大学汽车学院，陕西西安 710064
2.
广州汽车集团股份有限公司汽车工程研究院，广东广州 511434
3.
驭势科技(北京)有限公司，北京 102400

基金项目:

国家重点研发计划 2021YFE0203600

陕西省自然科学基金项目 2017JQ6045

详细信息

作者简介:
杨炜(1985-)，男，陕西蒲城人，长安大学讲师，工学博士，从事汽车主动安全技术与智能网联汽车研究

中图分类号: U495
计量
- 文章访问数: 61
- HTML全文浏览量: 25
- PDF下载量: 10
- 被引次数: 0
出版历程
- 收稿日期: 2024-05-30
- 刊出日期: 2024-12-25

Homogeneous platoon speed planning and following control in front vehicle cut-in and cut-out conditions

YANG Wei^1
,,
SUN Xue¹,
SI Yu²,
HAN Yi¹,
CAI Yao³

1.
School of Automobile, Chang'an University, Xi'an 710064, Shaanxi, China
2.
Automotive Engineering Research Institute, Guangzhou Automobile Group Co., Ltd., Guangzhou 511434, Guangdong, China
3.
Uisee Technology (Beijing) Co., Ltd., Beijing 102400, China

Funds:

National Key Research and Development Program of China 2021YFE0203600

Natural Science Foundation of Shaanxi Province 2017JQ6045

More Information

Author Bio:
YANG Wei(1985-), male, assistant professor, PhD, yw@chd.edu.cn

摘要

摘要: 针对匀质队列定速巡航时前车切入切出可能导致碰撞风险以及跟随控制效率低、稳定性差的问题，提出一种前车切入与切出工况下匀质队列速度规划与跟随控制模型，基于卷积神经网络-门控循环单元(CNN-GRU)混合网络建立轨迹预测模型，以预测未来一段时域内的前车换道轨迹；通过构建纵向位移与时间的关系，确定了前车的切入或切出状态，搭建了跟随车速度跟随模型，并进行了队列整体速度规划；建立了模糊线性上层控制器，根据车速差输出符合驾驶场景需求的期望加速度；结合纵向逆动力学模型和模糊比例-积分-微分(PID)控制建立了下层控制器，将期望加速度转化为驱动转矩或制动压力，从而直接控制车辆；为进一步验证提出的控制模型的有效性，搭建了PreScan/CarSIM/SIMULINK联合仿真平台，设计了相邻前车切入和切出时的仿真工况，并将提出的控制模型与自适应巡航控制(ACC)方案进行了对比。研究结果表明：应用提出的控制模型后，所有信息流拓扑结构队列中均未出现追尾现象，且最大间距误差、全局平均速度跟踪误差和局部平均速度跟踪误差分别至少降低了55.9%、40.6%和42.0%。由此可见，提出的控制模型在前车切入与切出工况下不仅能避免潜在的追尾事故，而且可以有效缩短队列车辆间的最大间距，减小队列的速度跟踪误差，有利于提升队列的跟随效率和行驶稳定性。
- 交通控制 /
- 匀质队列 /
- 速度规划 /
- 换道轨迹预测 /
- 车辆跟随 /
- 分层控制
Abstract: To solve the problems that the front vehicle cut-in and cut-out may lead to a collision risk, as well as the low efficiency and poor stability of following control during constant speed cruise of the homogeneous platoon, a homogeneous platoon speed planning and following control model in front vehicle cut-in and cut-out conditions was proposed. Based on the convolutional neural network-gated recurrent unit (CNN-GRU) hybrid network, a trajectory prediction model was established to predict the lane change trajectory of front vehicle within a future time domain. By constructing the relationship between longitudinal displacement and time, the front vehicle cut-in or cut-out state was determined. The speed following model of following vehicles was built, and the overall speed planning of the platoon was carried out. A fuzzy linear upper controller was established to output the desired acceleration according to the speed difference meeting the driving scenario requirements. Combining the longitudinal inverse dynamics model and fuzzy proportional integral derivative (PID) control, a lower controller was established to convert the desired acceleration into the driving torque or braking pressure. Thus, the direct control of the vehicle was achieved. To further verify the effectiveness of the proposed control model, a PreScan/CarSIM/SIMULINK co-simulation platform was built, simulation conditions for the adjacent front vehicle cut-in and cut-out were designed, and the proposed control model was compared with the adaptive cruise control (ACC) scheme. Research results show that after applying the proposed control model, no rear-end coallision occurs in platoons for all information flow topologies, and the maximum spacing difference, global average speed tracking error and local average speed tracking error reduce at least 55.9%, 40.6% and 42.0%, respectively. Therefore, the proposed control model can not only avoid potential rear-end collisions in front vehicle cut-in and cut-out conditions, but also can effectively shorten the maximum gap between platoon vehicles, reduce the speed tracking error of the platoon, and help to improve the following efficiency and driving stability of the platoon.
- traffic control /
- homogeneous platoon /
- speed planning /
- lane change trajectory prediction /
- car-following /
- hierarchical control

HTML全文

图 1 控制策略框架

Figure 1. Structure of control strategy

下载: 全尺寸图片幻灯片

图 2 CNN-GRU模型网络结构

Figure 2. Network structure of CNN-GRU model

下载: 全尺寸图片幻灯片

图 3 轨迹预测模型训练流程

Figure 3. Training process of trajectory prediction model

下载: 全尺寸图片幻灯片

图 4 驾驶人在环仿真平台结构

Figure 4. Structure of driver-in-the-loop simulation platform

下载: 全尺寸图片幻灯片

图 5 相邻前车换道场景

Figure 5. Lane change scenario for neighboring front vehicle

下载: 全尺寸图片幻灯片

图 6 前车切入时刻占据路径

Figure 6. Occupation path at front vehicle cut-in moment

下载: 全尺寸图片幻灯片

图 7 ST图及其栅格化处理

Figure 7. ST diagram and its rasterization

下载: 全尺寸图片幻灯片

图 8 动态规划算法结果

Figure 8. Results of dynamic planning algorithm

下载: 全尺寸图片幻灯片

图 9 二次规划算法结果

Figure 9. Results of quadratic planning algorithm

下载: 全尺寸图片幻灯片

图 10 梯形速度规划算法结果

Figure 10. Results of trapezoidal speed planning algorithm

下载: 全尺寸图片幻灯片

图 11 七次多项式模型优化结果

Figure 11. Optimization results of seventh degree polynomial model

下载: 全尺寸图片幻灯片

图 12 匀质队列分布式分层控制器

Figure 12. Homogeneous platoon distributed hierarchical controller

下载: 全尺寸图片幻灯片

图 13 模糊线性上层控制器

Figure 13. Fuzzy linear upper controller

下载: 全尺寸图片幻灯片

图 14 模糊推理系统结构

Figure 14. Structure of fuzzy reasoning system

下载: 全尺寸图片幻灯片

图 15 下层控制器结构

Figure 15. Structure of lower controller

下载: 全尺寸图片幻灯片

图 16 e_c的隶属度函数

Figure 16. Membership function of e_c

下载: 全尺寸图片幻灯片

图 17 不同模型预测轨迹与实际轨迹对比

Figure 17. Comparison between predicted trajectories by different models and actual trajectory

下载: 全尺寸图片幻灯片

图 18 联合仿真平台结构

Figure 18. Structure of co-simulation platform

下载: 全尺寸图片幻灯片

图 19 前车切入场景

Figure 19. Scenario of front vehicle cut-in

下载: 全尺寸图片幻灯片

图 20 前车切出场景

Figure 20. Scenario of front vehicle cut-out

下载: 全尺寸图片幻灯片

图 21 使用ACC策略时的队列车间距

Figure 21. Platoon headways when using ACC strategy

下载: 全尺寸图片幻灯片

图 22 使用速度跟随策略时的队列车间距

Figure 22. Platoon headways when using speed following strategy

下载: 全尺寸图片幻灯片

表 1 驾驶人年龄、驾龄分布

Table 1. Driver age and driving experience distributions

驾驶人分类特征	特征分布	试验人员数
年龄分布/岁	20~30	4
	31~45	4
	其他	2
驾龄分布/年	3	2
	4	2
	5	2
	6	2
	7	2

下载: 导出CSV

表 2 线性控制单元控制增益

Table 2. Control gains of linear control unit

信息流拓扑结构	k
BD	(6, 13, 6)^T
其他	(0.5, 1.2, 0.6)^T

下载: 导出CSV

表 3 模糊推理系统中各变量论域

Table 3. Variable universes in fuzzy reasoning system

拓扑结构	变量	论域
BD	e	[-1, 1]
	e_c	[-3, 3]
	ΔK_v	[0, 5]
其他	e	[-2, 2]
	e_c	[-3, 3]
	ΔK_v	[0, 0.6]

下载: 导出CSV

表 4 模糊推理系统规则

Table 4. Fuzzy reasoning system rules

ΔK_v		e_c
ΔK_v		NH	NC	NL	Z0	PL	PC	PH
e	NH	NH	NH	NC	NC	NC	NC	NC
	NC	NH	NH	NH	NH	NH	NH	NC
	NL	NH	NH	NH	NH	NC	NC	NL
	Z0	NH	NH	NH	NH	NH	NC	NC
	PL	NC	NC	NC	NL	NL	Z0	Z0
	PC	PH	PH	PH	PH	PH	PH	PH
	PH	PH	PH	PH	PH	PH	PH	PH

下载: 导出CSV

表 5 平均y坐标位置误差的平均值

Table 5. Average values of average y-coordinate position errors m

预测模型	不同预测时域(s)下的误差平均值
预测模型	1	2	3	4
CNN-GRU	0.143	0.258	0.786	0.749
CNN-LSTM	0.199	0.208	0.741	0.824
GRU	0.304	0.735	0.886	0.902

下载: 导出CSV

表 6 最终y坐标误差的平均值

Table 6. Average values of final y-coordinate errors m

预测模型	不同预测时域(s)下的误差平均值
预测模型	1	2	3	4
CNN-GRU	0.165	0.240	0.447	0.473
CNN-LSTM	0.193	0.172	0.539	0.686
GRU	0.409	0.735	0.997	1.026

下载: 导出CSV

表 7 平均x坐标误差的平均值

Table 7. Average values of average x-coordinate errors m

预测模型	不同预测时域(s)下的误差平均值
预测模型	1	2	3	4
CNN-GRU	2.909	3.604	3.299	3.974
CNN-LSTM	5.293	5.174	5.741	5.762
GRU	7.265	8.374	9.545	9.897

下载: 导出CSV

表 8 最终x坐标误差的平均值

Table 8. Average values of final x-coordinate errors m

预测模型	不同预测时域(s)下的误差平均值
预测模型	1	2	3	4
CNN-GRU	2.709	2.707	2.954	4.089
CNN-LSTM	5.148	5.153	3.762	5.779
GRU	7.993	9.978	10.142	11.481

下载: 导出CSV

表 9 最大间距差对比

Table 9. Comparison of maximum spacing difference m

拓扑结构	模糊控制策略	对比策略
PF	2.464 7	2.758 9
PLF	2.118 5	2.193 5
BD	0.927 1	0.947 8
BDL	2.118 4	2.193 3
TPF	2.118 5	2.193 5
TPLF	2.118 5	2.193 5

下载: 导出CSV

表 10 全局平均速度跟踪误差对比

Table 10. Comparison of global average speed tracking error m·s^-1

拓扑结构	模糊控制策略	对比策略
PF	0.510 2	0.605 0
PLF	0.083 8	0.089 3
BD	0.115 7	0.121 8
BDL	0.083 9	0.089 3
TPF	0.184 2	0.201 4
TPLF	0.083 5	0.089 0

下载: 导出CSV

表 11 局部平均速度跟踪误差对比

Table 11. Comparison of local average speed tracking error m·s^-1

拓扑结构	PF	BD	TPF
模糊控制策略	0.534 2	0.098 6	0.126 7
对比策略	0.645 9	0.104 0	0.279 8

下载: 导出CSV

表 12 最大间距差对比

Table 12. Comparison of maximum spacing difference m

拓扑结构	速度跟随策略	对比策略
PF	2.717 9	6.487 5
PLF	2.171 9	4.925 3
BD	0.866 2	1.978 3
BDL	2.171 9	4.925 3
TPF	2.171 9	4.925 3
TPLF	2.171 9	4.925 3

下载: 导出CSV

表 13 全局平均速度跟踪误差对比

Table 13. Comparison of global average speed tracking error m·s^-1

拓扑结构	速度跟随策略	对比策略
PF	1.1387	2.182 9
PLF	0.1811	0.305 1
BD	0.2242	0.386 5
BDL	0.1811	0.304 9
TPF	0.4049	0.691 7
TPLF	0.1811	0.304 9

下载: 导出CSV

表 14 局部平均速度跟踪误差对比

Table 14. Comparison of local average speed tracking error m·s^-1

拓扑结构	PF	BD	TPF
速度跟随策略	1.197 0	0.189 4	0.279 8
对比策略	2.347 6	0.331 0	0.483 2

下载: 导出CSV

参考文献(33)

[1]	王琼, 郭戈. 车队速度滚动时域动态规划及非线性控制[J]. 自动化学报, 2019, 45(5): 888-896. WANG Qiong, GUO Ge. Platoon speed receding horizon dynamic programming and nonlinear control[J]. Acta Automatica Sinica, 2019, 45(5): 888-896. (in Chinese)
[2]	BASIRI M H, GHOJOGH B, AZAD N L, et al. Distributed nonlinear model predictive control and metric learning for heterogeneous vehicle platooning with cut-in/cut-out maneuvers[C]//IEEE. 2020 59th IEEE Conference on Decision and Control (CDC). New York: IEEE, 2020: 2849-2856.
[3]	GHANNADPOUR S F, ZARRABI A. Multi-objective heterogeneous vehicle routing and scheduling problem with energy minimizing[J]. Swarm and Evolutionary Computation, 2019, 44: 728-747. doi: 10.1016/j.swevo.2018.08.012
[4]	杨澜, 赵祥模, 吴国垣, 等. 智能网联汽车协同生态驾驶策略综述[J]. 交通运输工程学报, 2020, 20(5): 58-72. doi: 10.19818/j.cnki.1671-1637.2020.05.004 YANG Lan, ZHAO Xiang-mo, WU Guo-yuan, et al. Review on connected and automated vehicles based cooperative eco-driving strategies[J]. Journal of Traffic and Transportation Engineering, 2020, 20(5): 58-72. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2020.05.004
[5]	DU Hao, LENG Su-peng, HE Jian-hua, et al. Digital twin based trajectory prediction for platoons of connected intelligent vehicles[C]//IEEE. 2021 IEEE 29th International Conference on Network Protocols (ICNP). New York: IEEE, 2021: 1-6.
[6]	GUO Ge, WANG Qiong. Fuel-efficient en route speed planning and tracking control of truck platoons[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(8): 3091-3103. doi: 10.1109/TITS.2018.2872607
[7]	刘平, 李振鹏, 蒋平, 等. 一种新的V2I下车速规划与模型预测控制方法[J]. 重庆交通大学学报(自然科学版), 2022, 41(7): 27-33. doi: 10.3969/j.issn.1674-0696.2022.07.05 LIU Ping, LI Zhen-peng, JIANG Ping, et al. A new method for vehicle speed planning and model prediction control under V2I[J]. Journal of Chongqing Jiaotong University (Natural Science), 2022, 41(7): 27-33. (in Chinese) doi: 10.3969/j.issn.1674-0696.2022.07.05
[8]	LI Yong-fu, TANG Chuan-cong, LI Ke-zhi, et al. Consensus- based cooperative control for multi-platoon under the connected vehicles environment[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6): 2220-2229. doi: 10.1109/TITS.2018.2865575
[9]	尹燕莉, 黄学江, 潘小亮, 等. 基于PID与Q-Learning的混合动力汽车队列分层控制[J]. 吉林大学学报(工学版), 2023, 53(5): 1481-1489. YIN Yan-li, HUANG Xue-jiang, PAN Xiao-liang, et al. Hierarchical control of hybrid electric vehicle platooning based on PID and Q-Learning algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(5): 1481-1489. (in Chinese)
[10]	YANG Jun-ru, LIU Xing-liang, LIU Shi-dong, et al. Longitudinal tracking control of vehicle platooning using DDPG-based PID[C]//IEEE. 2020 4th CAA International Conference on Vehicular Control and Intelligence (CVCI). New York: IEEE, 2020: 656-661.
[11]	闵海根, 杨一鸣, 王武祺, 等. 基于深度确定性策略梯度的队列纵向协同控制策略[J]. 长安大学学报(自然科学版), 2021, 41(4): 90-100. MIN Hai-gen, YANG Yi-ming, WANG Wu-qi, et al. Deep deterministic policy gradient based cooperative platoon longitudinal control strategy[J]. Journal of Chang'an University (Natural Science Edition), 2021, 41(4): 90-100. (in Chinese)
[12]	雷利利, 张通. 基于模糊MPC的智能车队纵向跟随控制[J]. 江苏大学学报(自然科学版), 2022, 43(4): 394-399, 430. doi: 10.3969/j.issn.1671-7775.2022.04.004 LEI Li-li, ZHANG Tong. Longitudinal following control of intelligent vehicle fleet based on fuzzy MPC[J]. Journal of Jiangsu University (Natural Science Edition), 2022, 43(4): 394-399, 430. (in Chinese) doi: 10.3969/j.issn.1671-7775.2022.04.004
[13]	翟志强, 许进亮, 袁皓, 等. 自适应巡航系统车辆跟驰控制策略仿真[J]. 系统仿真学报, 2020, 32(5): 885-891. ZHAI Zhi-qiang, XU Jin-liang, YUAN Hao, et al. Simulation on a car-following strategy for adaptive cruise control system[J]. Journal of System Simulation, 2020, 32(5): 885-891. (in Chinese)
[14]	GOLI M, ESKANDARIAN A. MPC-based lateral controller with look-ahead design for autonomous multi-vehicle merging into platoon[C]//IEEE. 2019 American Control Conference. New York: IEEE, 2019: 5284-5291.
[15]	付智俊, 郭启翔, 何薇, 等. 基于前车意图识别的自动驾驶车辆实时避障换道策略研究[J]. 汽车电器, 2020(12): 1-7, 11. FU Zhi-jun, GUO Qi-xiang, HE Wei, et al. Research on real-time obstacle avoidance and lane change strategy of autonomous vehicles based on front vehicle intention recognition[J]. Auto Electric Parts, 2020(12): 1-7, 11. (in Chinese)
[16]	贾彦峰, 曲大义, 林璐, 等. 基于运行轨迹的网联混合车流速度协调控制[J]. 吉林大学学报(工学版), 2021, 51(6): 2051-2060. JIA Yan-feng, QU Da-yi, LIN Lu, et al. Coordinated speed control of connected mixed traffic flow based on trajectory[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51(6): 2051-2060. (in Chinese)
[17]	张一鸣, 周兵, 吴晓建, 等. 基于前车轨迹预测的高速智能车运动规划[J]. 汽车工程, 2020, 42(5): 574-580, 587. ZHANG Yi-ming, ZHOU Bing, WU Xiao-jian, et al. Motion planning of high speed intelligent vehicle based on front vehicle trajectory prediction[J]. Automotive Engineering, 2020, 42(5): 574-580, 587. (in Chinese)
[18]	CHEN Chong-pu, GUO Jian-hua, GUO Chong, et al. Adaptive cruise control for cut-in scenarios based on model predictive control algorithm[J]. Applied Sciences, 2021, 11(11): 5293. doi: 10.3390/app11115293
[19]	张涛, 邹渊, 张旭东, 等. 考虑并线的网联车辆巡航控制研究[J]. 汽车工程, 2019, 41(9): 1028-1035. ZHANG Tao, ZOU Yuan, ZHANG Xu-dong, et al. A research on connected cruise control with consideration of merging[J]. Automotive Engineering, 2019, 41(9): 1028-1035. (in Chinese)
[20]	姚程文, 杨苹, 刘泽健. 基于CNN-GRU混合神经网络的负荷方法[J]. 电网技术, 2020, 44(9): 3416-3423. YAO Cheng-wen, YANG Ping, LIU Ze-jian. Load forecasting method based on CNN-GRU hybrid neural network[J]. Power System Technology, 2020, 44(9): 3416-3423. (in Chinese)
[21]	刘占文, 赵祥模, 李强, 等. 基于图模型与卷积神经网络的交通标志识别方法[J]. 交通运输工程学报, 2016, 16(5): 122-131. doi: 10.19818/j.cnki.1671-1637.2016.05.014 LIU Zhan-wen, ZHAO Xiang-mo, LI Qiang, et al. Traffic sign recognition method based on graphical model and convolutional neural network[J]. Journal of Traffic and Transportation Engineering, 2016, 16(5): 122-131. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2016.05.014
[22]	WEI Yu-guang, LIU Jiang-tao, BELEZAMO B, et al. Dynamic programming-based multi-vehicle longitudinal trajectory optimization with simplified car following models[J]. Transportation Research Part B: Methodological, 2017, 106: 102-129. doi: 10.1016/j.trb.2017.10.012
[23]	TAKAPOUI R, MOEHLE N, BOYD S, et al. A simple effective heuristic for embedded mixed-integer quadratic programming[C]//IEEE. 2016 American Control Conference (ACC). New York: IEEE, 2016: 5619-5625.
[24]	梁萌. 基于五次多项式算法的机器人轨迹规划研究[J]. 粘接, 2020, 44(11): 70-73. LIANG Meng. Research on robot trajectory planning based on quintic polynomial algorithm[J]. Adhesion, 2020, 44(11): 70-73. (in Chinese)
[25]	罗李平, 俞元洪, 罗振国. 三阶非线性中立型微分方程的振动分析[J]. 系统科学与数学, 2016, 36(4): 551-559. LUO Li-ping, YU Yuan-hong, LUO Zhen-guo. Oscillation analysis of third-order nonlinear-neutral differential equations[J]. Journal of Systems Science and Mathematical Sciences, 2016, 36(4): 551-559. (in Chinese)
[26]	石英男, 胥光申, 盛晓超. 基于七次多项式插值的RRT避障规划[J]. 轻工机械, 2022, 40(6): 1-6. doi: 10.3969/j.issn.1005-2895.2022.06.001 SHI Ying-nan, XU Guang-shen, SHENG Xiao-chao. RRT obstacle avoidance planning based on seventh degree polynomial interpolation[J]. Light Industry Machinery, 2022, 40(6): 1-6. (in Chinese) doi: 10.3969/j.issn.1005-2895.2022.06.001
[27]	ZHENG Yang, EBEN LI S E, WANG Jian-qiang, et al. Stability and scalability of homogeneous vehicular platoon: study on the influence of information flow topologies[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(1): 14-26. doi: 10.1109/TITS.2015.2402153
[28]	何德峰, 周丹, 罗捷. 跟随式车辆队列高效协同弦稳定预测控制[J]. 吉林大学学报(工学版), 2023, 53(3): 726-734. HE De-feng, ZHOU Dan, LUO Jie. Efficient cooperative predictive control of predecessor-following vehicle platoons with guaranteed string stability[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(3): 726-734. (in Chinese)
[29]	DARBHA S, KONDURI S, PAGILLA P R. Benefits of V2V communication for autonomous and connected vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(5): 1954-1963. doi: 10.1109/TITS.2018.2859765
[30]	李中奇, 许健. 基于改进模糊PID-Smith控制器的高速动车组停车方法[J]. 交通运输工程学报, 2020, 20(4): 145-154. doi: 10.19818/j.cnki.1671-1637.2020.04.011 LI Zhong-qi, XU Jian. High-speed EMU parking method based on improved fuzzy PID-Smith controller[J]. Journal of Traffic and Transportation Engineering, 2020, 20(4): 145-154. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2020.04.011
[31]	GIL P, SEBASTIÃO A, LUCENA C. Constrained nonlinear-based optimisation applied to fuzzy PID controllers tuning[J]. Asian Journal of Control, 2018, 20(1): 135-148. doi: 10.1002/asjc.1549
[32]	王力斌, 刘树伟. 基于模糊推理的油门防误踩系统控制研究[J]. 控制工程, 2020, 27(8): 1462-1467. WANG Li-bin, LIU Shu-wei. Research on the control system of preventing false stepping the accelerating pedal based on the fuzzy theory[J]. Control Engineering of China, 2020, 27(8): 1462-1467. (in Chinese)
[33]	ZHU Yan-liang, QIAN De-heng, REN Dong-chun, et al. StarNet: pedestrian trajectory prediction using deep neural network in star topology[C]//IEEE. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York: IEEE, 2019: 8075-8080.